{"as_of":"2026-08-16T08:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3257ede9c0b656e117625ee6e0b159eddf546e82b513186e1b4f17caaf0ffe4d","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:53:12.141036Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"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/1908.06377/citation-record","integrity":"/paper/1908.06377/integrity","json":"/paper/1908.06377/citation-record.json","paper":"/paper/1908.06377"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:12.800607Z","title":"Image collection pop-up: 3d reconstruction and clustering of rigid and non-rigid categories","venue":null,"work_id":"7c49bda4-d60b-4ef5-97af-cb1f7541454e","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.958238Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:0170762e578e159243087fadec5aa7e5a2aa133108233e5eedffb04c8f749b9f","observation_id":"0181a71f-66b4-4e42-9071-5116e2b23b7d","resolution":{"observed_at":"2026-08-14T12:53:12.805427Z","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":"2026-08-14T12:53:12.787682Z","title":"Trajectory space: A dual representation for nonrigid struc- ture from motion","venue":null,"work_id":"c0e929e7-62ae-40f4-9bc0-2ea24d09153a","year":2011},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.962588Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:009f73d9057aaa318afcdfbe46add07c9ac3b289954503b4895c24f387ead13b","observation_id":"5c8dca4d-a2df-4855-ab04-836d40f0f779","resolution":{"observed_at":"2026-08-14T12:53:12.792733Z","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":"2026-08-14T12:53:12.775018Z","title":"2d human pose estimation: New benchmark and state of the art analysis","venue":null,"work_id":"0b3bed4c-6b57-402d-b058-1eaf5372d472","year":2014},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.966256Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:24b53718bdb85c7a1eb15f9f6672e4745c70c49b28c412d191997384533730d9","observation_id":"b18052e4-426f-4901-9c01-e990471a8a66","resolution":{"observed_at":"2026-08-14T12:53:12.779604Z","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":"2026-08-14T12:53:12.761760Z","title":"A fast iterative shrinkage- thresholding algorithm with application to wavelet-based im- age deblurring","venue":null,"work_id":"f05c9eb2-9398-4dec-875e-0f2faac689bb","year":2009},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.969924Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:97054728146229502eb5f3368308c948bb2d572ab54bb53deb706424e392cde0","observation_id":"75fa5976-4e71-4a87-b20c-c4d5860a3dfb","resolution":{"observed_at":"2026-08-14T12:53:12.766984Z","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":"2026-08-14T12:53:12.749228Z","title":"Recovering non-rigid 3d shape from image streams","venue":null,"work_id":"7099d7fe-21a5-4d59-820a-1bcdefb4c36d","year":2000},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.973495Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:cb072cfadc73d9badc3c86bebb53963b2b789222ce0a6bf09e74f1a13fa80290","observation_id":"b5a8940c-3249-4ee6-b203-868053d5593c","resolution":{"observed_at":"2026-08-14T12:53:12.753484Z","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":"2026-08-14T12:53:12.734938Z","title":"3d human pose es- timation = 2d pose estimation + matching","venue":null,"work_id":"df6aa8f8-7ad3-49bd-a802-797d007140f3","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.977198Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:6619f6ec8bbaa67662d960c562ddf821e8ed38c3da689115a7c5e83fabd2a939","observation_id":"d2bc7a6a-d626-45ce-a657-c6e2728b2992","resolution":{"observed_at":"2026-08-14T12:53:12.741038Z","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":"2026-08-14T12:53:12.720105Z","title":"Synthesizing training images for boosting human 3d pose estimation","venue":null,"work_id":"42a79f6b-ce1f-4720-b668-d35881f5a018","year":2016},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.981258Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:26bd5fd7a1ba1e1aea0ca187aa5c560f91c9aae132f1232a8203c46eaff8ed0b","observation_id":"ee1d5b5f-5a59-4415-a9a7-2c9a378a8925","resolution":{"observed_at":"2026-08-14T12:53:12.725258Z","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":"2026-08-14T12:53:12.706316Z","title":"Learning 3d hu- man pose from structure and