{"id":"https://openalex.org/W3021338036","doi":"https://doi.org/10.1145/3293353.3293363","title":"Multimodal Egocentric Activity Recognition Using Multi-stream CNN","display_name":"Multimodal Egocentric Activity Recognition Using Multi-stream CNN","publication_year":2018,"publication_date":"2018-12-18","ids":{"openalex":"https://openalex.org/W3021338036","doi":"https://doi.org/10.1145/3293353.3293363","mag":"3021338036"},"language":"en","primary_location":{"id":"doi:10.1145/3293353.3293363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033495691","display_name":"Javed Imran","orcid":"https://orcid.org/0000-0001-6832-3509"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Javed Imran","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030765476","display_name":"Balasubramanian Raman","orcid":"https://orcid.org/0000-0001-6277-6267"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Balasubramanian Raman","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9988999962806702,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/computer-science","display_name":"Computer science","score":0.7275890707969666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5762650966644287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5009503364562988},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42175206542015076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3999583423137665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275890707969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5762650966644287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5009503364562988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42175206542015076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3999583423137665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293353.3293363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293353.3293363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing","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":28,"referenced_works":["https://openalex.org/W1507216665","https://openalex.org/W1522734439","https://openalex.org/W1947050545","https://openalex.org/W1947481528","https://openalex.org/W2003985931","https://openalex.org/W2050709211","https://openalex.org/W2108598243","https://openalex.org/W2127127580","https://openalex.org/W2136668269","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2193384753","https://openalex.org/W2194775991","https://openalex.org/W2195342085","https://openalex.org/W2270470215","https://openalex.org/W2341342588","https://openalex.org/W2342792048","https://openalex.org/W2432964524","https://openalex.org/W2462996230","https://openalex.org/W2480629583","https://openalex.org/W2751125921","https://openalex.org/W2781400102","https://openalex.org/W2798702867","https://openalex.org/W2802503116","https://openalex.org/W2952186347","https://openalex.org/W2962727177","https://openalex.org/W2964222622","https://openalex.org/W4256361765"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Egocentric":[0],"activity":[1,33,160],"recognition":[2,34],"(EAR)":[3],"is":[4,102,116,126],"an":[5],"emerging":[6],"area":[7],"in":[8,54],"the":[9,17,50,139,144,172],"field":[10],"of":[11,20,59,132,142],"computer":[12],"vision":[13,107],"research.":[14],"Motivated":[15],"by":[16,151],"current":[18,173],"success":[19],"Convolutional":[21],"Neural":[22],"Network":[23],"(CNN),":[24],"we":[25],"propose":[26],"a":[27,96,122],"multi-stream":[28],"CNN":[29],"for":[30,105,110],"multimodal":[31,158],"egocentric":[32,159],"using":[35],"visual":[36,64],"(RGB":[37],"videos)":[38],"and":[39,70,90,121,176],"sensor":[40,111,133],"stream":[41],"(accelerometer,":[42],"gyroscope,":[43],"etc.).":[44],"In":[45],"order":[46],"to":[47,94,129],"effectively":[48],"capture":[49],"spatio-temporal":[51],"information":[52],"contained":[53],"RGB":[55],"videos,":[56],"two":[57],"types":[58],"modalities":[60],"are":[61,78,91,149],"extracted":[62],"from":[63,135],"data:":[65],"Approximate":[66],"Dynamic":[67],"Image":[68,73],"(ADI)":[69],"Stacked":[71],"Difference":[72],"(SDI).":[74],"These":[75],"image-based":[76],"representations":[77],"generated":[79],"both":[80],"at":[81],"clip":[82],"level":[83],"as":[84,86],"well":[85],"entire":[87],"video":[88],"level,":[89],"then":[92],"utilized":[93],"finetune":[95],"pretrained":[97],"2D-CNN":[98],"called":[99],"MobileNet,":[100],"which":[101],"specifically":[103],"designed":[104],"mobile":[106],"applications.":[108],"Similarly":[109],"data,":[112],"each":[113,130],"training":[114],"sample":[115],"divided":[117],"into":[118],"three":[119],"segments,":[120],"deep":[123,177],"1D-CNN":[124],"network":[125],"trained":[127],"(corresponding":[128],"type":[131],"stream)":[134],"scratch.":[136],"During":[137],"testing,":[138],"softmax":[140],"scores":[141],"all":[143],"streams":[145],"(visual":[146],"+":[147],"sensor)":[148],"combined":[150],"late":[152],"fusion.":[153],"The":[154],"experiments":[155],"performed":[156],"on":[157],"dataset":[161],"demonstrates":[162],"that":[163],"our":[164],"proposed":[165],"approach":[166],"can":[167],"achieve":[168],"state-of-the-art":[169],"results,":[170],"outperforming":[171],"best":[174],"handcrafted":[175],"learning":[178],"based":[179],"techniques.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}