{"id":"https://openalex.org/W4304098887","doi":"https://doi.org/10.1145/3503161.3548035","title":"Equivariant and Invariant Grounding for Video Question Answering","display_name":"Equivariant and Invariant Grounding for Video Question Answering","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098887","doi":"https://doi.org/10.1145/3503161.3548035"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548035","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548035","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101762861","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0002-5659-793X"},"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":true,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389037","display_name":"Xiang Wang","orcid":"https://orcid.org/0000-0002-6148-6329"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Singapore","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195"},"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":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"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":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101762861"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.7129,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.89622374,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4714","last_page":"4722"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9940999746322632,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9912999868392944,"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/question-answering","display_name":"Question answering","score":0.9133962988853455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606683373451233},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5455989837646484},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5350568890571594},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4897198975086212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4797055125236511},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4764581024646759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42172789573669434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.130859375}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9133962988853455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606683373451233},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5455989837646484},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5350568890571594},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4897198975086212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4797055125236511},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4764581024646759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42172789573669434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.130859375},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548035","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3503161.3548035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548035","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304098887.pdf","grobid_xml":"https://content.openalex.org/works/W4304098887.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2143891888","https://openalex.org/W2516809705","https://openalex.org/W2765407302","https://openalex.org/W2806331055","https://openalex.org/W2904452845","https://openalex.org/W2945976633","https://openalex.org/W2954199749","https://openalex.org/W2962843949","https://openalex.org/W2962949233","https://openalex.org/W2963798744","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3005086430","https://openalex.org/W3035517717","https://openalex.org/W3102564565","https://openalex.org/W3135367836","https://openalex.org/W3152876231","https://openalex.org/W3166396011","https://openalex.org/W3167092180","https://openalex.org/W3171353004","https://openalex.org/W3173367591","https://openalex.org/W3174001836","https://openalex.org/W3175961224","https://openalex.org/W3177934633","https://openalex.org/W3203995540","https://openalex.org/W3205572000","https://openalex.org/W3207847779","https://openalex.org/W4200631219","https://openalex.org/W4214519690","https://openalex.org/W4224308683","https://openalex.org/W4300435650","https://openalex.org/W4312974690"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W2147241511","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952"],"abstract_inverted_index":{"Video":[0],"Question":[1],"Answering":[2],"(VideoQA)":[3],"is":[4],"the":[5,9,21,44,48,64,67,73,80,89],"task":[6],"of":[7,63],"answering":[8,49,92],"natural":[10],"language":[11],"questions":[12],"about":[13],"a":[14,76,84],"video.":[15],"Producing":[16],"an":[17,95],"answer":[18,72],"requires":[19],"understanding":[20],"interplay":[22],"across":[23],"visual":[24,57,81],"scenes":[25],"in":[26,31,83],"video":[27,65],"and":[28],"linguistic":[29],"semantics":[30],"question.":[32],"However,":[33],"most":[34],"leading":[35],"VideoQA":[36],"models":[37],"work":[38],"as":[39],"black":[40],"boxes,":[41],"which":[42,87],"make":[43],"visual-linguistic":[45],"alignment":[46],"behind":[47],"process":[50,93],"obscure.":[51],"Such":[52],"black-box":[53],"nature":[54],"calls":[55],"for":[56],"explainability":[58],"that":[59],"reveals":[60],"\"What":[61],"part":[62],"should":[66],"model":[68],"look":[69],"at":[70],"to":[71],"question?\".":[74],"Only":[75],"few":[77],"works":[78],"present":[79],"explanations":[82],"post-hoc":[85],"fashion,":[86],"emulates":[88],"target":[90],"model's":[91],"via":[94],"additional":[96],"method.":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
