{"id":"https://openalex.org/W7118189333","doi":"https://doi.org/10.1109/tmm.2026.3651016","title":"HitBack: Transformer With Hierarchical-Semantic Cross Attention and Background Contrast for Weakly Supervised Wildlife Semantic Segmentation","display_name":"HitBack: Transformer With Hierarchical-Semantic Cross Attention and Background Contrast for Weakly Supervised Wildlife Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118189333","doi":"https://doi.org/10.1109/tmm.2026.3651016"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651016","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034907025","display_name":"Puxuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153668","display_name":"Wenzhou-Kean University","ror":"https://ror.org/05609xa16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153668"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Puxuan Xie","raw_affiliation_strings":["Department of Computer Science, Wenzhou-Kean University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-5197-0715","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wenzhou-Kean University, Wenzhou, China","institution_ids":["https://openalex.org/I4210153668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121964070","display_name":"Wei Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhuo","raw_affiliation_strings":["Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-5780-0364","affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I4210105229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083051797","display_name":"Xinshao Wang","orcid":"https://orcid.org/0000-0001-8907-8258"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinshao Wang","raw_affiliation_strings":["Department of Engineering Science, University of Oxford, Oxford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8907-8258","affiliations":[{"raw_affiliation_string":"Department of Engineering Science, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076939216","display_name":"Songhe Deng","orcid":"https://orcid.org/0009-0005-9843-2083"},"institutions":[{"id":"https://openalex.org/I4210153668","display_name":"Wenzhou-Kean University","ror":"https://ror.org/05609xa16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153668"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhe Deng","raw_affiliation_strings":["Department of Computer Science, Wenzhou-Kean University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-9843-2083","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wenzhou-Kean University, Wenzhou, China","institution_ids":["https://openalex.org/I4210153668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101363147","display_name":"Weizhao He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153668","display_name":"Wenzhou-Kean University","ror":"https://ror.org/05609xa16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153668"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhao He","raw_affiliation_strings":["Department of Computer Science, Wenzhou-Kean University, Wenzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wenzhou-Kean University, Wenzhou, China","institution_ids":["https://openalex.org/I4210153668"]}]},{"author_position":"last","author":{"id":null,"display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"institutions":[{"id":"https://openalex.org/I4210153668","display_name":"Wenzhou-Kean University","ror":"https://ror.org/05609xa16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210153668"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["Department of Computer Science, Wenzhou-Kean University, Wenzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1420-0815","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wenzhou-Kean University, Wenzhou, China","institution_ids":["https://openalex.org/I4210153668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.02298782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2363","last_page":"2377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.748199999332428,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.748199999332428,"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/T10199","display_name":"Wildlife Ecology and Conservation","score":0.05920000001788139,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02879999950528145,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.626800000667572},{"id":"https://openalex.org/keywords/snapshot","display_name":"Snapshot (computer storage)","score":0.5806000232696533},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5662000179290771},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.38839998841285706},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.3776000142097473},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331999778747559},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6200000047683716},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27709999680519104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651016","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7097988128662109}],"awards":[{"id":"https://openalex.org/G4600207245","display_name":null,"funder_award_id":"62576216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5272848669","display_name":null,"funder_award_id":"2024A1515010194","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Monitoring":[0],"wildlife":[1,18,49,133],"behavior":[2],"and":[3,35,55,67,73,91,118,147,167,172,218,226,241,250],"population":[4],"changes":[5],"is":[6,20,160,176,215,247],"critical":[7],"for":[8,97,115,127,151],"conservation":[9],"efforts.":[10],"However,":[11],"specialized":[12],"analysis":[13],"of":[14,17,27,46,99,105,213,223],"large":[15],"volumes":[16],"images":[19,108],"extremely":[21],"chal":[22],"lenging,":[23],"necessitating":[24],"the":[25,43,82,93,100,165,173,186,191,208,238],"use":[26,45],"artificial":[28],"intelligence":[29],"techniques":[30],"to":[31,81,162,178],"automatically":[32],"detect,":[33],"segment,":[34],"classify":[36],"species":[37,111],"captured":[38],"by":[39,182],"trap":[40],"cameras.":[41],"Despite":[42],"increasing":[44],"AI":[47],"in":[48,132,185],"monitoring,":[50],"challenges":[51],"with":[52,77,112,207],"data":[53,246],"quality":[54],"availability":[56],"persist.":[57],"The":[58,157,211],"Snapshot":[59],"Serengeti":[60,101],"(SS)":[61],"dataset":[62,76,122],"only":[63],"has":[64],"image-level":[65],"labels":[66,79],"very":[68],"few":[69],"bounding":[70],"box":[71],"labels,":[72],"there's":[74],"no":[75],"pixel-level":[78],"due":[80],"significant":[83],"annotation":[84,245],"costs.":[85],"To":[86],"this":[87],"end,":[88],"we":[89,136],"create":[90],"release":[92],"large-scale":[94],"Semantic":[95],"Segmentation":[96],"Snapshots":[98],"(S4)":[102],"dataset,":[103],"consisting":[104],"24K":[106],"high-quality":[107],"across":[109,170],"47":[110],"precise":[113],"masks,":[114],"both":[116,164],"common":[117],"rare":[119],"species.":[120],"This":[121],"serves":[123],"as":[124],"a":[125,139],"resource":[126],"developing":[128],"semantic":[129,154],"segmentation":[130,155],"algorithms":[131],"studies.":[134],"Additionally,":[135],"introduce":[137],"HitBack,":[138],"novel":[140],"method":[141],"leveraging":[142],"Hierarchical-Semantic":[143],"Cross":[144],"Attention":[145],"(HCA)":[146],"Background":[148],"Contrast":[149],"(BC)":[150],"weakly":[152],"supervised":[153,240],"(WSSS).":[156],"HCA":[158],"module":[159,175],"used":[161],"capture":[163],"shared":[166],"distinct":[168],"features":[169],"species,":[171],"BC":[174],"designed":[177],"enhance":[179],"foreground":[180],"activation":[181],"ensuring":[183],"consistency":[184],"backgrounds.":[187],"Extensive":[188],"experiments":[189],"on":[190],"newly":[192],"proposed":[193],"S<sup":[194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">4</sup>":[196],"benchmark":[197],"show":[198],"that,":[199],"our":[200,231],"HitBack":[201,214,232],"presents":[202],"competitive":[203],"performance":[204,235],"when":[205,244],"compared":[206],"state-of-the-art":[209],"models.":[210],"mIoU":[212],"+10.4%,":[216],"+14.7%,":[217],"+18.4%":[219],"higher":[220],"than":[221],"that":[222,236],"ToCo,":[224],"SIPE,":[225],"MCTformer,":[227],"respectively.":[228],"In":[229],"addition,":[230],"even":[233],"obtains":[234],"surpasses":[237],"fully":[239],"semi-supervised":[242],"methods":[243],"limited.":[248],"Code":[249],"datasets":[251],"will":[252],"be":[253],"available":[254],"at":[255],"Github.":[256]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-05T00:00:00"}