{"as_of":"2026-08-16T11:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a598233d0ddd1c1b6d8ff00eeca7d9d8ebc40c6143967904b2c0b82e36c9f0c1","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:46:00.290506Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.06537/citation-record","integrity":"/paper/1908.06537/integrity","json":"/paper/1908.06537/citation-record.json","paper":"/paper/1908.06537"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:01.046108Z","title":"Dense semantic correspondence where every pixel is a classifier","venue":null,"work_id":"bf51707f-d0ed-4edb-80a8-66138090db34","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.028049Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:2cc9d50714ffde73fe3e2e82c639366c1a5f855910b0df211c930f844ac51b7e","observation_id":"954e36e2-9c87-49ab-b6fb-5041fbf7b56c","resolution":{"observed_at":"2026-08-14T12:46:01.050628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:01.027667Z","title":"Detect what you can: De- tecting and representing objects using holistic models and body parts","venue":null,"work_id":"a75cc80e-faac-4826-b414-7310214628c5","year":2014},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.033866Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:a44a861b21cdd77695b4a6dc5434d1c9f2cc74cfb0db8696f5916c44c8f2ecd7","observation_id":"c9941350-1d81-469f-a302-27418f6ccd8c","resolution":{"observed_at":"2026-08-14T12:46:01.035510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:01.000080Z","title":"Learning graphs to match","venue":null,"work_id":"8b90a16d-cb70-44e0-951c-ed747b251f87","year":2013},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.040971Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:d75636c77a22286b2101d37f09e54aa8062fe120cd214590ca13788f248ca752","observation_id":"b5605077-c9c7-4bed-abbb-5fee935899d4","resolution":{"observed_at":"2026-08-14T12:46:01.005016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.975692Z","title":"Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals","venue":null,"work_id":"3802a9ad-8ee9-418c-bf5a-ae7ba19d4839","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.047446Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:d428cf509431455be5d060b1a2939dc46fae02efc4690d5431907cf16ed2df52","observation_id":"54a708da-dbf2-49a9-a59a-2a4328614895","resolution":{"observed_at":"2026-08-14T12:46:00.980570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.961641Z","title":"Universal correspondence network","venue":null,"work_id":"65a8f819-e18b-4615-ad9d-f69329b92382","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.055677Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:96b59506e602552253bdad7793ae561919bf784c993f69a220f1769c322485d1","observation_id":"6e3162b4-adfa-490c-8e00-a256280a50c0","resolution":{"observed_at":"2026-08-14T12:46:00.966898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.947763Z","title":"Histograms of oriented gradi- ents for human detection","venue":null,"work_id":"086c2318-ba23-4746-9396-f06900a7e3ca","year":2005},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.062053Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:1cc84342926bc38bc281c707d28b2b39724050d3857a849f32386a562e7c051d","observation_id":"eb8b006f-9130-428c-9e26-cd4af30ae479","resolution":{"observed_at":"2026-08-14T12:46:00.952448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.934155Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"5cbc57ae-4d05-40d9-960d-fc2d2d0c5f09","year":2009},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.072184Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:0caa05ec16b7a8aa3d25b7196982ed220452c14d83695221596a694481d9d1d4","observation_id":"28a4cb2f-ceae-44c1-a2e6-33529a5ac3b9","resolution":{"observed_at":"2026-08-14T12:46:00.939205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.921975Z","title":"Approximate thin plate spline mappings","venue":null,"work_id":"0ffa2138-df92-4527-bd9f-f86056e17033","year":2002},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.081724Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:eda0191ea95017caafb7f95e299070e9a775126c5728d846d3de28b4fa1ef7fc","observation_id":"fda83724-5f6e-4db6-bc53-1754afbc7292","resolution":{"observed_at":"2026-08-14T12:46:00.926448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.909498Z","title":null,"venue":null,"work_id":"e8d0fba4-f41a-4e16-9aa0-bc2458a2d834","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.087742Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:1e5e0c4c96ffb60b94306e4e6d6e4d2ba43bd4a20aa17814e78a152e62b139a2","observation_id":"d272c252-e877-4895-b9da-687b2242ecfa","resolution":{"observed_at":"2026-08-14T12:46:00.913663Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.896518Z","title":"Hierarchical