{"id":"https://openalex.org/W4415536518","doi":"https://doi.org/10.1145/3746027.3755484","title":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","display_name":"MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536518","doi":"https://doi.org/10.1145/3746027.3755484"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755484","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755484","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056459475","display_name":"Hongxu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongxu Ma","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-8623-0976","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076345681","display_name":"Guanshuo Wang","orcid":"https://orcid.org/0000-0001-6391-4385"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanshuo Wang","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6391-4385","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005929117","display_name":"Fufu Yu","orcid":"https://orcid.org/0000-0002-4062-696X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fufu Yu","raw_affiliation_strings":["Tencent YouTu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4062-696X","affiliations":[{"raw_affiliation_string":"Tencent YouTu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010363243","display_name":"Qiong Jia","orcid":"https://orcid.org/0000-0001-9576-6559"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiong Jia","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9576-6559","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086397952","display_name":"Shouhong Ding","orcid":"https://orcid.org/0000-0002-3175-3553"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouhong Ding","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3175-3553","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4514","last_page":"4523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","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/T11439","display_name":"Video Analysis and Summarization","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/T10531","display_name":"Advanced Vision and Imaging","score":0.9987000226974487,"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":0.9983999729156494,"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/semantics","display_name":"Semantics (computer science)","score":0.7613000273704529},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.625},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5392000079154968},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5008999705314636},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5005999803543091},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4629000127315521},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3531999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843999862670898},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7613000273704529},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835000276565552},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4339999854564667},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755484","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755484","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1958932515","https://openalex.org/W2103908291","https://openalex.org/W2111078031","https://openalex.org/W2512435841","https://openalex.org/W2737677090","https://openalex.org/W2776277180","https://openalex.org/W2894280539","https://openalex.org/W2897628926","https://openalex.org/W2919974746","https://openalex.org/W2948958195","https://openalex.org/W2962766617","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2963729528","https://openalex.org/W2963919999","https://openalex.org/W2964089981","https://openalex.org/W2964158702","https://openalex.org/W2990503944","https://openalex.org/W2997429269","https://openalex.org/W3035339529","https://openalex.org/W3096609285","https://openalex.org/W3196253003","https://openalex.org/W3201832684","https://openalex.org/W4312544061","https://openalex.org/W4312693115","https://openalex.org/W4386083094","https://openalex.org/W4402727583"],"related_works":[],"abstract_inverted_index":{"Video":[0],"Moment":[1],"Retrieval":[2],"(MR)":[3],"and":[4,13,42,80,99,110,127,147,159],"Highlight":[5],"Detection":[6],"(HD)":[7],"aim":[8],"to":[9,103,152],"pinpoint":[10],"specific":[11],"moments":[12],"assess":[14],"clip-wise":[15],"relevance":[16],"based":[17],"on":[18,163],"the":[19,36,53,85,90,93,120,125,139,154],"text":[20,87],"query.":[21],"While":[22],"DETR-based":[23],"joint":[24],"frameworks":[25],"have":[26],"made":[27],"significant":[28],"strides,":[29],"there":[30],"remains":[31],"untapped":[32],"potential":[33],"in":[34],"harnessing":[35],"intricate":[37],"relationships":[38],"between":[39],"temporal":[40,97],"motion":[41,79,98,126],"spatial":[43,100],"semantics":[44,81,101,128],"within":[45,78,124],"video":[46],"content.":[47],"In":[48],"this":[49,135],"paper,":[50],"we":[51,118,137],"propose":[52,148],"Motion-Semantics":[54],"DETR":[55],"(MS-DETR),":[56],"a":[57,176],"framework":[58],"that":[59,168],"captures":[60],"rich":[61],"motion-semantics":[62],"features":[63],"through":[64],"unified":[65],"learning":[66,151],"for":[67,108,115],"MR/HD":[68,131,165],"tasks.":[69],"The":[70],"encoder":[71],"first":[72],"explicitly":[73],"models":[74,174],"disentangled":[75],"intra-modal":[76],"correlations":[77],"dimensions,":[82],"guided":[83],"by":[84,144,175],"given":[86],"queries.":[88],"Subsequently,":[89],"decoder":[91],"utilizes":[92],"task-wise":[94],"correlation":[95],"across":[96],"dimensions":[102,129,143],"enable":[104],"precise":[105],"query-guided":[106],"localization":[107],"MR":[109],"refined":[111],"highlight":[112],"boundary":[113],"delineation":[114],"HD.":[116],"Furthermore,":[117],"observe":[119],"inherent":[121],"sparsity":[122],"dilemma":[123],"of":[130],"datasets.":[132],"To":[133],"address":[134],"issue,":[136],"enrich":[138],"corpus":[140],"from":[141],"both":[142],"generation":[145],"strategies":[146],"contrastive":[149],"denoising":[150],"ensure":[153],"above":[155],"components":[156],"learn":[157],"robustly":[158],"effectively.":[160],"Extensive":[161],"experiments":[162],"four":[164],"benchmarks":[166],"demonstrate":[167],"our":[169],"method":[170],"outperforms":[171],"existing":[172],"state-of-the-art":[173],"margin.":[177],"Our":[178],"code":[179],"is":[180],"available":[181],"at":[182],"https://github.com/snailma0229/MS-DETR.git.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}