{"id":"https://openalex.org/W4402981346","doi":"https://doi.org/10.1109/icme57554.2024.10687750","title":"DeCMG: Denoise with Cross-modality Guidance Makes Better Text-Video Retrieval","display_name":"DeCMG: Denoise with Cross-modality Guidance Makes Better Text-Video Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981346","doi":"https://doi.org/10.1109/icme57554.2024.10687750"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5006470125","display_name":"Rui Deng","orcid":"https://orcid.org/0000-0002-6666-9095"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Deng","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.2142,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50651864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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":0.9965999722480774,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9962000250816345,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9957000017166138,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7749218940734863},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703588604927063},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46084001660346985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45789793133735657},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4428626298904419},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.43008050322532654},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3317272961139679}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7749218940734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703588604927063},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46084001660346985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45789793133735657},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4428626298904419},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.43008050322532654},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3317272961139679}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2143017621","https://openalex.org/W2425121537","https://openalex.org/W2886641317","https://openalex.org/W2963017553","https://openalex.org/W2984008963","https://openalex.org/W3174873881","https://openalex.org/W3204588463","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312372711","https://openalex.org/W6684090549","https://openalex.org/W6784184991","https://openalex.org/W6784333009","https://openalex.org/W6787247333","https://openalex.org/W6791353385","https://openalex.org/W6846822233"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2399947890","https://openalex.org/W655728004","https://openalex.org/W2046272293"],"abstract_inverted_index":{"The":[0,66],"effectiveness":[1,167],"of":[2,34,40,142,168],"text-video":[3,61],"retrieval":[4],"depends":[5],"on":[6],"establishing":[7],"precise":[8],"semantic":[9],"correspondence":[10],"between":[11],"text":[12],"and":[13,27,37,100,108,127,146,157,166],"video.":[14],"However,":[15],"current":[16],"CLIP-based":[17],"[1]":[18],"approaches,":[19],"have":[20],"encountered":[21],"challenges":[22],"in":[23,68,73,85,119,124,144,148],"adequately":[24],"learning":[25],"temporal":[26],"cross-modality":[28,64],"features":[29,72],"due":[30],"to":[31,76,102],"the":[32,38,71,106,164],"lack":[33],"prior":[35],"knowledge":[36],"scarcity":[39],"labeled":[41],"training":[42,125],"data.":[43],"To":[44],"tackle":[45],"this":[46],"issue,":[47],"we":[48],"propose":[49],"DeCMG":[50,69,93,138],"(Denoise":[51],"with":[52,88],"Cross-Modality":[53],"Guidance),":[54],"a":[55,82,89,121],"novel":[56],"method":[57],"that":[58],"enhances":[59],"fine-grained":[60],"alignment":[62,104],"through":[63],"collaboration.":[65],"collaboration":[67],"allows":[70],"one":[74],"modality":[75,87],"be":[77,129],"better":[78],"optimized":[79],"by":[80],"performing":[81],"denoising":[83,97],"task":[84],"another":[86],"guidance":[90],"vector.":[91],"Specifically,":[92],"incorporates":[94],"two":[95],"self-generated":[96],"tasks":[98,113],"(TextDe":[99],"VisualDe)":[101],"achieve":[103],"at":[105],"word-video":[107],"frame-text":[109],"levels,":[110],"respectively.":[111],"These":[112,160],"are":[114],"implemented":[115],"as":[116],"plugins,":[117],"resulting":[118],"only":[120],"minor":[122],"increase":[123],"time":[126],"can":[128],"entirely":[130],"removed":[131],"during":[132],"inference.":[133],"Across":[134],"four":[135],"benchmark":[136],"datasets,":[137],"yielded":[139],"average":[140],"improvements":[141],"1.1%":[143],"text-to-video":[145],"1.8%":[147],"video-to-text":[149],"Recall@1,":[150],"surpassing":[151],"our":[152],"baseline":[153],"models":[154],"(X-CLIP":[155],"[2]":[156],"X-Pool":[158],"[3]).":[159],"experimental":[161],"results":[162],"validate":[163],"efficiency":[165],"DeCMG.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}