{"id":"https://openalex.org/W7164845633","doi":"https://doi.org/10.1145/3805622.3810695","title":"Fine-grained Text-Video Retrieval with Patch-level Temporal Difference and Aggregation","display_name":"Fine-grained Text-Video Retrieval with Patch-level Temporal Difference and Aggregation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164845633","doi":"https://doi.org/10.1145/3805622.3810695"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810695","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810695","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108680971","display_name":"Jialong Hu","orcid":"https://orcid.org/0009-0008-3196-2188"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialong Hu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-3196-2188","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025890671","display_name":"Zijie Song","orcid":"https://orcid.org/0000-0002-1262-764X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Song","raw_affiliation_strings":["Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1262-764X","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114803028","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0001-7243-2177"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7243-2177","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040235604","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-1042-8361"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1042-8361","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019391894","display_name":"Jia Li","orcid":"https://orcid.org/0000-0001-9446-249X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9446-249X","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101459058","display_name":"Yixiao Ma","orcid":"https://orcid.org/0009-0002-7849-6950"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiao Ma","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-7849-6950","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93860064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"327","last_page":"336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9165999889373779,"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":0.9165999889373779,"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":0.04569999873638153,"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":0.007799999788403511,"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/salient","display_name":"Salient","score":0.5552999973297119},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.4869999885559082},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"Temporal resolution","score":0.4674000144004822},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.430400013923645},{"id":"https://openalex.org/keywords/complementarity","display_name":"Complementarity (molecular biology)","score":0.4255000054836273},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.414000004529953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3431999981403351},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.3391999900341034},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537000179290771},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5552999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288000106811523},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3244999945163727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C202227193","wikidata":"https://www.wikidata.org/wiki/Q6345568","display_name":"Kadir\u2013Brady saliency detector","level":4,"score":0.259799987077713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810695","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810695","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.417992502450943,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2885775891","https://openalex.org/W2963017553","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2984008963","https://openalex.org/W2990503944","https://openalex.org/W3035265375","https://openalex.org/W3043840704","https://openalex.org/W3174873881","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W4225414521","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312299780","https://openalex.org/W4312372711","https://openalex.org/W4386072365","https://openalex.org/W4386075789","https://openalex.org/W4386076265","https://openalex.org/W4390871725","https://openalex.org/W4390872434","https://openalex.org/W4390873082","https://openalex.org/W4390874668","https://openalex.org/W4390889802","https://openalex.org/W4393147969","https://openalex.org/W4393159202","https://openalex.org/W4402703062","https://openalex.org/W4402704596","https://openalex.org/W4402777374","https://openalex.org/W4409366588","https://openalex.org/W4409366779","https://openalex.org/W4413144429","https://openalex.org/W4413144844","https://openalex.org/W4413259066","https://openalex.org/W4414360309","https://openalex.org/W4415537437","https://openalex.org/W4415708746","https://openalex.org/W4415799009","https://openalex.org/W7133218155"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Text-Video":[1],"Retrieval":[2],"(TVR)":[3],"methods":[4],"predominantly":[5],"rely":[6],"on":[7,134],"global":[8],"frame":[9],"representations,":[10],"often":[11],"disregarding":[12],"the":[13,62,81,111,154,162,173],"fine-grained":[14,121,169],"temporal":[15,166],"variations":[16,79],"required":[17],"for":[18,57],"precise":[19,117],"patch-level":[20],"alignment.":[21,71],"This":[22],"is":[23,28],"critical":[24],"as":[25],"video":[26,127],"motion":[27,92],"inherently":[29],"spatially":[30],"localized;":[31],"consequently,":[32],"coarse":[33],"frame-level":[34],"modeling":[35,65,167],"tends":[36],"to":[37,89,105,115],"be":[38],"dominated":[39],"by":[40],"static":[41,86],"backgrounds,":[42],"overshadowing":[43],"salient":[44],"action":[45],"cues.":[46],"To":[47],"address":[48],"this":[49],"limitation,":[50],"we":[51],"propose":[52],"TRFG,":[53],"a":[54,101,107,120],"novel":[55],"framework":[56],"text-video":[58],"retrieval":[59,149],"that":[60,140],"addresses":[61],"challenges":[63],"of":[64,110,158,164],"Temporal":[66,74,102],"Reasoning":[67],"and":[68,137,148,156,168],"Fine-Grained":[69],"cross-modal":[70],"First,":[72],"our":[73],"Difference":[75],"module":[76,104,123],"captures":[77],"frame-to-frame":[78],"at":[80],"patch":[82],"level,":[83],"effectively":[84],"suppressing":[85],"background":[87],"noise":[88],"highlight":[90],"\"active\"":[91],"regions.":[93],"Second,":[94],"these":[95,125],"differential":[96],"signals":[97],"are":[98],"synthesized":[99],"via":[100],"Aggregation":[103],"form":[106],"coherent":[108],"representation":[109],"event\u2019s":[112],"trajectory.":[113],"Finally,":[114],"ensure":[116],"semantic":[118],"matching,":[119],"interaction":[122,170],"aligns":[124],"dynamic":[126],"tokens":[128],"with":[129],"textual":[130],"details.":[131],"Extensive":[132],"experiments":[133],"MSRVTT,":[135],"ActivityNet,":[136],"DiDeMo":[138],"demonstrate":[139],"TRFG":[141],"achieves":[142],"state-of-the-art":[143],"performance":[144],"across":[145],"multiple":[146],"backbones":[147],"tasks.":[150],"Ablation":[151],"studies":[152],"confirm":[153],"complementarity":[155],"generalizability":[157],"both":[159],"modules,":[160],"underscoring":[161],"importance":[163],"explicit":[165],"in":[171],"bridging":[172],"modality":[174],"gap.":[175]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}