metric learning and matching for 2d and 3d geometric correspon- dences","venue":null,"work_id":"476e5e29-1520-4af3-ad8d-53378a204976","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.093796Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:86e3f287fc64d161c43813adfc6496d6c947f03af92a6090d94ae44b82c7205a","observation_id":"a284438e-8bf6-4e95-8a54-eec3abca65c2","resolution":{"observed_at":"2026-08-14T12:46:00.900806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.883553Z","title":"Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories","venue":null,"work_id":"de1f047f-3c1f-49c3-a4f7-b00652d5247e","year":2004},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.098831Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:850864e8fc1d16d1565fe833d89a5ab563b90e7792dc0606cd42083479275f34","observation_id":"45e4e7bc-1560-4832-bd37-2484561e3f26","resolution":{"observed_at":"2026-08-14T12:46:00.887955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.869904Z","title":"Deformable part models are convolutional neural net- works","venue":null,"work_id":"5a6afb17-8482-4aa8-88b0-47945201ea58","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.103169Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:0f98ff5b54552123d254b79062c95a23de11038d2f3c51c92e8d818fa16dee11","observation_id":"fdd2fbda-79a3-470a-8ccd-592c74b204f8","resolution":{"observed_at":"2026-08-14T12:46:00.874871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.856072Z","title":"Caltech-256 object category dataset","venue":null,"work_id":"aac1ddb2-8956-4a39-948b-a3295ebb4a5c","year":2007},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.107901Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:46900e6c8c479e8895f4a36d9b7a6b1012422ade14b5355b11ce8a892b364fa0","observation_id":"155fd1d6-52dd-425d-824b-80714360564f","resolution":{"observed_at":"2026-08-14T12:46:00.861159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.842916Z","title":"Proposal flow","venue":null,"work_id":"ef299eed-38ea-422e-beab-2fc251e77715","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.112268Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:33c6e0cc8dfcead3decb375809fb99d9a3d0cc3d6923007c4b7aa4318ce5f09f","observation_id":"a95cee06-ad15-4403-b88d-332ccfb1b866","resolution":{"observed_at":"2026-08-14T12:46:00.847802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.828727Z","title":"Proposal flow: Semantic correspondences from ob- ject proposals","venue":null,"work_id":"d08ae73f-c06e-44cc-a951-f8566e928af8","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.116935Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:602d9ff3e1c9856c32418d03906aafa370fa9215c7ef33f4d28b890984c71ee9","observation_id":"52854131-60bf-4c2e-a20a-0cad9cf13ae5","resolution":{"observed_at":"2026-08-14T12:46:00.833366Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.815533Z","title":"Scnet: Learning semantic correspondence","venue":null,"work_id":"b02edc51-a316-4ab0-aeed-5145ff8b846b","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.121204Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:330ac20e835db5c1155aaa8a36fd6744ffb7abae96bdd7db0bfbd3fe095cb8f9","observation_id":"01a7f0b3-3779-4b11-a055-6176e22039e5","resolution":{"observed_at":"2026-08-14T12:46:00.819844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.802243Z","title":"Semantic contours from inverse detectors","venue":null,"work_id":"96b07396-1425-41f9-95a9-c6018743dbd4","year":2011},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.126048Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:f4e3bdd6669594ecb057ca044d16685425e4c9e7c2de751afdb3f20e370d7d1e","observation_id":"3150a1de-aca6-4b24-8200-9f8d6037dbf3","resolution":{"observed_at":"2026-08-14T12:46:00.807042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.788035Z","title":"Hypercolumns for object segmentation and fine-grained localization","venue":null,"work_id":"d340270e-0eec-4c71-9e54-a6efddd8fd3d","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.130747Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:5088550b9851a30c2238342bfb6572b9d5464e183d8e4774281644ad305525cf","observation_id":"845f3a96-0bbb-49fd-9699-507dffe06f3e","resolution":{"observed_at":"2026-08-14T12:46:00.792609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.774397Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"39223444-ce34-4d8a-8954-fe9dc9df0190","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.134832Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:1e9e3ba88f3ff62b6da75a44e3a980a19cbe23789b7f2af5f7d32a15ad6e8c27","observation_id":"4c1ffce0-a007-4601-93bf-f492c5c69508","resolution":{"observed_at":"2026-08-14T12:46:00.778713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.761001Z","title":"Parn: Pyramidal affine regression net- works for dense semantic correspondence","venue":null,"work_id":"d5e21fd3-daab-4993-b8af-6126bb1ebfb3","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.139030Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:938a822331861085d7544af167edeedea0430a0ef9aa4d11cc7e4916d908d739","observation_id":"ba756c4f-00a2-4539-bf82-f8938ab7e6eb","resolution":{"observed_at":"2026-08-14T12:46:00.765932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.748473Z","title":"Warpnet: Weakly supervised matching for single- view reconstruction","venue":null,"work_id":"a35d82ea-37e6-4d0e-9daf-78eddeb3fe30","year":null},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.145071Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:3325c97621699d3c67f5f1ebd7c41cfce8678c89c11ea34d87f14424a2b5d4a2","observation_id":"0109daa5-393a-4b69-9ee5-1a72efdb0393","resolution":{"observed_at":"2026-08-14T12:46:00.753274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.736564Z","title":"De- formable spatial pyramid matching for fast dense correspon- dences","venue":null,"work_id":"df1d6860-7a44-41c8-874b-d44e6e8f1198","year":2013},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.149360Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:43af29d0e0b46a2632f740b39f8b5c7e2148ad4e839436781d4a890e3c990046","observation_id":"03c790ec-605c-43e6-9ce5-8675005bb4ce","resolution":{"observed_at":"2026-08-14T12:46:00.740822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.723918Z","title":"Recurrent transformer networks for semantic correspondence","venue":null,"work_id":"aa68cd4b-d9ce-4414-a056-a280dc4677d0","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.153848Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:d012f5226a9ccacd191ef532a32b08cdff55cb825f90a836a15e97454b583ea8","observation_id":"9c35aa14-f297-4780-a455-c9575f5e2cff","resolution":{"observed_at":"2026-08-14T12:46:00.728771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.710940Z","title":"Fcss: Fully con- volutional self-similarity for dense semantic correspondence","venue":null,"work_id":"628f7ca2-0216-4b1b-a8c5-a3f22d932254","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.158019Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:c09e4bfd639bee153c0448af3b08190a8b4a4f0153aabc63ee7ad1ed9c7a14ab","observation_id":"7e040368-71c1-4629-bc38-d0d931ff0578","resolution":{"observed_at":"2026-08-14T12:46:00.715666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.698480Z","title":"Dctm: Discrete-continuous transforma- tion matching for semantic flow","venue":null,"work_id":"98a718fc-4bb4-4b61-8ff6-0567a08fbf83","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.162640Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:f6c842890fd96483264ca60eb07ee65e8405536f82d62ce3b263d7e63741717e","observation_id":"f67415ea-c565-481c-b338-69268e1f096f","resolution":{"observed_at":"2026-08-14T12:46:00.703111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.684979Z","title":"Hypernet: Towards accurate region proposal generation and joint object detection","venue":null,"work_id":"73474e39-3740-440c-9334-9ebcf80ea264","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.167190Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:970bdaf0f16b52607179f32c0b3f974e3037144ffce1f2fd09d9954fbb346a71","observation_id":"20826d8b-c51b-43a2-a423-cbaabcdd30c8","resolution":{"observed_at":"2026-08-14T12:46:00.689160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.672685Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"262ec4fd-d59c-4b3c-8139-1e513f78ce47","year":2012},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.171995Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:752a7defb7126fb4d856f824f64f8986051c4791f65accd8f500e9b99c54cdb4","observation_id":"b87e81ae-60f1-48ef-800d-b0f36f194449","resolution":{"observed_at":"2026-08-14T12:46:00.676981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08341","last_updated":"2019-01-24T10:48:39Z","snapshot_observed_at":"2026-08-14T17:26:33.618239Z","submitted_at":"2019-01-24T10:48:39Z","title":"Semantic Matching by Weakly Supervised 2D Point Set