{"id":"https://openalex.org/W7171980553","doi":"https://doi.org/10.1145/3774521.3774572","title":"Zero-Shot Autism Behaviour Recognition Leveraging Multimodal Representations and Cross-Dataset Evaluation","display_name":"Zero-Shot Autism Behaviour Recognition Leveraging Multimodal Representations and Cross-Dataset Evaluation","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171980553","doi":"https://doi.org/10.1145/3774521.3774572"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774572","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774572","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021375290","display_name":"Darshan Gera","orcid":"https://orcid.org/0000-0002-9539-4385"},"institutions":[{"id":"https://openalex.org/I4819740","display_name":"Sri Sathya Sai Institute of Higher Learning","ror":"https://ror.org/05arzt710","country_code":"IN","type":"education","lineage":["https://openalex.org/I4819740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Darshan Gera","raw_affiliation_strings":["Sri Sathya Sai Institute of Higher Learning, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0002-9539-4385","affiliations":[{"raw_affiliation_string":"Sri Sathya Sai Institute of Higher Learning, Bengaluru, India","institution_ids":["https://openalex.org/I4819740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123777650","display_name":"Vignesh Sai Sankalp Sham","orcid":null},"institutions":[{"id":"https://openalex.org/I4819740","display_name":"Sri Sathya Sai Institute of Higher Learning","ror":"https://ror.org/05arzt710","country_code":"IN","type":"education","lineage":["https://openalex.org/I4819740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vignesh Sai Sankalp Sham","raw_affiliation_strings":["Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India"],"raw_orcid":"https://orcid.org/0009-0006-8565-8558","affiliations":[{"raw_affiliation_string":"Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India","institution_ids":["https://openalex.org/I4819740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123736647","display_name":"Ritu Raj Pradhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4819740","display_name":"Sri Sathya Sai Institute of Higher Learning","ror":"https://ror.org/05arzt710","country_code":"IN","type":"education","lineage":["https://openalex.org/I4819740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ritu Raj Pradhan","raw_affiliation_strings":["Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India"],"raw_orcid":"https://orcid.org/0009-0007-3950-6390","affiliations":[{"raw_affiliation_string":"Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India","institution_ids":["https://openalex.org/I4819740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006197061","display_name":"S. Balasubramanian","orcid":"https://orcid.org/0000-0001-8947-4840"},"institutions":[{"id":"https://openalex.org/I4819740","display_name":"Sri Sathya Sai Institute of Higher Learning","ror":"https://ror.org/05arzt710","country_code":"IN","type":"education","lineage":["https://openalex.org/I4819740"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Balasubramanian","raw_affiliation_strings":["Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India"],"raw_orcid":"https://orcid.org/0000-0001-8947-4840","affiliations":[{"raw_affiliation_string":"Sri Sathya Sai Institute of Higher Learning, Puttaparthi, India","institution_ids":["https://openalex.org/I4819740"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035065105","display_name":"Ravi Mukkamala","orcid":"https://orcid.org/0000-0001-6323-9789"},"institutions":[{"id":"https://openalex.org/I14303183","display_name":"Virginia Wesleyan University","ror":"https://ror.org/03ken7w58","country_code":"US","type":"education","lineage":["https://openalex.org/I14303183"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Mukkamala","raw_affiliation_strings":["https://www.cs.odu.edu/, Norfolk, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0001-6323-9789","affiliations":[{"raw_affiliation_string":"https://www.cs.odu.edu/, Norfolk, Virginia, USA","institution_ids":["https://openalex.org/I14303183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144179661","display_name":"Sreepada V Satya N Sarma","orcid":"https://orcid.org/0009-0005-0189-3538"},"institutions":[{"id":"https://openalex.org/I4210113876","display_name":"Sri