{"as_of":"2026-08-16T12:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ce92379d46ec49f7fb94d7f79f43443d70bd43e0aed0689a9da47274224efadf","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:37:37.887940Z","state":"measured"},{"denominator":49,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":49,"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/1908.08692/citation-record","integrity":"/paper/1908.08692/integrity","json":"/paper/1908.08692/citation-record.json","paper":"/paper/1908.08692"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:37:38.591653Z","title":"Divide and grow: Capturing huge diversity in crowd images with incrementally growing cnn","venue":null,"work_id":"74d1257a-dcf6-439b-a2d1-fea1a5fddf7f","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.682686Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:d82994bcc16a200820075ab4a8ac02fa1fcd5139adf92e7ffb3909bd87b8cfd3","observation_id":"1522b391-1808-45b4-ba5e-aa77ccebc05d","resolution":{"observed_at":"2026-08-14T11:37:38.596669Z","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":"1511.00561","last_updated":"2016-10-10T21:11:59Z","snapshot_observed_at":"2026-08-14T22:25:13.259510Z","submitted_at":"2015-11-02T15:51:03Z","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.00561","snapshot_observed_at":"2026-08-14T11:37:37.687887Z","title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.687887Z"},"links":{"cited_paper":"/paper/1511.00561","citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:2d94811cb81d6479d9aa779850487a7061ab9ce278380a012481adf50efa5b80","observation_id":"b6970c66-5fbe-4a39-8f35-669b3709770a","resolution":{"observed_at":"2026-08-14T11:37:37.687887Z","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":"2026-08-14T11:37:38.577663Z","title":"Crowdnet: A deep convolutional network for dense crowd counting","venue":null,"work_id":"470d5538-80c4-4db5-923a-20a55180790d","year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.693018Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:ea13c9a3e5a2b07eac7830812c3eaecb8516c70f35b2ff5fb0ab23eaf810d0f6","observation_id":"25b3810d-08cc-49e6-bde5-06fa88049874","resolution":{"observed_at":"2026-08-14T11:37:38.582361Z","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":"2026-08-14T11:37:38.563404Z","title":"Scale aggregation network for accurate and efficient crowd count- ing","venue":null,"work_id":"d8137b07-531b-43ce-bff6-74d35a5183a2","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.697680Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:f1352b22676cd0e4c03179936d5310436ca44eba1a00dafcb62dd1765817521f","observation_id":"d63b571c-9aa8-402a-9035-9e44ca5c519f","resolution":{"observed_at":"2026-08-14T11:37:38.567481Z","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":"2026-08-14T11:37:38.548778Z","title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs","venue":null,"work_id":"b2e311dc-fd2e-4b07-b839-b2ea23324d7a","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.702251Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:349a762c115799f7a462a0b532456a4b42b7b0901e3aa75d10c2994eb0502109","observation_id":"da1cf41c-f8fe-429b-ae2b-d31d510e513a","resolution":{"observed_at":"2026-08-14T11:37:38.553485Z","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":"2026-08-14T11:37:38.533486Z","title":"Crf-cnn: Modeling structured information in human pose estimation","venue":null,"work_id":"5cb8b9bf-8bda-4d75-94c0-0696d790b6c8","year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.707020Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:4dfc7b38c51c9dfec5fd9da8c8920da57cf16263584bb72cb19b5d65042da2c1","observation_id":"ee1aa863-e8ef-43c4-9f95-e014d8080b46","resolution":{"observed_at":"2026-08-14T11:37:38.539107Z","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":"2026-08-14T11:37:38.519028Z","title":"Pcc net: Perspective crowd counting via spatial convolutional network","venue":null,"work_id":"c129be92-0eec-4464-9fed-5636a5d37cc6","year":2019},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.712124Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:469700439526e0a465b6a692fba572f6ad502c1865320c3bda3873863d579cc5","observation_id":"bf2f971e-0ca5-4e00-87de-683b3e444e34","resolution":{"observed_at":"2026-08-14T11:37:38.523571Z","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":"2026-08-14T11:37:38.504086Z","title":"Marked point processes for crowd