{"id":"https://openalex.org/W4304080724","doi":"https://doi.org/10.1145/3503161.3548333","title":"HERO: HiErarchical spatio-tempoRal reasOning with Contrastive Action Correspondence for End-to-End Video Object Grounding","display_name":"HERO: HiErarchical spatio-tempoRal reasOning with Contrastive Action Correspondence for End-to-End Video Object Grounding","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080724","doi":"https://doi.org/10.1145/3503161.3548333"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548333","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101737334","display_name":"Mengze Li","orcid":"https://orcid.org/0000-0002-3482-234X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengze Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103281205","display_name":"Tianbao Wang","orcid":"https://orcid.org/0000-0002-6945-9448"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianbao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425893","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0000-0002-8570-5792"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757087","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-0030-8289"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Shanghai Institute for Advanced Study of Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Shanghai Institute for Advanced Study of Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082131901","display_name":"Wenqiao Zhang","orcid":"https://orcid.org/0000-0002-5988-7609"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011439390","display_name":"Jiaxu Miao","orcid":"https://orcid.org/0000-0002-4238-8475"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Miao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085955762","display_name":"Shiliang Pu","orcid":"https://orcid.org/0000-0001-5269-7821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiliang Pu","raw_affiliation_strings":["Hikvision, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004882141","display_name":"Fei Wu","orcid":"https://orcid.org/0000-0003-2139-8807"},"institutions":[{"id":"https://openalex.org/I4210111959","display_name":"Shanghai Advanced Research Institute","ror":"https://ror.org/02br7py06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210111959"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wu","raw_affiliation_strings":["Shanghai Institute for Advanced Study of Zhejiang University, Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Institute for Advanced Study of Zhejiang University, Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210111959","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101737334"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.5652,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.88777984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3801","last_page":"3810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T10812","display_name":"Human Pose and Action Recognition","score":0.9990000128746033,"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":0.9840999841690063,"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/computer-science","display_name":"Computer science","score":0.8034890294075012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5864027738571167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4647713303565979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034890294075012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5864027738571167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4647713303565979}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548333","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2798708692","https://openalex.org/W2890502146","https://openalex.org/W2904910963","https://openalex.org/W2946086442","https://openalex.org/W2951323451","https://openalex.org/W2963017553","https://openalex.org/W2963843782","https://openalex.org/W2964284374","https://openalex.org/W2969897437","https://openalex.org/W2987734933","https://openalex.org/W3034298080","https://openalex.org/W3034655362","https://openalex.org/W3034772468","https://openalex.org/W3035590142","https://openalex.org/W3037266902","https://openalex.org/W3049478012","https://openalex.org/W3092900809","https://openalex.org/W3092962760","https://openalex.org/W3093017735","https://openalex.org/W3099839483","https://openalex.org/W3104309049","https://openalex.org/W3159619744","https://openalex.org/W3166712493","https://openalex.org/W3174966920","https://openalex.org/W3175824375","https://openalex.org/W3205059508","https://openalex.org/W3206019042","https://openalex.org/W4224309908"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"<u>V</u>ideo":[0],"<u>O</u>bject":[1],"<u>G</u>rounding":[2],"(VOG)":[3],"is":[4,22,98],"the":[5,13,30,36,41,48,74,91,103,113,119,128,138,172,176,179,189,201,217],"problem":[6],"of":[7,40,178,221],"associating":[8],"spatial":[9,223],"object":[10],"regions":[11,224],"in":[12,159],"video":[14,43,93,120,163],"to":[15,193,215,232],"a":[16,23,60,134],"descriptive":[17],"natural":[18],"language":[19,105],"query.":[20],"This":[21],"challenging":[24],"vision-language":[25],"task":[26,58,76],"that":[27,80,90,117,171],"necessitates":[28],"constructing":[29],"correct":[31],"cross-modal":[32,140,218],"correspondence":[33,141],"and":[34,44,123,164,199,209,225],"modeling":[35],"appropriate":[37],"spatio-temporal":[38,181],"context":[39],"query":[42,106],"caption,":[45],"thereby":[46],"localizing":[47],"specific":[49],"objects":[50],"accurately.":[51],"In":[52],"this":[53,57],"paper,":[54],"we":[55,110,186],"tackle":[56],"by":[59,184,239],"novel":[61],"framework":[62],"called":[63],"<u>H</u>i<u>E</u>rarchical":[64],"spatio-tempo<u>R</u>al":[65],"reas<u>O</u>ning":[66],"(HERO)":[67],"with":[68,102],"contrastive":[69,115],"action":[70,130],"correspondence.":[71,132],"We":[72,228],"study":[73],"VOG":[75,154],"at":[77],"two":[78,244],"aspects":[79],"prior":[81],"works":[82],"overlooked:":[83],"(1)":[84],"Contrastive":[85],"Action":[86],"Correspondence-aware":[87],"Retrieval.":[88],"Notice":[89],"fine-grained":[92,139],"semantics":[94],"(e.g.,":[95,107],"multiple":[96],"actions)":[97],"not":[99],"totally":[100],"aligned":[101],"annotated":[104],"single":[108],"action),":[109],"first":[111],"introduce":[112],"weakly-supervised":[114],"learning":[116],"classifies":[118],"as":[121],"action-consistent":[122],"action-independent":[124],"frames":[125],"relying":[126],"on":[127,243],"video-caption":[129],"semantic":[131],"Such":[133],"design":[135,188],"can":[136],"build":[137],"for":[142],"more":[143],"accurate":[144],"subsequent":[145],"VOG.":[146],"(2)":[147],"Hierarchical":[148],"Spatio-temporal":[149],"Modeling":[150],"Improvement.":[151],"While":[152],"transformer-based":[153],"models":[155],"present":[156],"their":[157],"potential":[158],"sequential":[160],"modality":[161],"(i.e.,":[162],"caption)":[165],"modeling,":[166],"existing":[167,237],"evidence":[168],"also":[169],"indicates":[170],"transformer":[173],"suffers":[174],"from":[175],"issue":[177],"insensitive":[180],"locality.":[182],"Motivated":[183],"that,":[185],"carefully":[187],"hierarchical":[190],"reasoning":[191],"layers":[192],"decouple":[194],"fully":[195],"connected":[196],"multi-head":[197],"attention":[198],"remove":[200],"redundant":[202],"interfering":[203],"correlations.":[204],"Furthermore,":[205],"our":[206,234],"proposed":[207],"pyramid":[208],"shifted":[210],"alignment":[211],"mechanisms":[212],"are":[213],"effective":[214],"improve":[216],"information":[219],"utilization":[220],"neighborhood":[222],"temporal":[226],"frames.":[227],"conducted":[229],"extensive":[230],"experiments":[231],"show":[233],"HERO":[235],"outperforms":[236],"techniques":[238],"achieving":[240],"significant":[241],"improvement":[242],"benchmark":[245],"datasets.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":20}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}