{"id":"https://openalex.org/W4415540858","doi":"https://doi.org/10.1145/3746027.3755268","title":"Video-to-Image Affordance Grounding via Visual Conceptual Learning","display_name":"Video-to-Image Affordance Grounding via Visual Conceptual Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540858","doi":"https://doi.org/10.1145/3746027.3755268"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755268","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5053970295","display_name":"Zhiyuan Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyuan Fan","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071264607","display_name":"K.M. Liang","orcid":"https://orcid.org/0009-0000-4613-247X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyi Liang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053970295"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1709259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3972","last_page":"3980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9952999949455261,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.9447000026702881},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5288000106811523},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.3912999927997589},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.37119999527931213},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9447000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639999985694885},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164000034332275},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4320000112056732},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C13606891","wikidata":"https://www.wikidata.org/wiki/Q2623243","display_name":"Conceptual model","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755268","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2616247523","https://openalex.org/W2885511330","https://openalex.org/W2955657995","https://openalex.org/W2983465317","https://openalex.org/W3021013305","https://openalex.org/W3096609285","https://openalex.org/W3135359526","https://openalex.org/W3145450063","https://openalex.org/W3153149165","https://openalex.org/W4313156423","https://openalex.org/W4390227499"],"related_works":[],"abstract_inverted_index":{"Video-to-Image":[0],"Affordance":[1],"Grounding":[2],"aims":[3],"to":[4,50,83,89,113,136],"localize":[5],"object":[6],"affordances":[7],"in":[8,37],"static":[9],"images":[10],"by":[11],"learning":[12,130],"from":[13,95,131,138],"human":[14],"demonstration":[15,96],"videos.":[16,97],"However,":[17],"existing":[18],"fully":[19,80],"supervised":[20,42,81],"methods":[21],"rely":[22],"on":[23,146],"paired":[24,168],"image-video":[25],"inputs":[26,170],"during":[27,171],"both":[28],"training":[29],"and":[30,107],"inference,":[31],"which":[32],"significantly":[33],"limits":[34],"their":[35],"practicality":[36],"real-world":[38],"scenarios.":[39],"Conversely,":[40],"weakly":[41],"approaches":[43],"support":[44],"video-free":[45],"inference":[46],"but":[47,140],"often":[48],"struggle":[49],"capture":[51],"the":[52,73,78,85,99,119,134],"most":[53],"critical":[54],"interaction":[55,93],"features":[56,94,104],"necessary":[57],"for":[58,128],"affordance":[59,129],"learning.":[60],"To":[61],"overcome":[62],"these":[63,102],"limitations,":[64],"we":[65,76],"propose":[66],"a":[67,108,125],"novel":[68],"two-stage":[69],"framework,":[70],"VCL.":[71],"In":[72,98],"first":[74],"stage,":[75,101],"adopt":[77],"standard":[79],"paradigm":[82,127],"train":[84],"model,":[86],"enabling":[87,133],"it":[88],"effectively":[90],"extract":[91],"meaningful":[92],"second":[100],"extracted":[103],"are":[105],"conceptualized,":[106],"conceptual":[109],"module":[110],"is":[111],"introduced":[112],"map":[114],"natural":[115],"language":[116],"instructions":[117],"into":[118],"concept":[120],"space.":[121],"Our":[122],"approach":[123],"establishes":[124],"new":[126],"demonstrations,":[132],"model":[135,154,162],"learn":[137],"video":[139,169],"perform":[141],"precise":[142],"text-conditioned":[143,161],"inference.":[144,172],"Experiments":[145],"two":[147],"benchmark":[148],"datasets":[149],"show":[150],"that":[151],"our":[152,160],"base":[153],"outperforms":[155],"previous":[156],"state-of-the-art":[157],"methods,":[158],"while":[159],"achieves":[163],"competitive":[164],"performance":[165],"without":[166],"requiring":[167],"Code":[173],"will":[174],"be":[175],"released":[176],"at":[177],"https://github.com/Fanzy27/VCL.":[178]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}