{"id":"https://openalex.org/W4417266589","doi":"https://doi.org/10.1109/iccv51701.2025.02068","title":"Object-Centric Video Question Answering with Visual Grounding and Referring","display_name":"Object-Centric Video Question Answering with Visual Grounding and Referring","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417266589","doi":"https://doi.org/10.1109/iccv51701.2025.02068"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.19599","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100645300","display_name":"Haochen Wang","orcid":"https://orcid.org/0000-0003-3178-6125"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Haochen Wang","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032372317","display_name":"Qirui Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirui Chen","raw_affiliation_strings":["SAI, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAI, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035332982","display_name":"Cilin Yan","orcid":"https://orcid.org/0000-0001-9754-129X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cilin Yan","raw_affiliation_strings":["Xiaohongshu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066854056","display_name":"Jiayin Cai","orcid":"https://orcid.org/0009-0007-8903-212X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayin Cai","raw_affiliation_strings":["Xiaohongshu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125047","display_name":"Xiaolong Jiang","orcid":"https://orcid.org/0000-0002-0745-1184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolong Jiang","raw_affiliation_strings":["Xiaohongshu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100666109","display_name":"Yao Hu","orcid":"https://orcid.org/0000-0003-4573-5740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Hu","raw_affiliation_strings":["Xiaohongshu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaohongshu Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076097168","display_name":"Weidi Xie","orcid":"https://orcid.org/0000-0003-3804-2639"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["SAI, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAI, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120782164","display_name":"Stratis Gavves","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Stratis Gavves","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100645300"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37860168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22274","last_page":"22284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9947999715805054,"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":0.9947999715805054,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0006000000284984708,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0005000000237487257,"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/question-answering","display_name":"Question answering","score":0.698199987411499},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6938999891281128},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5465999841690063},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5307000279426575},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4668999910354614},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4388999938964844},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.391400009393692},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569999933242798},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.698199987411499},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6938999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5307000279426575},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4668999910354614},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36340001225471497},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.19599","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19599","pdf_url":"https://arxiv.org/pdf/2507.19599","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2507.19599","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.19599","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.19599","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.19599","pdf_url":"https://arxiv.org/pdf/2507.19599","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Large":[1],"Language":[2],"Models":[3],"(VideoLLMs)":[4],"have":[5],"recently":[6],"demonstrated":[7],"remarkable":[8],"progress":[9],"in":[10,64,159,169],"general":[11],"video":[12,65,116,136,161,172],"understanding.":[13,175],"However,":[14],"existing":[15,133],"models":[16],"primarily":[17],"focus":[18],"on":[19,129,145],"high-level":[20],"comprehension":[21],"and":[22,60,78,131,139,164,173],"are":[23],"limited":[24],"to":[25,71,101],"text-only":[26],"responses,":[27],"restricting":[28],"the":[29,102],"flexibility":[30],"for":[31,58,62],"object-centric,":[32],"multiround":[33],"interactions.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,43,82,109],"make":[39],"three":[40],"contributions:":[41],"(i)":[42],"address":[44],"these":[45],"limitations":[46],"by":[47],"introducing":[48],"a":[49,88,106,112],"VideoLLM":[50],"model,":[51],"capable":[52],"of":[53,148],"performing":[54],"both":[55,76,160],"object":[56,141],"referring":[57,140],"input":[59,96],"grounding":[61],"output":[63],"reasoning":[66],"tasks,":[67],"i.e.,":[68],"allowing":[69],"users":[70],"interact":[72],"with":[73],"videos":[74],"using":[75],"textual":[77],"visual":[79,94],"prompts;":[80],"(ii)":[81],"propose":[83],"STOM":[84],"(Spatial-Temporal":[85],"Overlay":[86],"Module),":[87],"novel":[89],"approach":[90],"that":[91,122,152],"propagates":[92],"arbitrary":[93],"prompts":[95],"at":[97],"any":[98],"single":[99],"timestamp":[100],"remaining":[103],"frames":[104],"within":[105],"video;":[107],"(iii)":[108],"present":[110],"VideoInfer,":[111],"manually":[113],"curated":[114],"object-centric":[115,171],"instruction":[117],"dataset":[118],"featuring":[119],"questionanswering":[120],"pairs":[121],"require":[123],"reasoning.":[124],"We":[125],"conduct":[126],"comprehensive":[127],"experiments":[128],"VideoInfer":[130],"other":[132],"benchmarks":[134,147],"across":[135],"question":[137,162],"answering":[138,163],"segmentation.":[142],"The":[143],"results":[144],"12":[146],"6":[149],"tasks":[150],"show":[151],"our":[153],"proposed":[154],"model":[155],"consistently":[156],"outperforms":[157],"baselines":[158],"segmentation,":[165],"underscoring":[166],"its":[167],"robustness":[168],"multimodal,":[170],"image":[174],"Project":[176],"page:":[177],"https://qirui-chen.github.io/RGA3-release/.":[178]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}