counting","venue":null,"work_id":"147186bd-2878-4eaa-ad00-e4d5a8ff919a","year":2009},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.716423Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:47d4f1316921a5c9ac3c2b9af54d23d13438de39a04488822e8905536a29eee6","observation_id":"eee2e52e-8fcb-472f-97c1-f491a4add09e","resolution":{"observed_at":"2026-08-14T11:37:38.509454Z","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":"2026-08-14T11:37:37.721076Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.721076Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:fa77b2253d161d2b8fda2c8e09ec370d716fe9d61fcf6c63c5ddf4221f893bb4","observation_id":"8249d808-cddd-4e86-af4e-27774e1d599c","resolution":{"observed_at":"2026-08-14T11:37:37.721076Z","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":"2026-08-14T11:37:38.480393Z","title":"Densely connected convolutional net- works","venue":null,"work_id":"ee828421-134c-4ac3-941b-d56cd412c6a7","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.725587Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:6fa86acd3a298da508016d0259b0acfacbe51bb8bead0ffc2d351a009ad98cc5","observation_id":"552d1138-19f0-4853-95a2-7a323f4bfeb9","resolution":{"observed_at":"2026-08-14T11:37:38.485124Z","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":"2026-08-14T11:37:38.465455Z","title":"Multi-source multi-scale counting in extremely dense crowd images","venue":null,"work_id":"5811a28f-c7e2-4080-9f0c-3a83173f3f3d","year":2013},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.730256Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:783d80d7e0841a23dae0017f219ff826ec3e07d8a5bab450a9488efc3bd89b7b","observation_id":"bf8a8c99-398d-46e2-a0b3-0f8d4f09b619","resolution":{"observed_at":"2026-08-14T11:37:38.470545Z","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":"2026-08-14T11:37:38.451224Z","title":"Composition loss for counting, density map estima- tion and localization in dense crowds","venue":null,"work_id":"515dff84-c1d7-4802-8479-02c3efe77f3d","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.734841Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:b8808e03b95823359ca020ec4f35bb6982fe984c28c0879bfe2abcc952f0ee86","observation_id":"a1433068-d6e9-41cc-9949-3f6ef2233411","resolution":{"observed_at":"2026-08-14T11:37:38.455183Z","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":"2026-08-14T11:37:38.438472Z","title":"Crowd counting by adaptively fusing predictions from an image pyramid","venue":null,"work_id":"d98bf2df-5a9f-43ab-aacf-0b321a1a6301","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.739343Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:fc52f419a3eb8663495220a2992a39ce258bec2bed8bcbc9aa9f33368ddf0978","observation_id":"3e03b9fc-dddf-4eda-9863-d06a3c982cfa","resolution":{"observed_at":"2026-08-14T11:37:38.442423Z","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":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T11:37:37.743868Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.743868Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:e3c472b8e08e2cbd76f997369fa3879462ffe32a6dd9f3e9e780808d280b08f5","observation_id":"e2badad3-e428-4ed5-9736-e31aa5f0cfdb","resolution":{"observed_at":"2026-08-14T11:37:37.743868Z","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":"2026-08-14T11:37:38.423338Z","title":"Efficient inference in fully connected crfs with gaussian edge potentials","venue":null,"work_id":"3bb32fc0-a035-4daa-8bf9-22e0edf2cd17","year":2011},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.748479Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:62c309c58a56ee5670b8e87bfa27f8a43bf33c93a1674897c821363531e35b34","observation_id":"e85a1b58-9e91-47e6-8289-0c27f028fbcc","resolution":{"observed_at":"2026-08-14T11:37:38.428328Z","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":"2026-08-14T11:37:38.409162Z","title":"Conditional random fields: Probabilistic models for seg- menting and labeling sequence data","venue":null,"work_id":"83735e5e-2359-4b95-a55b-ac8439ee4848","year":2001},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.753091Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:64241a2f05dd40beca047ffebeb0462c2d779343fd5965a6f86fc14b80a5b4d3","observation_id":"e2a32c6c-36aa-4ae4-a3fa-5aab1d99a33f","resolution":{"observed_at":"2026-08-14T11:37:38.413867Z","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":"2026-08-14T11:37:38.394368Z","title":"Csrnet: Di- lated convolutional neural networks