motion","venue":null,"work_id":"00aa398e-8456-4aa3-bfaa-c66fa1b942ac","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.984502Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:69a439aa2be3f75527f2d7d33025d5f5ad3defaa8cf76fc7adb6915dbe593c04","observation_id":"a906caab-74d0-431a-9fb1-0d5ff6e608b3","resolution":{"observed_at":"2026-08-14T12:53:12.711693Z","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":"2026-08-14T12:53:12.692138Z","title":"A simple prior- free method for non-rigid structure-from-motion factoriza- tion","venue":null,"work_id":"50700e33-1659-4247-99db-27b9d8682952","year":2014},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.987785Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:8949aa488a6e09cc2786533d39de6b1250e3a9b81ce1fbf21a0f51f4faf87874","observation_id":"8d64ec18-0374-4b96-87c6-6168941012c6","resolution":{"observed_at":"2026-08-14T12:53:12.697493Z","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":"2026-08-14T12:53:12.677991Z","title":"An iterative thresholding algorithm for linear inverse prob- lems with a sparsity constraint","venue":null,"work_id":"936618f2-2693-4e52-9389-4d369e3b6d48","year":2004},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.990923Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:5125cacfc989aa4cababa5c6821f13245f4c5ad87014b9121c8b67b2944ec284","observation_id":"7d772552-c06c-4806-a7fc-d5a506035b30","resolution":{"observed_at":"2026-08-14T12:53:12.683078Z","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":"2026-08-14T12:53:12.665043Z","title":"Non-rigid structure from motion using ranklet-based track- ing and non-linear optimization","venue":null,"work_id":"5859c148-2f30-4ff5-9789-a5ebb03c8237","year":2007},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.994187Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:22d08382668dfe217e147b910da8c9f3686a39412310719dbb7965e888f9d103","observation_id":"80573fb3-6f4b-480c-bb9f-fa63af38b966","resolution":{"observed_at":"2026-08-14T12:53:12.668964Z","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":"2026-08-14T12:53:12.650487Z","title":"Can 3d pose be learned from 2d projections alone? In Proceedings of the European Conference on Computer Vision (ECCV) , pages 0–0, 2018","venue":null,"work_id":"48ee653d-a25c-4489-b740-b6c7bf96f46c","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:11.998244Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:b9613bc58b935b8bba71bda989c2ca5f0f56fc8ab9f29fafcfa9fc2005392f64","observation_id":"fdb1f0ce-936f-43be-acbc-456a4e917f20","resolution":{"observed_at":"2026-08-14T12:53:12.655834Z","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":"2026-08-14T12:53:12.636054Z","title":"Harley, William Seto, and Katerina Fragkiadaki","venue":null,"work_id":"58b7598e-a295-4f2c-921c-523ce3f0a889","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.002266Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:f3cc6b53c13a75b40360905ca10db34ed2084b2e5e05e296f84515dc1fe5b6d3","observation_id":"63283f5d-ce0f-40fb-a1bc-4ae9a9cdebd0","resolution":{"observed_at":"2026-08-14T12:53:12.642134Z","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":"2026-08-14T12:53:12.621163Z","title":"Unsupervised monocular depth estimation with left- right consistency","venue":null,"work_id":"fa5757ea-5ba9-46a5-a21e-105b02170cf7","year":null},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.006415Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:263f62a4842ca3eeabf58661f4f71c3cd6fe5e1975d8bc9b5fc8d4da382794c3","observation_id":"ad491d56-f65a-4f00-a681-9bb371bf460b","resolution":{"observed_at":"2026-08-14T12:53:12.626335Z","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":"2026-08-14T12:53:12.606919Z","title":"Computing smooth time trajectories for camera and deformable shape in structure from motion with occlusion","venue":null,"work_id":"da896470-e249-44c5-a1f3-2acf3b2a15eb","year":2011},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.010524Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:c7745235ea462721f52d6fb92f4db8e071c9ada173ed74b382bdc58641780ed1","observation_id":"d7dc8060-40b6-4c93-bcdb-ae295ad2b79d","resolution":{"observed_at":"2026-08-14T12:53:12.612197Z","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":"2026-08-14T12:53:12.591722Z","title":"Kernel non-rigid structure from motion","venue":null,"work_id":"7b498fb3-c677-4f6b-be0d-9a9aee41548b","year":2011},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.014477Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:d9c6297b2c26dfea18d7b7e1ca03493f814008ed681c9fd1782cf8808586fe4c","observation_id":"07b6d7e0-b6b8-42a0-8e84-42a5f2a07a2a","resolution":{"observed_at":"2026-08-14T12:53:12.597561Z","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":"2026-08-14T12:53:12.577708Z","title":"Learning