{"id":"https://openalex.org/W4390190135","doi":"https://doi.org/10.1109/iccvw60793.2023.00502","title":"MMTF: Multi-Modal Temporal Fusion for Commonsense Video Question Answering","display_name":"MMTF: Multi-Modal Temporal Fusion for Commonsense Video Question Answering","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4390190135","doi":"https://doi.org/10.1109/iccvw60793.2023.00502"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5016610370","display_name":"Mobeen Ahmad","orcid":"https://orcid.org/0000-0001-5909-0125"},"institutions":[],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mobeen Ahmad","raw_affiliation_strings":["PYLER CO., LTD, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"PYLER CO., LTD, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452459","display_name":"Geonwoo Park","orcid":"https://orcid.org/0000-0003-3712-638X"},"institutions":[],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geonwoo Park","raw_affiliation_strings":["PYLER CO., LTD, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"PYLER CO., LTD, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066171177","display_name":"Dongchan Park","orcid":"https://orcid.org/0000-0002-6098-0210"},"institutions":[],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongchan Park","raw_affiliation_strings":["PYLER CO., LTD, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"PYLER CO., LTD, Seoul, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088022002","display_name":"Sanguk Park","orcid":"https://orcid.org/0000-0002-0240-8902"},"institutions":[],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanguk Park","raw_affiliation_strings":["PYLER CO., LTD, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"PYLER CO., LTD, Seoul, South Korea","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.259,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":67,"max":78},"biblio":{"volume":null,"issue":null,"first_page":"4659","last_page":"4664"},"is_retracted":false,"is_paratext":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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.999,"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":0.9988,"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/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5681865},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.48503846}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.72794294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761045},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6013291},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5681865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241775},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.48503846},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41549003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40736932},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37045112},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.102550566},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw60793.2023.00502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":37,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2194775991","https://openalex.org/W2606982687","https://openalex.org/W2765716052","https://openalex.org/W2904452845","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2963155035","https://openalex.org/W2966683369","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W2997344006","https://openalex.org/W2998166190","https://openalex.org/W3023993913","https://openalex.org/W3034730770","https://openalex.org/W3035265375","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105232955","https://openalex.org/W3167092180","https://openalex.org/W3171668871","https://openalex.org/W3175961224","https://openalex.org/W3187433838","https://openalex.org/W3203995540","https://openalex.org/W3214661002","https://openalex.org/W4200631219","https://openalex.org/W4214519690","https://openalex.org/W4221166385","https://openalex.org/W4285600797","https://openalex.org/W4288287305","https://openalex.org/W4312246181","https://openalex.org/W4312954271","https://openalex.org/W4312974690","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4385488510","https://openalex.org/W4320165839","https://openalex.org/W4313191056","https://openalex.org/W4287633646","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W3035583586","https://openalex.org/W2196562041","https://openalex.org/W2151799802","https://openalex.org/W2073302931"],"abstract_inverted_index":{"Video":[0],"question":[1,13,79],"answering":[2],"is":[3],"a":[4,61],"challenging":[5],"task":[6],"that":[7,66],"requires":[8],"understanding":[9],"the":[10,15,23,68,72,82],"video":[11,49,73,90],"and":[12,50,74,86,98,113],"in":[14],"same":[16],"context.":[17,100],"This":[18],"becomes":[19],"even":[20],"harder":[21],"when":[22],"questions":[24],"involve":[25],"reasoning,":[26],"such":[27],"as":[28],"predicting":[29],"future":[30],"events":[31],"or":[32],"explaining":[33],"counterfactual":[34],"events,":[35],"because":[36],"they":[37],"need":[38],"knowledge":[39],"not":[40],"explicitly":[41],"shown.":[42],"Existing":[43],"methods":[44],"use":[45],"coarse-grained":[46],"fusion":[47,64],"of":[48,71],"language":[51],"features,":[52],"ignoring":[53],"temporal":[54,69,84],"information.":[55],"To":[56],"address":[57],"this,":[58],"we":[59],"propose":[60],"novel":[62],"vision-text":[63],"module":[65,77],"learns":[67],"context":[70],"question.":[75],"Our":[76],"expands":[78],"tokens":[80],"along":[81],"video's":[83],"axis":[85],"fuses":[87],"them":[88],"with":[89,96],"features":[91],"to":[92],"generate":[93],"new":[94],"representations":[95],"local":[97],"global":[99],"We":[101],"evaluated":[102],"our":[103],"method":[104],"on":[105],"four":[106],"VideoQA":[107],"datasets,":[108],"including":[109],"MSVD-QA,":[110],"NExT-QA,":[111],"Causal-VidQA,":[112],"AGQA-2.0.":[114]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4390190135","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-01-19T15:53:31.737722","created_date":"2023-12-26"}