{"id":"https://openalex.org/W2752576222","doi":"https://doi.org/10.1145/3077136.3084144","title":"Seeing Bot","display_name":"Seeing Bot","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2752576222","doi":"https://doi.org/10.1145/3077136.3084144","mag":"2752576222"},"language":"en","primary_location":{"id":"doi:10.1145/3077136.3084144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3084144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"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":"Yingwei Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024833177","display_name":"Zhaofan Qiu","orcid":"https://orcid.org/0000-0002-7485-9198"},"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":"Zhaofan Qiu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"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":"Houqiang Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"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/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5572,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79635223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1341","last_page":"1344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9940999746322632,"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/closed-captioning","display_name":"Closed captioning","score":0.9878900051116943},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8580112457275391},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5458186268806458},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5294439792633057},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5218269228935242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4775848388671875},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43372848629951477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4018063247203827},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.35082244873046875},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34231171011924744},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33681806921958923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3333343267440796},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06507930159568787}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9878900051116943},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580112457275391},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5458186268806458},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5294439792633057},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5218269228935242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4775848388671875},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43372848629951477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4018063247203827},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35082244873046875},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34231171011924744},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33681806921958923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3333343267440796},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06507930159568787},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3077136.3084144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3077136.3084144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval","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":15,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1931639407","https://openalex.org/W1947481528","https://openalex.org/W1969732194","https://openalex.org/W2123024445","https://openalex.org/W2123301721","https://openalex.org/W2130942839","https://openalex.org/W2139501017","https://openalex.org/W2164290393","https://openalex.org/W2526346186","https://openalex.org/W2552161745","https://openalex.org/W2556388456","https://openalex.org/W2963175879"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W1544128162","https://openalex.org/W91730491","https://openalex.org/W3009270862"],"abstract_inverted_index":{"We":[0],"demonstrate":[1],"a":[2,12,27],"video":[3,62,70,115,155],"captioning":[4,38,71],"bot,":[5],"named":[6],"Seeing":[7,31,122],"Bot,":[8],"which":[9,79],"can":[10,80],"generate":[11],"natural":[13],"language":[14],"description":[15,128],"about":[16],"what":[17],"it":[18],"is":[19,94,144],"seeing":[20],"in":[21,40,149],"near":[22],"real":[23],"time.":[24],"Specifically,":[25],"given":[26],"live":[28,154],"streaming":[29],"video,":[30],"Bot":[32,123],"runs":[33],"two":[34,106],"pre-learned":[35],"and":[36,52,69,99,117,131,152],"complementary":[37],"modules":[39,72,108],"parallel":[41,107],"-":[42],"one":[43],"for":[44,48,55,59],"generating":[45,56],"image-level":[46],"caption":[47,58,88,103],"each":[49,60],"sampled":[50,61],"frame,":[51],"the":[53,67,82,101,105,111,118,126,133,150],"other":[54],"video-level":[57],"clip.":[63],"In":[64],"particular,":[65],"both":[66],"image":[68],"are":[73],"boosted":[74],"by":[75,109],"incorporating":[76],"semantic":[77,112],"attributes":[78],"enrich":[81],"generated":[83,119,127],"descriptions,":[84],"leading":[85],"to":[86,97,129,135],"human-level":[87],"generation.":[89],"A":[90],"visual-semantic":[91],"embedding":[92],"model":[93],"then":[95],"exploited":[96],"rank":[98],"select":[100],"final":[102],"from":[104],"considering":[110],"relevance":[113],"between":[114],"content":[116],"captions.":[120],"The":[121],"finally":[124],"converts":[125],"speech":[130,134],"sends":[132],"an":[136,140],"end":[137],"user":[138],"via":[139],"earphone.":[141],"Our":[142],"demonstration":[143],"conducted":[145],"on":[146],"any":[147],"videos":[148],"wild":[151],"supports":[153],"captioning.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2017-09-15T00:00:00"}