spatially-smooth mappings in non-rigid structure from motion","venue":null,"work_id":"3665e4c6-e855-4d12-8377-37cacc6189be","year":2012},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.018248Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:ae09cb6d83f127bf2f46fd0c678b8f4cd8d42cb5d75e3dd968f8ed87178efa11","observation_id":"109d579c-d00c-42db-8705-470de45ddfda","resolution":{"observed_at":"2026-08-14T12:53:12.583098Z","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":"2026-08-14T12:53:12.565600Z","title":"Human3.6m: Large scale datasets and predic- tive methods for 3d human sensing in natural environments","venue":null,"work_id":"29d549c4-a088-4830-8a5f-0cbb57053e12","year":2014},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.022314Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:4a6db3fa309382248e9c9129db725ddca4b12c37f1e3d0f7aec7e6957517f49b","observation_id":"c578f1e6-9f2d-439d-bd0c-e01e525c7054","resolution":{"observed_at":"2026-08-14T12:53:12.570697Z","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":"2026-08-14T12:53:12.026564Z","title":"Panoptic studio: A massively multiview system for social motion capture","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.026564Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:2bcfb7b43bceef5185fa5440ef36c43b4abf995b0fd381d39245738714307889","observation_id":"fb4f74c1-dc4b-48a7-a2db-fdf7b5ff6288","resolution":{"observed_at":"2026-08-14T12:53:12.026564Z","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":"2026-08-14T12:53:12.543984Z","title":"Prior-less compressible struc- ture from motion","venue":null,"work_id":"8932585b-a3a2-4eea-92a5-11cc69a2a58a","year":2016},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.030646Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:9f2fc10aa58f811a6276d6d43b154ac491582fb6898600b11edf66ec6647bcb0","observation_id":"75ab4fc9-e96c-4e8c-96d6-714ce08a59bb","resolution":{"observed_at":"2026-08-14T12:53:12.548558Z","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":"1902.10840","last_updated":"2019-02-28T00:04:24Z","snapshot_observed_at":"2026-08-14T17:09:59.238831Z","submitted_at":"2019-02-28T00:04:24Z","title":"Deep Interpretable Non-Rigid Structure from Motion","version":1},"cited_work":{"arxiv_id":"1902.10840","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.10840","snapshot_observed_at":"2026-08-14T12:53:12.209579Z","title":"Deep Interpretable Non-Rigid Structure from Motion","venue":"cs.CV","work_id":"832996a9-8f12-4389-ab96-629f9cadeba6","year":2019},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.034415Z"},"links":{"cited_paper":"/paper/1902.10840","citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:5e662600c91671815bbae1f7324d7c4455af9c255315c6e8751500fbfacf6d83","observation_id":"9b01a7ee-c18f-4112-98f3-fb762ba1c59a","resolution":{"observed_at":"2026-08-14T12:53:12.214040Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-14T12:53:12.531881Z","title":"Structure from category: a generic and prior-less approach","venue":null,"work_id":"812c7cf1-12a3-4469-b4bc-2f887305b660","year":2016},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.039028Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:35040803e428bcdf0e7edb5a7ce911aac840038284a7c4379202764286a9d0dd","observation_id":"b1ffcf06-d4a9-4d27-b1f6-8498b14e8b45","resolution":{"observed_at":"2026-08-14T12:53:12.536338Z","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":"1803.00233","last_updated":"2018-03-23T22:19:20Z","snapshot_observed_at":"2026-08-14T19:40:48.085528Z","submitted_at":"2018-03-01T07:08:39Z","title":"Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective","version":2},"cited_work":{"arxiv_id":"1803.00233","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.00233","snapshot_observed_at":"2026-08-14T12:53:12.192547Z","title":"Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective","venue":"cs.CV","work_id":"63f586d0-55e2-43d5-a7aa-68feaddccb57","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.043184Z"},"links":{"cited_paper":"/paper/1803.00233","citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:6d536ada65ef632f57e818841d56f7346df30d24925c98b80386524799db0c8f","observation_id":"ba436052-6948-4c64-95b6-c43baab81ec7","resolution":{"observed_at":"2026-08-14T12:53:12.196689Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-14T12:53:12.517541Z","title":"Multi- body non-rigid