Registration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08341","snapshot_observed_at":"2026-08-14T12:46:00.176542Z","title":"Se- mantic matching by weakly supervised 2d point set registra- tion","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.176542Z"},"links":{"cited_paper":"/paper/1901.08341","citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:f41becf686133d57d7d73200ed7e18d8db66fd1b59bce1e72f5924577e506e9f","observation_id":"0c08261c-4ecc-49b8-9754-a71f634cc1c9","resolution":{"observed_at":"2026-08-14T12:46:00.176542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.660764Z","title":"One-shot learning of object categories","venue":null,"work_id":"dcf96f72-b7df-4bba-867c-25b346c4d5ce","year":2006},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.181444Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:195d235a0502c434857f9f6352806ec82e0659d920a404c7e8746d56484ae53c","observation_id":"399c6b6a-58c6-4d81-be7a-a71a36fa9689","resolution":{"observed_at":"2026-08-14T12:46:00.664762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.648544Z","title":"Feature pyramid networks for object detection","venue":null,"work_id":"56a3d71f-8a58-4c75-a900-6e7be5479077","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.185575Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:e4e59486b6b935f786729e69d8280487a36656bedf0a166dbfa4dc9b85077633","observation_id":"c58c75ac-127c-4f07-9913-5c68255df7ce","resolution":{"observed_at":"2026-08-14T12:46:00.652490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.636592Z","title":"Jointly optimizing 3d model fitting and fine-grained classification","venue":null,"work_id":"2fefb4c8-13c8-46ea-b72b-c7e657b145ab","year":2014},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.189930Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:5b386c6eb95f610968737a67a9299b4c5c6cc346bbba808c2a9e77b584c7a266","observation_id":"2201dd96-f23d-4e93-9b5c-f777bd94432b","resolution":{"observed_at":"2026-08-14T12:46:00.640608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.624318Z","title":"Sift flow: Dense correspondence across scenes and its applications","venue":null,"work_id":"c19a0dae-50f2-43f2-9623-2667591663da","year":2008},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.194562Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:5f1948ff095e6670ffbe931354aed9e3344438e5ef9df756654a7a36262894ab","observation_id":"4a31cd6b-39fe-4ba3-b84d-c7793d022839","resolution":{"observed_at":"2026-08-14T12:46:00.628608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.611693Z","title":"DARTS: Differentiable architecture search","venue":null,"work_id":"2e62e66a-72d1-4b59-82d5-2fa7bdf31565","year":2019},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.198945Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:2a38fb3aa284d11fffb1fd1c2662bb3403431de4193f8e5889d04d4d458e7bc0","observation_id":"67625399-14be-41c0-81e4-eb52188d9776","resolution":{"observed_at":"2026-08-14T12:46:00.615967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.599259Z","title":"Do con- vnets learn correspondence? In Proc","venue":null,"work_id":"1c950c61-9be9-4c6d-b650-32d4902962f6","year":2014},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.203290Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:acf10a94446f60824c79bb6be25c095f9beb983cb711e10185b7e83a50d1d3bd","observation_id":"8163e004-28b3-4798-accb-7e99770c5716","resolution":{"observed_at":"2026-08-14T12:46:00.603546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.587432Z","title":"Prime object proposals with randomized prim’s algorithm","venue":null,"work_id":"f2c5d3cd-651a-437f-bd1f-d27455f73d46","year":2013},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.207838Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:091a78afa8710edad5fce978795b5933644a252df2d9c20669a9b5ab84fa20c3","observation_id":"cf52457f-999f-4ce9-99a0-120c22c7d037","resolution":{"observed_at":"2026-08-14T12:46:00.591370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.575452Z","title":"Medress, F.S","venue":null,"work_id":"54b71c16-7e62-4290-8eb5-83b871cd50ef","year":1977},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.212132Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:faf01f8f745187cd5d12f9833f241996b13d0b0f69c3499f518b563105ff65f6","observation_id":"680d63c0-8aa9-46c9-b75b-f94c5fd0dc82","resolution":{"observed_at":"2026-08-14T12:46:00.579643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.563101Z","title":"Self-supervised learning of geometrically stable features through probabilistic