{"id":"https://openalex.org/W4372266022","doi":"https://doi.org/10.1109/icassp49357.2023.10094789","title":"Decaying Contrast for Fine-Grained Video Representation Learning","display_name":"Decaying Contrast for Fine-Grained Video Representation Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266022","doi":"https://doi.org/10.1109/icassp49357.2023.10094789"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100373135","display_name":"Heng Zhang","orcid":"https://orcid.org/0000-0002-5712-6136"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heng Zhang","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027552992","display_name":"Bing Su","orcid":"https://orcid.org/0000-0001-8560-1910"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Su","raw_affiliation_strings":["Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China,Gaoling School of Artificial Intelligence,Beijing,China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100373135"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03672777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7984892129898071},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.749565839767456},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7427277565002441},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.7115226984024048},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6515341401100159},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6503891944885254},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6333209872245789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6096303462982178},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5891299247741699},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5625342130661011},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.512008011341095},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.506942093372345},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4218823313713074},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3548056483268738},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34342968463897705},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09943926334381104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07324415445327759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7984892129898071},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.749565839767456},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7427277565002441},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.7115226984024048},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6515341401100159},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6503891944885254},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6333209872245789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096303462982178},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5891299247741699},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5625342130661011},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.512008011341095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.506942093372345},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4218823313713074},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3548056483268738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34342968463897705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09943926334381104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07324415445327759},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6299999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1821462560","https://openalex.org/W2126579184","https://openalex.org/W2139038971","https://openalex.org/W2842511635","https://openalex.org/W2902287040","https://openalex.org/W2944828972","https://openalex.org/W2948242301","https://openalex.org/W2963155035","https://openalex.org/W2997907976","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3009623812","https://openalex.org/W3010874390","https://openalex.org/W3034215340","https://openalex.org/W3034781633","https://openalex.org/W3035524453","https://openalex.org/W3037927086","https://openalex.org/W3104591054","https://openalex.org/W3110190397","https://openalex.org/W3110306138","https://openalex.org/W3115964123","https://openalex.org/W3123599388","https://openalex.org/W3145385912","https://openalex.org/W4297808394","https://openalex.org/W6638523607","https://openalex.org/W6774314701","https://openalex.org/W6774352276","https://openalex.org/W6774670964","https://openalex.org/W6779965299","https://openalex.org/W6781036140","https://openalex.org/W6782052401","https://openalex.org/W6789246422"],"related_works":["https://openalex.org/W2417253731","https://openalex.org/W2350469024","https://openalex.org/W2491583298","https://openalex.org/W2036154621","https://openalex.org/W2327827625","https://openalex.org/W2395860100","https://openalex.org/W2163296013","https://openalex.org/W795077857","https://openalex.org/W2376416463","https://openalex.org/W2007338512"],"abstract_inverted_index":{"Prior":[0],"contrast-based":[1],"methods":[2],"for":[3,35,72],"video":[4,23,50,101,132],"representation":[5,75],"learning":[6],"mainly":[7],"focus":[8],"on":[9,135],"clip":[10],"discrimination":[11,112],"while":[12,102],"ignoring":[13],"the":[14,21,25,31,65,69,93,99,103,111,119,130],"context":[15],"and":[16,40],"relationship":[17],"of":[18,79,96,113],"clips":[19,37,97],"from":[20,98],"same":[22,100],"in":[24,44,129],"temporal":[26,70],"dimension.":[27],"As":[28],"a":[29,60,126],"consequence,":[30],"learned":[32],"spatiotemporal":[33,74],"representations":[34],"successive":[36],"are":[38],"inconsistent":[39],"hence":[41],"perform":[42],"poorly":[43],"fine-grained":[45,73,131],"downstream":[46],"tasks":[47],"such":[48],"as":[49],"fragment":[51],"retrieval":[52,133],"or":[53],"localization.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"decaying":[61,86,105,121],"strategy":[62],"to":[63,91,109],"grasp":[64],"gradual":[66],"evolution":[67],"along":[68],"dimension":[71],"learning,":[76],"which":[77],"consists":[78],"two":[80],"novel":[81],"contrastive":[82,87,106,122],"losses.":[83],"The":[84],"external":[85],"loss":[88,107],"is":[89],"designed":[90],"increase":[92],"relative":[94],"similarity":[95],"internal":[104],"aims":[108],"maintain":[110],"clips.":[114],"Experimental":[115],"results":[116],"show":[117],"that":[118],"proposed":[120],"training":[123],"approach":[124],"achieves":[125],"significant":[127],"improvement":[128],"task":[134],"multiple":[136],"benchmark":[137],"datasets.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}