structure-from-motion","venue":null,"work_id":"7867f0ac-4cab-4ff0-84b0-810297390119","year":2016},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.047615Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:d2c2bfac382e5d1c447068a36a59c177d03fd2d6d7bad2b0906d7ef5760f2892","observation_id":"b31a9537-9717-4e30-ab16-93f68eac42c4","resolution":{"observed_at":"2026-08-14T12:53:12.522827Z","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":"2026-08-14T12:53:12.504418Z","title":"Consensus of non-rigid reconstructions","venue":null,"work_id":"671bc6be-5926-44bf-9487-9ef91e007af5","year":2016},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.051102Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:d005769a7a052e4eb8ad70eb38f491ef3ebccdbf67a9f79bab8e5593aac9ecca","observation_id":"d12d3d7e-1714-4bfc-b0ed-ea89544e48da","resolution":{"observed_at":"2026-08-14T12:53:12.509189Z","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":"2026-08-14T12:53:12.490612Z","title":"A simple yet effective baseline for 3d human pose es- timation","venue":null,"work_id":"aa143b76-282d-4bfe-8dcf-496788438fa6","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.054634Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:387a28a1f1ef7198752060165a1ad41266061eaca626e46d34aa2a0a2d91aec6","observation_id":"6a1f2f9a-e4f0-450d-8f70-cb62073d905c","resolution":{"observed_at":"2026-08-14T12:53:12.496049Z","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":"2026-08-14T12:53:12.475757Z","title":"Convo- lutional neural networks analyzed via convolutional sparse coding","venue":null,"work_id":"0ca2189b-8a43-45d7-9a5a-acea944b0d00","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.058115Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:efb3aefbb38c1a3548fbd2639268a165549f12c852072d2ac2159158434b1203","observation_id":"fa1f1a45-b31d-460c-858b-226587e6dd53","resolution":{"observed_at":"2026-08-14T12:53:12.482374Z","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":"2026-08-14T12:53:12.462757Z","title":"Ordinal depth supervision for 3d human pose estimation","venue":null,"work_id":"6812baa8-ca38-4ca0-b694-4db8dc691edf","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.061971Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:28ce13d0fc6fad86acfa13fcccb25780ac7c3b527728ea069a320191366e43fd","observation_id":"8dcedbf4-c83d-48a7-8e52-b46435423b27","resolution":{"observed_at":"2026-08-14T12:53:12.467572Z","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":"2026-08-14T12:53:12.449689Z","title":"Coarse-to-fine volumetric predic- tion for single-image 3d human pose","venue":null,"work_id":"0d29af24-8d95-4632-b366-c041cce58702","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.065841Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:5fab5ad521e6650cedbd1025c049233c94307a67c7d7eeda47a439dd432a090e","observation_id":"b52888c7-f33a-45d6-a93b-04857bfd3323","resolution":{"observed_at":"2026-08-14T12:53:12.454466Z","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":"2026-08-14T12:53:12.437151Z","title":"Harvesting multiple views for marker-less 3d human pose annotations","venue":null,"work_id":"77726eb5-8418-4659-9835-05bcd18e3bc5","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.069871Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:9cfaaee811423164e8f5fba9626b4896f30f75858346c7ded442e148aacd9678","observation_id":"5af11bb6-7903-41d2-b8cd-721df8fa2489","resolution":{"observed_at":"2026-08-14T12:53:12.441984Z","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":"2026-08-14T12:53:12.423330Z","title":"Re- constructing 3d human pose from 2d image landmarks","venue":null,"work_id":"cedb4502-5e5f-4871-82ff-f0b9c8f42b7e","year":2012},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.074358Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:29aaafc86a883d284a1532eabca180fa4e026838aed14551ae033b00386efeb9","observation_id":"5d104e20-3f82-46b8-9082-b98d76a3b4dc","resolution":{"observed_at":"2026-08-14T12:53:12.428395Z","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":"2026-08-14T12:53:12.408858Z","title":"Unsu- pervised geometry-aware representation for 3d human pose estimation","venue":null,"work_id":"4df1f11d-cb7c-49ff-92e1-ab4a44e3f267","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.078135Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:b695d4c09a6b6254a42ae283718ca60a6f83d177f053e40c5be34d033f00c7ae","observation_id":"e3149904-34b7-48ce-b770-bf0f4273e030","resolution":{"observed_at":"2026-08-14T12:53:12.414023Z","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":"2026-08-14T12:53:12.396357Z","title":"Learning monocular 