introspection","venue":null,"work_id":"8e99fc14-9bca-4f0e-9393-8e5f1282f912","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.217541Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:51514b01fa34d41709284aaa594a6e3ae7d918419eaa50ff9241587a05fc1bd7","observation_id":"7d9f69b1-d188-4ed3-a5a8-0d4d3af1cea9","resolution":{"observed_at":"2026-08-14T12:46:00.567304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.551749Z","title":"I have seen enough: Transferring parts across categories","venue":null,"work_id":"dc939630-3f87-4d36-ac0d-d8e96e837fac","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.222336Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:6182c36d83456a717232371ca15121fb726b0f9f53f0ed910f39cd80d1ff4f87","observation_id":"de4c1e97-17e7-4a42-bcb0-83063dcbe498","resolution":{"observed_at":"2026-08-14T12:46:00.555935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.539386Z","title":"An- chornet: A weakly supervised network to learn geometry- sensitive features for semantic matching","venue":null,"work_id":"6b9b5c8c-3d75-4f2f-bbf1-afec3efe13d9","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.226908Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:a7fb770742ba0911e0d856667344546b292488b173a540e6fb84929624f13283","observation_id":"b8ed8c28-5479-4af0-991f-a7f35cc8be98","resolution":{"observed_at":"2026-08-14T12:46:00.543540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.526852Z","title":"Multiscale combinatorial grouping for image segmentation and object proposal gener- ation","venue":null,"work_id":"d96d2bd0-d305-437a-b4d9-8e39f07d6245","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.230892Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:70ae7c5751b09529b8f31e0de9519e9b8db381e5486ca11424c7eec5194fe0ab","observation_id":"0b9fe979-657f-4f13-87a1-82c29bfdcdb4","resolution":{"observed_at":"2026-08-14T12:46:00.531060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.514601Z","title":"Convo- lutional neural network architecture for geometric matching","venue":null,"work_id":"e9c6f61b-b835-453b-bfcb-f0a47170e895","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.235251Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:75dff43d100b752df2536bd11f1195156fdb2ece7c3edda8d39571dab7c4cce9","observation_id":"a9d43556-4e5a-4c7b-ba81-dc858e102d13","resolution":{"observed_at":"2026-08-14T12:46:00.518803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.501675Z","title":"End-to- end weakly-supervised semantic alignment","venue":null,"work_id":"dfa8a192-c266-4f59-9495-9f57dbe6dde1","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.239759Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:82d162e3c9d3e4e2b24f1ce8e3108b8e430dae526bbc682c30146e1574150195","observation_id":"868c8cea-0a85-4ac1-bf83-d42fe626ae03","resolution":{"observed_at":"2026-08-14T12:46:00.506599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.488033Z","title":"Neighbourhood con- sensus networks","venue":null,"work_id":"0643c906-cb06-4ddf-9e94-d009a62d2d5f","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.244619Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:671d62b367fa6aa772ef349b099d0bbb4ffff9fb24d7836fb7caab50f959589e","observation_id":"94ce9214-163d-45f9-b541-aef2634f7f76","resolution":{"observed_at":"2026-08-14T12:46:00.492498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.474097Z","title":"Unsupervised joint object discovery and segmentation in internet images","venue":null,"work_id":"e0e47811-a272-4649-bfdc-00aa900d97a5","year":1939},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.248656Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:6775222675bc0ca86f558ea8175350f2f513baaf1943f5e3ba1dde9eeb2ee04c","observation_id":"3ad9d188-d572-44b7-ae3e-200e6f5e78f2","resolution":{"observed_at":"2026-08-14T12:46:00.478953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.459820Z","title":"Attentive semantic alignment with offset-aware correlation kernels","venue":null,"work_id":"9a069963-3f39-42b0-8eb9-f5b5c32e274f","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.253140Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:81c487a68dc3f83550792d9e8612957f7e09a10e73e37a234085a39862cb5fbf","observation_id":"09fbf33c-815d-4f6d-ba99-899b90fc2466","resolution":{"observed_at":"2026-08-14T12:46:00.464353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.447575Z","title":"Joint re- covery of dense correspondence and cosegmentation in two