{"id":"https://openalex.org/W2802219444","doi":"https://doi.org/10.1145/3191442.3191459","title":"Learn to Classify and Count","display_name":"Learn to Classify and Count","publication_year":2018,"publication_date":"2018-02-24","ids":{"openalex":"https://openalex.org/W2802219444","doi":"https://doi.org/10.1145/3191442.3191459","mag":"2802219444"},"language":"en","primary_location":{"id":"doi:10.1145/3191442.3191459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3191442.3191459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Image and Graphics Processing","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/A5053560715","display_name":"Zichen Song","orcid":"https://orcid.org/0000-0003-4105-7495"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zichen Song","raw_affiliation_strings":["University of Electronic Science and Technology of China, West Hi-Tech Zone, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, West Hi-Tech Zone, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101992406","display_name":"Qiang Qiu","orcid":"https://orcid.org/0000-0002-7709-6288"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Qiu","raw_affiliation_strings":["University of Electronic Science and Technology of China, West Hi-Tech Zone, Chengdu, SiChuan, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, West Hi-Tech Zone, Chengdu, SiChuan, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053560715"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.1045,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41995105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994000196456909,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/pascal","display_name":"Pascal (unit)","score":0.7430287599563599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382518649101257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7230122089385986},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6992182731628418},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6482090950012207},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6261306405067444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5988369584083557},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5947209000587463},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5285094380378723},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42267847061157227},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4175407290458679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32907918095588684},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.30834561586380005}],"concepts":[{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7430287599563599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382518649101257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7230122089385986},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6992182731628418},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6482090950012207},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6261306405067444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5988369584083557},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5947209000587463},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5285094380378723},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42267847061157227},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4175407290458679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32907918095588684},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30834561586380005},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3191442.3191459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3191442.3191459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Image and Graphics 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":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1567302070","https://openalex.org/W1686810756","https://openalex.org/W1954873805","https://openalex.org/W2037227137","https://openalex.org/W2062118960","https://openalex.org/W2062227835","https://openalex.org/W2117539524","https://openalex.org/W2161381512","https://openalex.org/W2183182206","https://openalex.org/W2243213007","https://openalex.org/W2410641892","https://openalex.org/W2519281173","https://openalex.org/W2520723410","https://openalex.org/W2563399268","https://openalex.org/W2605572715","https://openalex.org/W2618530766","https://openalex.org/W2741077351","https://openalex.org/W2750549109","https://openalex.org/W2912500072","https://openalex.org/W2949162858","https://openalex.org/W2962835968","https://openalex.org/W2962854645","https://openalex.org/W2963150697","https://openalex.org/W2963686699","https://openalex.org/W2963745697"],"related_works":["https://openalex.org/W3192357901","https://openalex.org/W3036286480","https://openalex.org/W2387360586","https://openalex.org/W4287027631","https://openalex.org/W4237171675","https://openalex.org/W2952736415","https://openalex.org/W3209723314","https://openalex.org/W1689909837","https://openalex.org/W2953362004","https://openalex.org/W4298525700"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,107],"focus":[4],"on":[5,32,52,155,172],"the":[6,33,53,100,137,142,178],"problem":[7],"of":[8,19,46,81,94,122,139,180],"object":[9,47,73,146,164],"classification":[10,74,95,103,162],"and":[11,27,75,96,104,144,163],"counting":[12,48,76,97,105,165],"in":[13,141,160],"natural":[14],"scenes.":[15],"The":[16,150],"existing":[17,82],"methods":[18,45],"instance":[20],"detection":[21],"can":[22,135],"be":[23],"utilized":[24],"to":[25,62,77,114],"classify":[26],"count.":[28],"These":[29],"works":[30],"depend":[31],"bounding":[34,126],"box":[35,127],"annotations,":[36],"which":[37,92,176],"requires":[38],"time-consuming":[39],"human":[40],"labeling":[41],"effort.":[42],"Meanwhile,":[43],"traditional":[44],"are":[49,59],"mostly":[50],"based":[51],"class-insensitive":[54],"density":[55],"map,":[56],"therefore":[57],"they":[58],"only":[60],"able":[61],"count":[63,145],"one":[64],"specific":[65],"category.":[66,149],"We":[67,84,167],"propose":[68,108],"a":[69,86,109],"unified":[70],"framework":[71],"for":[72],"overcome":[78],"these":[79],"drawbacks":[80],"works.":[83],"employ":[85],"two-stream":[87],"convolutional":[88],"neural":[89],"network":[90],"(CNN),":[91],"consists":[93],"branches.":[98],"Considering":[99],"correlation":[101,111],"between":[102],"tasks,":[106,175],"novel":[110],"loss":[112],"function":[113],"coordinate":[115],"representations":[116],"learned":[117],"by":[118],"both":[119,173],"two":[120,174],"branches":[121],"network.":[123],"Without":[124],"hand-labeled":[125],"annotations":[128],"as":[129],"supervision":[130],"information,":[131],"our":[132,181],"end-to-end":[133],"model":[134],"recognize":[136],"category":[138],"objects":[140],"image":[143],"numbers":[147],"per":[148],"proposed":[151,182],"method":[152],"is":[153],"evaluated":[154],"PASCAL":[156],"VOC":[157],"2007":[158],"dataset":[159],"multi-label":[161],"tasks.":[166],"have":[168],"achieved":[169],"improved":[170],"performance":[171],"shows":[177],"effectiveness":[179],"method.":[183]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}