3d human pose estimation from multi-view images","venue":null,"work_id":"547e4c35-1488-4148-9121-4d32f4bb31e9","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.082292Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:d1b0825335b780fe12d2bb1cd3c3f9914526b3b42f2ab0ceb5dde5e189205325","observation_id":"8bbf37e7-464d-46e2-bbb1-64a5c3f96f52","resolution":{"observed_at":"2026-08-14T12:53:12.401113Z","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":"2026-08-14T12:53:12.382653Z","title":"Sparse coding via thresholding and local competition in neural circuits","venue":null,"work_id":"6005bc81-61cf-44b5-ba94-1fd63f73d360","year":2008},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.086036Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:20f4d8f828401a4d3301885a7d38aa5d7022086fa45099ddb4a053e3c73efa62","observation_id":"27b911db-5ced-4bd7-805a-b389ac90ccab","resolution":{"observed_at":"2026-08-14T12:53:12.387535Z","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":"2026-08-14T12:53:12.369029Z","title":"Apollocar3d: A large 3d car instance understanding benchmark for autonomous driving, 2018","venue":null,"work_id":"56a420e9-5ad5-429a-9cc9-b797970a4c8b","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.090114Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:7fad300cae3b5d47b4aace309c6cc4046cf6cde1a215073ef55986e9bb13a825","observation_id":"cf97c982-5160-425a-9296-15d26d23dcce","resolution":{"observed_at":"2026-08-14T12:53:12.374689Z","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":"2026-08-14T12:53:12.357742Z","title":"Integral human pose regression","venue":null,"work_id":"25445f03-9157-4b22-ba16-2082ba72728a","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.094314Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:2ad6fc2adcb53614436353cbba89019ac7de1aa446586d465a2c9fac21ad6c2d","observation_id":"a7b722a6-97ea-407d-b97a-554837d3a049","resolution":{"observed_at":"2026-08-14T12:53:12.361594Z","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":"2026-08-14T12:53:12.347716Z","title":"Lifting from the deep: Convolutional 3d pose estimation from a sin- gle image","venue":null,"work_id":"352d83f5-8d25-4ff7-b37c-db9e12ec2348","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.098315Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:87aaae5f4ee39c3a924dce6a88cd1c3ac8cefffc5569841da4f6a8e7672ac91f","observation_id":"b9825b57-ff99-4969-8e71-96e930b0f0eb","resolution":{"observed_at":"2026-08-14T12:53:12.351013Z","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":"2026-08-14T12:53:12.335714Z","title":"Self-supervised learning of motion capture","venue":null,"work_id":"2dbb0596-46f3-467e-bd9c-ae7b52e11309","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.102640Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:66d1159a1350fa6a309d097f688c068b0b95f411012dfba29642ede82704efab","observation_id":"80626987-723e-413e-a70b-f3e311b39955","resolution":{"observed_at":"2026-08-14T12:53:12.340135Z","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":"2026-08-14T12:53:12.323167Z","title":"Deep image prior","venue":null,"work_id":"0f73fcfc-36ec-4718-a4c0-98fc5611939d","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.106160Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:e9829b2dbdd477a1c706e74e39c1e78c8258c2fe722340f46d432cc33503a29c","observation_id":"cd0e5011-8503-4580-930f-0ce125d66dad","resolution":{"observed_at":"2026-08-14T12:53:12.327342Z","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":"2026-08-14T12:53:12.310689Z","title":"Learning from synthetic humans","venue":null,"work_id":"6ae45ef6-c71b-400c-9dc6-7dc678392d57","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.109467Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:be165c6ceb9f89440808d6c944a9cb43033073bb8d15af73d2164a85b6cf1ccc","observation_id":"db2e1b75-cfe0-48e8-ab51-40e80a11b3ec","resolution":{"observed_at":"2026-08-14T12:53:12.314684Z","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":"1902.09868","last_updated":"2019-03-12T14:20:04Z","snapshot_observed_at":"2026-08-14T17:11:06.444752Z","submitted_at":"2019-02-26T11:23:54Z","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","version":2},"cited_work":{"arxiv_id":"1902.09868","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.09868","snapshot_observed_at":"2026-08-14T12:53:12.173348Z","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","venue":"cs.CV","work_id":"1c26fa70-f29e-4914-80c1-4490b7689401","year":2019},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.113111Z"},"links":{"cited_paper":"/paper/1902.09868","citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:bde6f8aebd6d602c32b7d8ba9b6f78905cd9e41166a5c8a0787378c1d55fd003","observation_id":"869056bf-9f4d-437e-b4b7-c1b993e8a516","resolution":{"observed_at":"2026-08-14T12:53:12.179982Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-14T12:53:12.297891Z","title":"Learning