images","venue":null,"work_id":"e54b8045-bb10-4481-adcf-92a3daeb22ac","year":2016},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.257027Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:22ed206134a3180e7289dfd634729490c0d1839fa0c4106b5521ffac16f1735b","observation_id":"bfad372e-89df-44f5-a946-91ea4276f0bb","resolution":{"observed_at":"2026-08-14T12:46:00.452012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.435412Z","title":"Deep semantic feature matching","venue":null,"work_id":"0ebc3a71-c0de-4482-b07d-56c5925e4ed4","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.261489Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:4df611659579a16b24093a7bed08a3cf834d78cf6d12a68a3f722088e7fd61d9","observation_id":"a2771d98-bbf4-41a8-b830-5cc878c95c14","resolution":{"observed_at":"2026-08-14T12:46:00.439471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.422126Z","title":"Selective search for ob- ject recognition","venue":null,"work_id":"36256faa-3ab4-40df-a114-7cffb328e7a3","year":2013},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.265697Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:dc249185818c8a7053c4b250ba08879f526c71705792de035e463afe046f953e","observation_id":"d1559bcb-2ee0-4a4b-9710-33283ba81241","resolution":{"observed_at":"2026-08-14T12:46:00.426408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.269344Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.269344Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:ad69c55a8d9688bed48849b58c88d3d7a61667b7d776c25677df0247c32e8d4c","observation_id":"38230954-7a18-439b-b651-d447f2469f87","resolution":{"observed_at":"2026-08-14T12:46:00.269344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.398789Z","title":"Beyond pascal: A benchmark for 3d object detection in the wild","venue":null,"work_id":"84b415db-2f0f-4445-9fd1-5c2ed6b5a86c","year":2014},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.273205Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:5d828c4b3ab785d8c818dcbb33963cc35d6776202402415a1ac720b5a7a54068","observation_id":"aad45cb2-8e30-4265-b0e7-738d323c020e","resolution":{"observed_at":"2026-08-14T12:46:00.404426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.01569","last_updated":"2019-04-08T17:50:26Z","snapshot_observed_at":"2026-08-14T16:52:49.494726Z","submitted_at":"2019-04-02T17:57:16Z","title":"Exploring Randomly Wired Neural Networks for Image Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.01569","snapshot_observed_at":"2026-08-14T12:46:00.277262Z","title":"Girshick, and Kaiming He","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.277262Z"},"links":{"cited_paper":"/paper/1904.01569","citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:77df07b905c11c9a816a2de3f6035847c935670ab5535a2427984ced887c4469","observation_id":"bab47ca8-2e5d-47d5-8571-d99a63fec14b","resolution":{"observed_at":"2026-08-14T12:46:00.277262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.383807Z","title":"FlowWeb: Joint image set alignment by weaving con- sistent, pixel-wise correspondences","venue":null,"work_id":"b16c6979-d7d7-47a8-a7dd-bfcb27546146","year":2015},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.282092Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:1511d799a81b8d5ba3d8a5132f4d2d878d635be063fb37dc66f6dfe63bac1341","observation_id":"cc2dff21-df04-45ad-9615-db9fe5a4f59a","resolution":{"observed_at":"2026-08-14T12:46:00.388879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.368703Z","title":"Neural architecture search with reinforcement learning","venue":null,"work_id":"f86d27e6-3456-41df-8f6d-709f4438dace","year":2017},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.286410Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:1a24e0f139c1a996fdb91bc6704e7c819a033f15866f12555c571a87faf63efe","observation_id":"166d10f7-757a-4b18-8699-be3edaaaeb47","resolution":{"observed_at":"2026-08-14T12:46:00.373850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:46:00.352448Z","title":null,"venue":null,"work_id":"6cb83f2c-4c60-4151-9c97-1a29c520ab03","year":2018},"citing_paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T12:46:00.290506Z"},"links":{"citing_paper":"/paper/1908.06537"},"observation_digest":"sha256:d63edf5fe8a6dda0ca8f006161c3d7c0e3cf40a7c275e8fef73b2754b630d739","observation_id":"8da0d8ef-8828-400c-9390-3e24a9a2bdb2","resolution":{"observed_at":"2026-08-14T12:46:00.358177Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.06537","last_updated":"2019-08-18T23:23:54Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T12:39:19.411887Z","submitted_at":"2019-08-18T23:23:54Z","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":49},"total_outbound_references":54},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:1908.06537."}