for understanding the highly congested scenes","venue":null,"work_id":"f6811333-0e8d-432d-9062-0dc77fee5da8","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.757394Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:4645e3a49578a41186c4ca14cde318bbeb441c2c0fd7a95602c5f0a19ab9f6c5","observation_id":"6abc1db8-ca21-4b2c-bbe6-1d078159b121","resolution":{"observed_at":"2026-08-14T11:37:38.399106Z","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":"2026-08-14T11:37:37.761061Z","title":"Feature pyramid networks for object detection","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.761061Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:54574cd14998a1a1f79fe76a0527a03aeb72bce9c53852507c285c5168af0f86","observation_id":"22a0a005-f830-4e94-aff0-0e1ff002f2ab","resolution":{"observed_at":"2026-08-14T11:37:37.761061Z","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":"2026-08-14T11:37:38.369212Z","title":"Decidenet: Counting varying density crowds through attention guided detection and density estimation","venue":null,"work_id":"49e17fe8-fa7a-47c0-ad2a-00a217890ee0","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.764822Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:111a7891c9a36b3e3e676ea4fe0985091eb0ab568444c4b61900ef17f1cf5e0a","observation_id":"5db8d46a-ba17-4742-ad54-d3ed9c42a5d1","resolution":{"observed_at":"2026-08-14T11:37:38.373835Z","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":"2026-08-14T11:37:38.355501Z","title":"Crowd counting using deep recurrent spatial- aware network","venue":null,"work_id":"c7018a1d-9c1a-49a1-8cca-da8368b825cc","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.768523Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:8e1ed3d8f98b589027755f44d7b9a99147d9c15d0e3ea6b3ab6b872ac6e06dda","observation_id":"7ec483c5-cd52-47d9-b7cc-d80282925e3c","resolution":{"observed_at":"2026-08-14T11:37:38.360032Z","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":"2026-08-14T11:37:38.341601Z","title":"Attentive crowd flow machines","venue":null,"work_id":"99773bd8-3e82-4b86-877e-41417ddc7542","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.772176Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:d5feaec3ac5f9a2b5a051c90c49b3bc649312882da492d5a60f01c7ea9cfef82","observation_id":"64ab284f-5443-4af1-92b4-4197d075812f","resolution":{"observed_at":"2026-08-14T11:37:38.345994Z","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":"1811.11968","last_updated":"2019-04-11T06:27:08Z","snapshot_observed_at":"2026-08-14T17:51:35.660664Z","submitted_at":"2018-11-29T05:10:03Z","title":"ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.11968","snapshot_observed_at":"2026-08-14T11:37:37.775956Z","title":"Adcrowdnet: An attention-injective deformable convolutional network for crowd understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.775956Z"},"links":{"cited_paper":"/paper/1811.11968","citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:291c9d840f3cb873b2a2d349a162f75e720572c1281185d96609fd37f1b67316","observation_id":"1f87f9ba-c6f4-42c7-bc6d-d57c2dbf1774","resolution":{"observed_at":"2026-08-14T11:37:37.775956Z","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":"2026-08-14T11:37:38.327680Z","title":"Geometric and physical constraints for drone- based head plane crowd density estimation","venue":null,"work_id":"01d8a179-433a-42c1-840f-4cf28a9e428e","year":2019},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.780018Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:ceeecc439ed989cc7a2edace17c21b4eddbb43bdb0fefa5eb8a49c6a07983bc9","observation_id":"08a828c0-57b0-4e8c-bd1e-7d5765ac0784","resolution":{"observed_at":"2026-08-14T11:37:38.332219Z","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":"1811.10452","last_updated":"2019-04-15T08:32:16Z","snapshot_observed_at":"2026-08-14T17:53:17.021651Z","submitted_at":"2018-11-26T15:31:22Z","title":"Context-Aware Crowd Counting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.10452","snapshot_observed_at":"2026-08-14T11:37:37.783630Z","title":"Context- aware crowd counting","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.783630Z"},"links":{"cited_paper":"/paper/1811.10452","citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:5b81f472bc2655a275984e2e91da701440ee9e71c67533a41ca89bb28dfac420","observation_id":"d705c06d-567f-49da-9100-4cda0a936e0f","resolution":{"observed_at":"2026-08-14T11:37:37.783630Z","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":"2026-08-14T11:37:38.313903Z","title":"Towards