depth from monocular videos us- ing direct methods","venue":null,"work_id":"0a6c2edf-b2e8-4e65-87cc-2fbf2d207042","year":2022},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.117375Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:b2d1ee58dcb29d0b21e61188fbc807bdf61dfa2dd55a0f0b00fc2efb3a92f767","observation_id":"a35f1a46-27e3-4d1f-9972-81ed87b6e5b7","resolution":{"observed_at":"2026-08-14T12:53:12.302787Z","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":"2026-08-14T12:53:12.286055Z","title":"Single image 3d interpreter network","venue":null,"work_id":"25afb879-cfcf-4b5d-bdf4-234fbe6b4448","year":null},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.121257Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:260a7ff39efd247294ba61e2b572fa9e3fd0985bea34832ae1d4b2ba1eca35a0","observation_id":"b25be17c-01c1-4321-8d1a-96b1553b7a51","resolution":{"observed_at":"2026-08-14T12:53:12.289870Z","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":"2026-08-14T12:53:12.273823Z","title":"3d human pose estima- tion in the wild by adversarial learning","venue":null,"work_id":"22561187-9859-4868-81bc-eeedcc64a50e","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.125255Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:edc39abcaac167d750a01be1de291c75e0918ccf951d11eee1bc75aca0c96df1","observation_id":"7aa4a49a-08ea-4267-b3df-88e628d57239","resolution":{"observed_at":"2026-08-14T12:53:12.278268Z","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":"2026-08-14T12:53:12.260918Z","title":"Monocular 3d pose and shape estimation of multiple people in natural scenes - the importance of multiple scene constraints","venue":null,"work_id":"a905e16c-01c8-471e-9266-49697adbc7da","year":2018},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.129172Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:0f18711abe72b0611b9d02e4c40c052279d3da70277c68beb852a0deb4570836","observation_id":"f61df2f8-7ac1-41be-975a-0e3b35604316","resolution":{"observed_at":"2026-08-14T12:53:12.266043Z","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":"2026-08-14T12:53:12.248011Z","title":"Unsupervised learning of depth and ego-motion from video","venue":null,"work_id":"d1e88cc8-c894-4ae5-9a47-2d01678956be","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.133480Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:0731bf974ed39179b524a3842fa5b8c6ba792cdb01866ee6af244bddc8d88302","observation_id":"22e0b1a1-7652-46f5-a3e7-904e4f002514","resolution":{"observed_at":"2026-08-14T12:53:12.252327Z","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":"2026-08-14T12:53:12.235883Z","title":"Towards 3d human pose estimation in the wild: a weakly-supervised approach","venue":null,"work_id":"4b5fce30-98b4-4f32-a6f5-bc94a6891571","year":2017},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.137276Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:4a24cb7936ec12c9c1421f628883dad3c7d2ed13871ddc8f88fe2a0b626a6daf","observation_id":"5d7150ee-39d0-4252-9353-192bd1b0d1c4","resolution":{"observed_at":"2026-08-14T12:53:12.240351Z","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":"2026-08-14T12:53:12.222825Z","title":"Complex non-rigid motion 3d reconstruction by union of subspaces","venue":null,"work_id":"7612fd1e-385b-442f-a62d-a553d636d694","year":2014},"citing_paper":{"arxiv_id":"1908.06377","last_updated":"2019-08-18T04:48:49Z","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:12.141036Z"},"links":{"citing_paper":"/paper/1908.06377"},"observation_digest":"sha256:e9a75d129de4e78bf25c1e485d3cfbdf05e2bc6a8c5fc20ee7d3fd17b69f493e","observation_id":"a948c3e3-db35-4964-b3f9-c5c6137c837d","resolution":{"observed_at":"2026-08-14T12:53:12.226930Z","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":"1908.06377","last_updated":"2019-08-18T04:48:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T12:45:00.053396Z","submitted_at":"2019-08-18T04:48:49Z","title":"Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":3,"verified_fuzzy":44},"total_outbound_references":48},"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 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:1908.06377."}