{"id":"https://openalex.org/W7113913389","doi":"https://doi.org/10.1145/3774521.3774619","title":"UnCageNet: Tracking and Pose Estimation of Caged Animals","display_name":"UnCageNet: Tracking and Pose Estimation of Caged Animals","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7113913389","doi":"https://doi.org/10.1145/3774521.3774619"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774521.3774619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.07712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sayak Dutta","orcid":"https://orcid.org/0009-0001-3104-6082"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sayak Dutta","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, Gujarat, India"],"raw_orcid":"https://orcid.org/0009-0001-3104-6082","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Harish Katti","orcid":"https://orcid.org/0000-0003-4223-0325"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harish Katti","raw_affiliation_strings":["National Institutes of Health, Besthesda, USA"],"raw_orcid":"https://orcid.org/0000-0003-4223-0325","affiliations":[{"raw_affiliation_string":"National Institutes of Health, Besthesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shashikant Verma","orcid":"https://orcid.org/0000-0002-9862-1379"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashikant Verma","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, Gujarat, India"],"raw_orcid":"https://orcid.org/0000-0002-9862-1379","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shanmuganathan Raman","orcid":"https://orcid.org/0000-0003-2718-7891"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shanmuganathan Raman","raw_affiliation_strings":["IIT Gandhinagar, Gandhinagar, Gujarat, India"],"raw_orcid":"https://orcid.org/0000-0003-2718-7891","affiliations":[{"raw_affiliation_string":"IIT Gandhinagar, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I27674431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52396998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5758000016212463,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.5758000016212463,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.12210000306367874,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.06129999831318855,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.8170999884605408},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6927000284194946},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6905999779701233},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6010000109672546},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5705000162124634},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.4767000079154968},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8567000031471252},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8360000252723694},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.8170999884605408},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6905999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6410999894142151},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41990000009536743},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.4194999933242798},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774521.3774619","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774521.3774619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.07712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.07712","pdf_url":"https://arxiv.org/pdf/2512.07712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.07712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.07712","pdf_url":"https://arxiv.org/pdf/2512.07712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Animal":[0],"tracking":[1,74,125],"and":[2,11,14,23,28,67,73,93,124,142],"pose":[3,71,122],"estimation":[4,72,123],"systems,":[5],"such":[6],"as":[7],"STEP":[8],"(Simultaneous":[9],"Tracking":[10],"Pose":[12],"Estimation)":[13],"ViTPose,":[15],"experience":[16],"substantial":[17],"performance":[18,101,119],"drops":[19],"when":[20],"processing":[21],"images":[22],"videos":[24],"with":[25,52,86],"cage":[26,95,110],"structures":[27,96],"systematic":[29],"occlusions.":[30,132],"We":[31,133],"present":[32],"a":[33,48],"novel":[34],"three-stage":[35],"preprocessing":[36],"pipeline":[37,114],"that":[38,97,108],"addresses":[39],"this":[40],"fundamental":[41],"limitation":[42],"through:":[43],"(1)":[44],"Cage":[45,57],"Segmentation":[46],"using":[47,59],"Gabor-enhanced":[49,80],"ResNet-UNet":[50],"architecture":[51],"tunable":[53],"orientation":[54],"filters,":[55],"(2)":[56],"Inpainting":[58],"CRFill":[60],"for":[61,121],"content-aware":[62],"reconstruction":[63],"of":[64,70,102],"occluded":[65],"regions,":[66],"(3)":[68],"Evaluation":[69],"on":[75],"the":[76,100],"uncaged":[77],"frames.":[78],"Our":[79],"segmentation":[81],"model":[82],"leverages":[83],"orientation-aware":[84],"features":[85],"72":[87],"directional":[88],"kernels":[89],"to":[90,117,127],"accurately":[91],"identify":[92],"segment":[94],"severely":[98],"impair":[99],"existing":[103],"methods.":[104],"Experimental":[105],"validation":[106],"demonstrates":[107],"removing":[109],"occlusions":[111],"through":[112],"our":[113],"enables":[115],"us":[116],"achieve":[118],"levels":[120],"comparable":[126],"those":[128],"in":[129,138],"environments":[130],"without":[131],"also":[134],"observed":[135],"significant":[136],"improvements":[137],"keypoint":[139],"detection":[140],"accuracy":[141],"trajectory":[143],"consistency.":[144]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-11T00:00:00"}