{"id":"https://openalex.org/W3153098222","doi":"https://doi.org/10.1145/3404835.3463021","title":"Cross Interaction Network for Natural Language Guided Video Moment Retrieval","display_name":"Cross Interaction Network for Natural Language Guided Video Moment Retrieval","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3153098222","doi":"https://doi.org/10.1145/3404835.3463021","mag":"3153098222"},"language":"en","primary_location":{"id":"doi:10.1145/3404835.3463021","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5039790968","display_name":"Xinli Yu","orcid":"https://orcid.org/0000-0002-8211-8058"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinli Yu","raw_affiliation_strings":["Temple University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102862530","display_name":"Mohsen Malmir","orcid":"https://orcid.org/0000-0002-8904-8099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohsen Malmir","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110117463","display_name":"Xin He","orcid":"https://orcid.org/0000-0003-0755-0964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064432881","display_name":"Jiangning Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiangning Chen","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748162","display_name":"Tong Wang","orcid":"https://orcid.org/0000-0003-4961-5092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Wang","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038042965","display_name":"Yue Wu","orcid":"https://orcid.org/0000-0001-8032-706X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320118","display_name":"Yue Liu","orcid":"https://orcid.org/0000-0003-2958-9923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Liu","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355884","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-4259-3882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Amazon.com, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon.com, Boston, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5039790968"],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":1.2627,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8163064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1860","last_page":"1864"},"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":0.9998000264167786,"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":0.9948999881744385,"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":0.8707826137542725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5990099310874939},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5045469999313354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4963870644569397},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4961896538734436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46790680289268494},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4409111738204956},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4326939582824707},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42853161692619324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3518759310245514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707826137542725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5990099310874939},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5045469999313354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4963870644569397},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4961896538734436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46790680289268494},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4409111738204956},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4326939582824707},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42853161692619324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3518759310245514},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404835.3463021","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404835.3463021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W2337252826","https://openalex.org/W2894280539","https://openalex.org/W2962869524","https://openalex.org/W2963389687","https://openalex.org/W2963524571","https://openalex.org/W2964089981","https://openalex.org/W2970608575","https://openalex.org/W2979933490","https://openalex.org/W2998355566","https://openalex.org/W3035339529","https://openalex.org/W3035640828","https://openalex.org/W3118778629"],"related_works":["https://openalex.org/W2185469136","https://openalex.org/W4306353150","https://openalex.org/W8219677","https://openalex.org/W3216879894","https://openalex.org/W2168054807","https://openalex.org/W2058990474","https://openalex.org/W2026860389","https://openalex.org/W2043363698","https://openalex.org/W3207883763","https://openalex.org/W4386977688"],"abstract_inverted_index":{"Natural":[0],"language":[1],"query":[2,49,102],"grounding":[3],"in":[4,52,64,78,115,189],"videos":[5],"is":[6],"a":[7,35,53,70,123],"challenging":[8],"task":[9,137],"that":[10,127,142,174],"requires":[11],"comprehensive":[12],"understanding":[13],"of":[14,20,185],"the":[15,30,44,116,144,175,186,192,207],"query,":[16],"video":[17,51,105,117],"and":[18,47,50,95,104,110,131,169],"fusion":[19,37,81],"information":[21],"across":[22],"these":[23],"modalities.":[24],"Existing":[25],"methods":[26,58],"mostly":[27],"emphasize":[28],"on":[29,163,194,206],"query-to-video":[31],"one-way":[32],"interaction":[33,75],"with":[34,73],"late":[36],"scheme,":[38],"lacking":[39],"effective":[40,155],"ways":[41],"to":[42,83,182],"capture":[43,84],"relationship":[45],"within":[46],"between":[48],"fine-grained":[54],"manner.":[55],"Moreover,":[56],"current":[57],"are":[59],"often":[60],"overly":[61],"complicated":[62],"resulting":[63],"long":[65],"training":[66,125,140,159],"time.":[67],"We":[68,172],"propose":[69,122],"self-attention":[71],"together":[72],"cross":[74],"multi-head-attention":[76],"mechanism":[77],"an":[79,164],"early":[80],"scheme":[82],"video-query":[85],"intra-dependencies":[86],"as":[87,89],"well":[88],"inter-relation":[90],"from":[91],"both":[92],"directions":[93],"(query-to-video":[94],"video-to-query).":[96],"The":[97,134],"cross-attention":[98],"method":[99,177],"can":[100],"associate":[101],"words":[103],"frames":[106],"at":[107],"any":[108],"position":[109],"account":[111],"for":[112],"long-range":[113],"dependencies":[114],"context.":[118],"In":[119],"addition,":[120],"we":[121],"multi-task":[124],"objective":[126],"includes":[128],"start/end":[129,145],"prediction":[130,146],"moment":[132,135],"segmentation.":[133],"segmentation":[136],"provides":[138],"additional":[139],"signals":[141],"remedy":[143],"noise":[147],"caused":[148],"by":[149,201],"annotator":[150],"disagreement.":[151],"Our":[152],"simple":[153],"yet":[154],"architecture":[156],"enables":[157],"speedy":[158],"(within":[160],"1":[161],"hour":[162],"AWS":[165],"P3.2xlarge":[166],"GPU":[167],"instance)":[168],"instant":[170],"inference.":[171],"showed":[173],"proposed":[176],"achieves":[178],"superior":[179],"performance":[180],"compared":[181],"complex":[183],"state":[184],"art":[187],"methods,":[188],"particular":[190],"surpassing":[191],"SOTA":[193],"high":[195],"IoU":[196],"metrics":[197],"([email":[198],"protected],":[199],"IoU=0.7)":[200],"3.52%":[202],"absolute":[203],"(11.09%":[204],"relative)":[205],"Charades-STA":[208],"dataset.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}