perspective-free object counting with deep learning","venue":null,"work_id":"bd7794aa-3f89-4ce8-b5d4-754ae55d2d33","year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.787920Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:39dd41d273ea72abc27e539f6ce6fca0cd6f03fcf06e5e7bc91da15883411467","observation_id":"e767a495-2000-4b64-ba9b-c27b31f96f5e","resolution":{"observed_at":"2026-08-14T11:37:38.318089Z","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":"2026-08-14T11:37:37.792177Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.792177Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:0564822eef3b208d796ebb729973869933b5bdb4334486a683655a90ca6d2bae","observation_id":"fa09265c-a049-4152-9f21-e4905b6272f1","resolution":{"observed_at":"2026-08-14T11:37:37.792177Z","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":"2026-08-14T11:37:38.291086Z","title":"Crowd counting via multi-view scale aggre- gation networks","venue":null,"work_id":"fa68da0b-1319-4858-88a9-11e77a44fd6c","year":2019},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.796391Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:e01ff3e520dae7335cbb437a5a5fb46a15753d0893e3adbc6f92ac3e0a11cf10","observation_id":"de6dfb38-1146-46d2-815f-525ff9f57c22","resolution":{"observed_at":"2026-08-14T11:37:38.295551Z","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":"2026-08-14T11:37:38.277113Z","title":"Iterative crowd counting","venue":null,"work_id":"0f7b6583-2122-42e5-8e49-1aa20bb3451c","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.800825Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:e1cea7ddf2f57d1b00eb51a1c253ac1f5e90cb887d7bcad05ae073cdc0b841fb","observation_id":"1d866885-fc54-4a40-b93a-542d6defd284","resolution":{"observed_at":"2026-08-14T11:37:38.281539Z","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":"2026-08-14T11:37:38.263844Z","title":"Continuous conditional random fields for efficient regression in large fully connected graphs","venue":null,"work_id":"b6f6c99e-32c2-4453-a4f6-ee8e2e9d9d62","year":2013},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.805124Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:690956ba6684ff0805cb5bbca1cc3e6dc749440998e678c19c33b242e1dc46de","observation_id":"5016e021-47ab-4b7c-ab58-367096f8092d","resolution":{"observed_at":"2026-08-14T11:37:38.268322Z","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":"2026-08-14T11:37:38.248598Z","title":"Switching convolutional neural network for crowd counting","venue":null,"work_id":"f56611ae-74ab-42f6-bab4-2624633a7002","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.809456Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:db9fe1b6c99bccb17c4e4a35fbc935ef3591deb3095839ed75aa5881c72c5f95","observation_id":"2b6c5d3b-f8be-4905-bde5-62e833a432ac","resolution":{"observed_at":"2026-08-14T11:37:38.253782Z","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":"2026-08-14T11:37:38.234291Z","title":"Crowd counting via adversarial cross-scale consistency pursuit","venue":null,"work_id":"7bb9acb9-05f7-4efd-bb86-96df7af8a6c1","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.813744Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:c607689dcd2aa45fe325d314dfd65e64e5b2f14cab5cad85719f5daa11876ba2","observation_id":"32c105d9-c43a-4bf4-85f4-4d0dfc34f35d","resolution":{"observed_at":"2026-08-14T11:37:38.238894Z","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":"2026-08-14T11:37:38.221191Z","title":"Crowd count- ing with deep negative correlation learning","venue":null,"work_id":"c4fab302-a4aa-4908-b4fd-58df666695cf","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.818097Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:e06a57eca456819fcaa17449a3fdbb2c6ec1476d1d0b513ea7780414962e1718","observation_id":"7481a7b3-7454-4500-a71e-c9f4ba73c4b1","resolution":{"observed_at":"2026-08-14T11:37:38.225095Z","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":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T11:37:37.822423Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.822423Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:b39e3d5974c9a96261145783065a819ff3becd49d30ec2fb737eaad9c8eb8ceb","observation_id":"a6ba5eaa-0f44-48a5-bc28-c1d39f45d280","resolution":{"observed_at":"2026-08-14T11:37:37.822423Z","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":"2026-08-14T11:37:38.208428Z","title":"Cnn-based