{"id":"https://openalex.org/W4415538751","doi":"https://doi.org/10.1145/3746027.3755848","title":"Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation","display_name":"Shallow Features Matter: Hierarchical Memory with Heterogeneous Interaction for Unsupervised Video Object Segmentation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538751","doi":"https://doi.org/10.1145/3746027.3755848"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/2507.22465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiangyu Zheng","orcid":"https://orcid.org/0009-0004-6104-1647"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zheng","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-6104-1647","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068452086","display_name":"Songcheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songcheng He","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1496-7585","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043818900","display_name":"Wanyun Li","orcid":"https://orcid.org/0000-0001-9224-1618"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyun Li","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9224-1618","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339621","display_name":"Xiaoqiang Li","orcid":"https://orcid.org/0000-0001-7243-2783"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Li","raw_affiliation_strings":["The School of Computer Engineering and Science, Shanghai University, Shang hai, China"],"raw_orcid":"https://orcid.org/0000-0001-7243-2783","affiliations":[{"raw_affiliation_string":"The School of Computer Engineering and Science, Shanghai University, Shang hai, China","institution_ids":["https://openalex.org/I113940042","https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441587","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-2358-8543"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2358-8543","affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.32616829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"796","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":1.0,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6122999787330627},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5120000243186951},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5062999725341797},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41280001401901245},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4023999869823456},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3734000027179718},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6122999787330627},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3517000079154968},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3352999985218048},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755848","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.22465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22465","pdf_url":"https://arxiv.org/pdf/2507.22465","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:2507.22465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.22465","pdf_url":"https://arxiv.org/pdf/2507.22465","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1943880421","https://openalex.org/W1973054923","https://openalex.org/W1976037690","https://openalex.org/W2012960460","https://openalex.org/W2055468140","https://openalex.org/W2110019070","https://openalex.org/W2118143383","https://openalex.org/W2127070222","https://openalex.org/W2140000690","https://openalex.org/W2187051054","https://openalex.org/W2470139095","https://openalex.org/W2739107216","https://openalex.org/W2808425487","https://openalex.org/W2974686944","https://openalex.org/W2987391422","https://openalex.org/W3035665735","https://openalex.org/W3049318984","https://openalex.org/W3080686309","https://openalex.org/W3138516171","https://openalex.org/W4366350967","https://openalex.org/W4387969348","https://openalex.org/W4387969542","https://openalex.org/W4390873201","https://openalex.org/W4398787780"],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"Video":[1],"Object":[2],"Segmentation":[3],"(UVOS)":[4],"aims":[5],"to":[6,73,96,112,132,150],"predict":[7],"pixel-level":[8,77],"masks":[9],"for":[10,119],"the":[11,66,74,123,134,138,163,182,189],"most":[12],"salient":[13],"objects":[14],"in":[15,28,35,53,185,192],"videos":[16],"without":[17],"any":[18],"prior":[19,78],"annotations.":[20],"While":[21],"memory":[22,81,110,142,187],"mechanisms":[23],"have":[24],"been":[25],"proven":[26],"critical":[27],"various":[29],"video":[30,211],"segmentation":[31],"paradigms,":[32],"their":[33,158],"application":[34],"UVOS":[36,62,209],"yield":[37],"only":[38],"marginal":[39],"performance":[40,206,220],"gains":[41],"despite":[42],"sophisticated":[43],"design.":[44],"Our":[45,195],"analysis":[46],"reveals":[47],"a":[48,107,146],"simple":[49],"but":[50],"fundamental":[51,103],"flaw":[52],"existing":[54],"methods:":[55],"over-reliance":[56],"on":[57,85],"memorizing":[58],"high-level":[59,86,117,193],"semantic":[60,92,129,141,190],"features.":[61],"inherently":[63],"suffers":[64],"from":[65],"deficiency":[67],"of":[68,76,126,137,165,181],"lacking":[69],"fine-grained":[70,183],"information":[71],"due":[72],"absence":[75],"knowledge.":[79],"Consequently,":[80],"design":[82,164],"relying":[83],"solely":[84],"features,":[87,143],"which":[88,121,155],"predominantly":[89],"capture":[90],"abstract":[91],"cues,":[93],"is":[94],"insufficient":[95],"generate":[97],"precise":[98],"predictions.":[99],"To":[100],"resolve":[101],"this":[102],"issue,":[104],"we":[105,144,177],"propose":[106,145],"novel":[108],"hierarchical":[109],"architecture":[111],"incorporate":[113],"both":[114],"shallow-":[115],"and":[116,128,140,171,188,210,228],"features":[118],"memory,":[120],"leverages":[122],"complementary":[124],"benefits":[125],"pixel":[127,139],"information.":[130],"Furthermore,":[131],"balance":[133],"simultaneous":[135],"utilization":[136],"heterogeneous":[147],"interaction":[148],"mechanism":[149],"perform":[151],"pixel-semantic":[152],"mutual":[153],"interactions,":[154],"explicitly":[156],"considers":[157],"inherent":[159],"feature":[160],"discrepancies.":[161],"Through":[162],"Pixel-guided":[166],"Local":[167],"Alignment":[168],"Module":[169,175],"(PLAM)":[170],"Semantic-guided":[172],"Global":[173],"Integration":[174],"(SGIM),":[176],"achieve":[178],"delicate":[179],"integration":[180],"details":[184],"shallow-level":[186],"representations":[191],"memory.":[194],"Hierarchical":[196],"Memory":[197],"with":[198],"Heterogeneous":[199],"Interaction":[200],"Network":[201],"(HMHI-Net)":[202],"consistently":[203,217],"achieves":[204],"state-of-the-art":[205],"across":[207,221],"all":[208],"saliency":[212],"detection":[213],"benchmarks.":[214],"Moreover,":[215],"HMHI-Net":[216],"exhibits":[218],"high":[219],"different":[222],"backbones,":[223],"further":[224],"demonstrating":[225],"its":[226],"superiority":[227],"robustness.":[229],"Project":[230],"page:":[231],"https://github.com/ZhengxyFlow/HMHI-Net":[232],".":[233]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-25T00:00:00"}