Sathya Sai Institute of Higher Medical Sciences","ror":"https://ror.org/0251z6a72","country_code":"IN","type":"healthcare","lineage":["https://openalex.org/I4210113876"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sreepada V Satya N Sarma","raw_affiliation_strings":["https://www.sssihl.edu.in/, Puttaparthi, India"],"raw_orcid":"https://orcid.org/0009-0005-0189-3538","affiliations":[{"raw_affiliation_string":"https://www.sssihl.edu.in/, Puttaparthi, India","institution_ids":["https://openalex.org/I4210113876"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/autism-spectrum-disorder","display_name":"Autism spectrum disorder","score":0.4878000020980835},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47609999775886536},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4625999927520752},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.4499000012874603},{"id":"https://openalex.org/keywords/autism","display_name":"Autism","score":0.4489000141620636},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.43950000405311584},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133999824523926},{"id":"https://openalex.org/C2778538070","wikidata":"https://www.wikidata.org/wiki/Q1436063","display_name":"Autism spectrum disorder","level":3,"score":0.4878000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.43950000405311584},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29030001163482666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774572","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774572","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 Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2067583440","https://openalex.org/W2173495842","https://openalex.org/W2769039400","https://openalex.org/W2963524571","https://openalex.org/W3139253241","https://openalex.org/W3215086423","https://openalex.org/W4304014690","https://openalex.org/W4312560592","https://openalex.org/W4379057633","https://openalex.org/W4390102352","https://openalex.org/W4390873312","https://openalex.org/W7133241830"],"related_works":[],"abstract_inverted_index":{"Autism":[0],"Spectrum":[1],"Disorder":[2],"(ASD)":[3],"is":[4],"characterized":[5],"by":[6,37],"stereotypical":[7],"and":[8,19,60,106,133,158],"repetitive":[9],"behaviors":[10],"that":[11,110],"can":[12],"often":[13],"be":[14],"identified":[15],"through":[16],"visual":[17,55],"patterns":[18],"contextual":[20],"understanding.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"propose":[26],"a":[27,82],"novel":[28],"zero-shot":[29,95,117],"multimodal":[30],"framework":[31,90],"for":[32,154],"early":[33],"ASD":[34,160],"behavior":[35,161],"recognition":[36,97,162],"leveraging":[38],"Large":[39],"Vision-Language":[40],"Models":[41],"(LVLMs),":[42],"specifically":[43],"InstructBLIP-Video,":[44],"in":[45,94],"conjunction":[46],"with":[47,63,74],"the":[48,89,104,139,149],"Video":[49],"Swin":[50],"Transformer.":[51],"Our":[52,146],"approach":[53],"extracts":[54],"features":[56,66],"from":[57,68,129],"30-frame":[58],"clips":[59],"fuses":[61],"them":[62],"instruction-based":[64],"seman-tic":[65],"generated":[67],"descriptive":[69],"prompts.":[70],"These":[71],"are":[72],"aligned":[73],"class-level":[75],"textual":[76],"descriptions":[77],"via":[78],"contrastive":[79],"learning":[80],"using":[81],"CLIP-based":[83],"encoder.":[84],"Without":[85],"any":[86],"task-specific":[87],"fine-tuning,":[88],"demonstrates":[91],"state-of-the-art":[92],"performance":[93],"action":[96],"of":[98,141,151],"ASD-related":[99],"behaviors.":[100],"Extensive":[101],"experiments":[102],"on":[103],"SSBD":[105],"ESBD":[107],"datasets":[108],"demonstrate":[109],"our":[111],"model":[112],"not":[113],"only":[114],"achieves":[115],"competitive":[116],"performance,":[118],"but":[119],"also":[120],"generalizes":[121],"effectively":[122],"across":[123],"datasets.":[124],"We":[125],"further":[126],"present":[127],"insights":[128],"confusion":[130],"matrix":[131],"analyses":[132],"conduct":[134],"an":[135],"ablation":[136],"study":[137],"highlighting":[138],"impact":[140],"different":[142],"projection":[143],"head":[144],"designs.":[145],"findings":[147],"underscore":[148],"potential":[150],"vision-language":[152],"models":[153],"building":[155],"efficient,":[156],"generalizable,":[157],"low-resource":[159],"systems.":[163]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}