cas- caded multi-task learning of high-level prior and density esti- mation for crowd counting","venue":null,"work_id":"ca59382f-5b04-4c50-896a-45476606d27f","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.826882Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:a1acadd95cd7a8d3830d5332d0a1f187e619c305fa580913c6e5860e2ec22d33","observation_id":"ead61083-651d-4070-a831-4b603dde2424","resolution":{"observed_at":"2026-08-14T11:37:38.212456Z","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":"2026-08-14T11:37:38.195080Z","title":"Generating high- quality crowd density maps using contextual pyramid cnns","venue":null,"work_id":"646ed3b0-1979-427c-80bd-fd94c9c642f8","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.831053Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:6054ae0298c416ef072b470aed6228a59cbc33643512f192daa657977cb271fe","observation_id":"445b2dac-a047-474f-b927-8ce0cb5f991a","resolution":{"observed_at":"2026-08-14T11:37:38.199528Z","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":"2026-08-14T11:37:38.181325Z","title":"Learning to count with cnn boosting","venue":null,"work_id":"baa3e360-88f7-41da-9643-4143e7ffa7ec","year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.836718Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:b463f695a9d6c85725f131a0e6878981b20902f2e71d9fbd5e1faae4cb5c09c6","observation_id":"213d57eb-0ad6-4434-af17-cacdd8810802","resolution":{"observed_at":"2026-08-14T11:37:38.185904Z","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":"2026-08-14T11:37:38.167349Z","title":"Di- viding and aggregating network for multi-view action recog- nition","venue":null,"work_id":"55c0945f-1369-4f48-bce9-f33465b327da","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.841659Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:90a0ea8ea0ac6d0e71bec299b3e6d733f68c81937ad50addbdfebb9536ad2fe8","observation_id":"d2036bae-5973-4171-84dc-ef79cfaa3f25","resolution":{"observed_at":"2026-08-14T11:37:38.171618Z","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":"2026-08-14T11:37:38.153886Z","title":"Image quality assessment: from error visibility to structural similarity","venue":null,"work_id":"44faaa80-d7bf-4d14-810d-c3c32a21599a","year":2004},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.846215Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:fd9d551a5710eff051a157c9124e204651f23d81cb71c1e90c182f0409e7793c","observation_id":"ed6a4b9b-d3e8-4dba-ae93-dda7fe226dfe","resolution":{"observed_at":"2026-08-14T11:37:38.158429Z","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":"2026-08-14T11:37:38.140151Z","title":"Multi- scale structural similarity for image quality assessment","venue":null,"work_id":"98532b46-c6c3-43b1-87b8-2af9f461d90e","year":2003},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.850558Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:4d88a1c4a8e5c93fa70483101977cc1228d2dcc9218dc7b54d12804bed907ae3","observation_id":"caf2a7ea-419e-443a-ac2d-5c98c2771539","resolution":{"observed_at":"2026-08-14T11:37:38.144799Z","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":"2026-08-14T11:37:38.125796Z","title":"Spatiotempo- ral modeling for crowd counting in videos","venue":null,"work_id":"1ca1907c-2206-42a6-84b7-d7b5584e2419","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.854831Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:b250608d3cc14da322bb25f9a08dc1e7480b1508097ec32e076c40078014c23c","observation_id":"43b8e4ac-4101-487e-ad65-ce856fbee518","resolution":{"observed_at":"2026-08-14T11:37:38.130680Z","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":"2026-08-14T11:37:38.110745Z","title":"Learning deep struc- tured multi-scale features using attention-gated crfs for con- tour prediction","venue":null,"work_id":"45df57f7-c6cf-4ad5-9e7a-492e53364832","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.859156Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:b362342a95891656f2c30d06b99996c3527b0dccdb3e49bdfd632aaf1b416f1d","observation_id":"5872490f-2da1-40f4-ba64-65e751e13586","resolution":{"observed_at":"2026-08-14T11:37:38.116107Z","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":"2026-08-14T11:37:38.097378Z","title":"Multi-scale convolutional neural networks for crowd