{"id":"https://openalex.org/W4387967944","doi":"https://doi.org/10.1145/3581783.3611714","title":"Depth-Aware Sparse Transformer for Video-Language Learning","display_name":"Depth-Aware Sparse Transformer for Video-Language Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387967944","doi":"https://doi.org/10.1145/3581783.3611714"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084439574","display_name":"Haonan Zhang","orcid":"https://orcid.org/0000-0003-1015-7338"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haonan Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-1015-7338","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China & Sichuan Artificial Intelligence Research Institute, Yibin, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Sichuan Artificial Intelligence Research Institute, Yibin, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Delft University of Technology, Delft, Holland"],"raw_orcid":"https://orcid.org/0000-0002-5771-2549","affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Holland","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4778","last_page":"4787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983999729156494,"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":0.783856987953186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.739998996257782},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6264699101448059},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4908636212348938},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42386671900749207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40153151750564575},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10461866855621338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783856987953186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.739998996257782},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6264699101448059},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4908636212348938},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42386671900749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40153151750564575},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10461866855621338},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611714","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G2546663186","display_name":null,"funder_award_id":"62020106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G259376912","display_name":null,"funder_award_id":"YYJC012022019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3015758051","display_name":null,"funder_award_id":"2022YFC2009900","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6864684409","display_name":null,"funder_award_id":"62122018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7314976618","display_name":"\u878d\u5408\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684\u6df1\u5ea6\u89c6\u89c9\u7406\u89e3\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8027008232","display_name":"\u534f\u540c\u6df1\u5ea6\u89c6\u9891\u7406\u89e3\u3001\u63cf\u8ff0\u548c\u89c6\u89c9\u95ee\u7b54\u7684\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772116","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8749585922","display_name":null,"funder_award_id":"No. 62122018, No. 62020106008, No. 61772116, No. 61872064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2554906389","https://openalex.org/W2890598214","https://openalex.org/W2904291752","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2962934715","https://openalex.org/W2964350391","https://openalex.org/W2981750519","https://openalex.org/W2997344006","https://openalex.org/W2997805943","https://openalex.org/W3034221024","https://openalex.org/W3035309251","https://openalex.org/W3035356601","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035635319","https://openalex.org/W3096935578","https://openalex.org/W3167092180","https://openalex.org/W3168640669","https://openalex.org/W3173367591","https://openalex.org/W3176425931","https://openalex.org/W3204588463","https://openalex.org/W3205398323","https://openalex.org/W3206675006","https://openalex.org/W3209229003","https://openalex.org/W3217340782","https://openalex.org/W4200631219","https://openalex.org/W4200631318","https://openalex.org/W4214520160","https://openalex.org/W4285606530","https://openalex.org/W4304481345","https://openalex.org/W4312384316","https://openalex.org/W6600704668"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2748922771"],"abstract_inverted_index":{"In":[0],"Video-Language":[1],"(VL)":[2],"learning":[3],"tasks,":[4,169],"a":[5,86,109,122,145,164],"massive":[6],"amount":[7],"of":[8,15,32,54,158,167],"text":[9],"annotations":[10],"are":[11],"describing":[12],"geometrical":[13,45],"relationships":[14],"instances":[16],"(e.g.":[17,37],"19.6%":[18],"to":[19,61,81,95,118,137,148],"45.0%":[20],"in":[21,42],"MSVD,":[22],"MSR-VTT,":[23],"MSVD-QA":[24],"and":[25,46,89,98,187],"MSVRTT-QA),":[26],"which":[27],"often":[28],"become":[29],"the":[30,33,50,63,83],"bottleneck":[31],"current":[34,72],"VL":[35],"tasks":[36],"60.8%":[38],"vs.":[39],"98.2%":[40],"CIDEr":[41],"MSVD":[43,174],"for":[44,133,178,192],"non-geometrical":[47],"annotations).":[48],"Considering":[49],"rich":[51],"spatial":[52],"information":[53,70],"depth":[55,69],"map,":[56],"an":[57],"intuitive":[58],"way":[59],"is":[60,79,131,196],"enrich":[62],"conventional":[64],"2D":[65,140],"visual":[66],"representations":[67,92],"with":[68,93,127,163],"through":[71],"SOTA":[73],"models,":[74],"e.g.":[75],"transformer.":[76],"However,":[77],"it":[78,161],"cumbersome":[80],"compute":[82],"self-attention":[84],"on":[85,100],"long-range":[87,154],"sequence":[88],"heterogeneous":[90],"video-level":[91],"regard":[94],"computation":[96],"cost":[97],"flexibility":[99],"various":[101],"frame":[102],"scales.":[103],"To":[104],"tackle":[105],"this,":[106],"we":[107,143],"propose":[108],"hierarchical":[110,146],"transformer,":[111],"termed":[112],"Depth-Aware":[113],"Sparse":[114],"Transformer":[115],"(DAST).":[116],"Specifically,":[117],"guarantee":[119],"computational":[120,129],"efficiency,":[121],"depth-aware":[123,139],"sparse":[124],"attention":[125],"modular":[126],"linear":[128],"complexity":[130],"designed":[132],"each":[134],"transformer":[135],"layer":[136],"learn":[138],"representations.":[141],"Furthermore,":[142],"design":[144],"structure":[147],"maintain":[149],"multi-scale":[150],"temporal":[151],"coherence":[152],"across":[153],"dependencies.":[155],"These":[156],"qualities":[157],"DAST":[159],"make":[160],"compatible":[162],"broad":[165],"range":[166],"video-language":[168],"including":[170],"video":[171,180],"captioning":[172],"(achieving":[173],"107.8%,":[175],"MSR-VTT":[176],"52.5%":[177],"CIDEr),":[179],"question":[181],"answering":[182],"(MSVD-QA":[183],"44.1%,":[184],"MSRVTT-QA":[185],"39.4%),":[186],"video-text":[188],"matching":[189],"(MSR-VTT":[190],"215.7":[191],"SumR).":[193],"Our":[194],"code":[195],"available":[197],"at":[198],"https://github.com/zchoi/DAST":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}