counting","venue":null,"work_id":"2c840829-08cf-4c5a-92c7-c9b62ad0d601","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.862687Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:5dfb65bde45696062ecfcc354c5db675221089ea99ee988477c1db4a4a5ecbec","observation_id":"5203d93f-73c5-43df-b1c2-d8c888c24d3b","resolution":{"observed_at":"2026-08-14T11:37:38.101600Z","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":"2026-08-14T11:37:38.082650Z","title":"Cross-scene crowd counting via deep convolutional neural networks","venue":null,"work_id":"bfe4b36c-5c00-4f65-830d-697de1b7d26d","year":2015},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.866285Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:179e6927ecff02bccd32accead318c4d8082fdfa0fd040b8f345412023395e27","observation_id":"9215ce92-f4bf-4ffe-b60b-8e703f74cd13","resolution":{"observed_at":"2026-08-14T11:37:38.087889Z","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":"2026-08-14T11:37:38.067712Z","title":"A bi-directional message passing model for salient object de- tection","venue":null,"work_id":"21d14951-4504-473d-987e-9775d851c78f","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.870004Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:2cb20de5e257d50af40efc6132c9df38ba354674fb3e467d8e7d76953137a58d","observation_id":"4fe66804-5d75-400a-b337-aadb793d71ea","resolution":{"observed_at":"2026-08-14T11:37:38.072382Z","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":"2026-08-14T11:37:38.051497Z","title":"Crowd counting via scale-adaptive convolutional neural network","venue":null,"work_id":"da77bffc-9339-478a-8e94-4669bd0134a5","year":2018},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.873505Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:772699ead6efc9095323a73cf23ce71e69ae769f92467bd41d11d2ecea2f734a","observation_id":"d40a7c67-d79c-4fd1-9d57-43065a03ded0","resolution":{"observed_at":"2026-08-14T11:37:38.056487Z","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":"2026-08-14T11:37:38.036839Z","title":"Understanding traffic density from large- scale web camera data","venue":null,"work_id":"dc143aea-5ebc-4c43-b71f-2fc6477088ff","year":null},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.877038Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:3a82c0337a5f03ab11bc654eae582c973b9e24def4ef45254ab80d37536d8f63","observation_id":"c2f94e1d-dd97-4ee0-bf82-6b05129a83d3","resolution":{"observed_at":"2026-08-14T11:37:38.041647Z","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":"2026-08-14T11:37:38.021775Z","title":"Single-image crowd counting via multi-column convolutional neural network","venue":null,"work_id":"aa4d9121-d1f2-4021-ad83-7cc6c4a887b3","year":2016},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.880743Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:277e81e066dc2d15abb2d440736a6ea47b24c5fc1c53ae543b162cddc3c165c4","observation_id":"12804c2e-2602-44d5-86e0-bb2167ddc239","resolution":{"observed_at":"2026-08-14T11:37:38.026852Z","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":"2026-08-14T11:37:38.006750Z","title":"Loss functions for image restoration with neural networks","venue":null,"work_id":"df487216-80d9-4362-84f6-e2d26590a3de","year":2017},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.884450Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:eaf942574b8c56a45a6d4f3913b41867a9182773fd4e3ba2201e8bfd8ac8114f","observation_id":"ee427ec6-6a98-4b80-b81c-758eb6c0a131","resolution":{"observed_at":"2026-08-14T11:37:38.011535Z","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":"2026-08-14T11:37:37.990055Z","title":"Conditional random fields as re- current neural networks","venue":null,"work_id":"12a35e48-687c-4685-b58a-dc7f006a5edb","year":2015},"citing_paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T11:37:37.887940Z"},"links":{"citing_paper":"/paper/1908.08692"},"observation_digest":"sha256:e5130418cfbf535e6b6cf3f9d0558fe492c9c89e2bfdd947e16321c7284f2618","observation_id":"b382590e-ca62-48d8-ac5f-1d55794679b9","resolution":{"observed_at":"2026-08-14T11:37:37.996281Z","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"}}],"paper":{"arxiv_id":"1908.08692","last_updated":"2019-08-23T06:59:36Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T10:29:05.897793Z","submitted_at":"2019-08-23T06:59:36Z","title":"Crowd Counting with Deep Structured Scale Integration Network"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":41},"total_outbound_references":49},"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 49 of 49 outbound references and 0 inbound Pith citation observations for arXiv:1908.08692."}