{"id":"https://openalex.org/W2810569083","doi":"https://doi.org/10.1145/3240508.3240540","title":"Collaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions","display_name":"Collaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2810569083","doi":"https://doi.org/10.1145/3240508.3240540","mag":"2810569083"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th 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/A5101546016","display_name":"Lishi Zhang","orcid":"https://orcid.org/0000-0003-3902-3480"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lishi Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048683915","display_name":"Chenghan Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghan Fu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059344854","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-4346-8696"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.53,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71028471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"474","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9975000023841858,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.8551096320152283},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7415757179260254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.63544762134552},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.5484127402305603},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5468263030052185},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4726245403289795},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.448181688785553},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4329655170440674},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42017504572868347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37295204401016235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36997950077056885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3417530655860901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551096320152283},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7415757179260254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63544762134552},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.5484127402305603},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5468263030052185},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4726245403289795},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.448181688785553},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4329655170440674},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42017504572868347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37295204401016235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36997950077056885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3417530655860901},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240540","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1495267108","https://openalex.org/W1614298861","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W1913661415","https://openalex.org/W1991367009","https://openalex.org/W2016133424","https://openalex.org/W2041291076","https://openalex.org/W2046658845","https://openalex.org/W2059319345","https://openalex.org/W2097405693","https://openalex.org/W2101581379","https://openalex.org/W2106471914","https://openalex.org/W2108598243","https://openalex.org/W2110764733","https://openalex.org/W2113606819","https://openalex.org/W2117539524","https://openalex.org/W2119112357","https://openalex.org/W2124351162","https://openalex.org/W2150066425","https://openalex.org/W2322480645","https://openalex.org/W2337429362","https://openalex.org/W2340897893","https://openalex.org/W2341555367","https://openalex.org/W2460470859","https://openalex.org/W2560544142","https://openalex.org/W2560730294","https://openalex.org/W2566871317","https://openalex.org/W2605991684","https://openalex.org/W2609825896","https://openalex.org/W2612271937","https://openalex.org/W2725513608","https://openalex.org/W2744874208","https://openalex.org/W2765716052","https://openalex.org/W2766605158","https://openalex.org/W2766690867","https://openalex.org/W2771621349","https://openalex.org/W2774004838","https://openalex.org/W2949842255","https://openalex.org/W2953236957","https://openalex.org/W2962887844","https://openalex.org/W2963971305","https://openalex.org/W6736750069"],"related_works":["https://openalex.org/W4205140848","https://openalex.org/W2068663075","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W2931688134","https://openalex.org/W4393677513","https://openalex.org/W4390832911","https://openalex.org/W2377919138","https://openalex.org/W829257147","https://openalex.org/W4385302116"],"abstract_inverted_index":{"Per-pixel":[0],"masks":[1,31,170],"of":[2,32,44],"semantic":[3,33,57],"objects":[4,34,58],"are":[5,13,112,137,172],"very":[6],"useful":[7],"in":[8,35,125,150],"many":[9],"applications,":[10],"which,":[11],"however,":[12],"tedious":[14],"to":[15,27,53,106,115,146],"be":[16],"annotated.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,42,47],"collaborative":[24],"annotation":[25,127,166],"approach":[26,162],"efficiently":[28],"generate":[29,168],"per-pixel":[30],"tagged":[36,45],"images":[37,87,152],"with":[38,117,134,153,174],"multi-granularity":[39],"supervisions.":[40],"Given":[41],"set":[43],"images,":[46],"computer":[48],"agent":[49,64,145],"is":[50],"dynamically":[51],"generated":[52,176],"roughly":[54],"localize":[55],"the":[56,61,73,77,126,144,154,165,178],"described":[59],"by":[60,98,128,177],"tag.":[62],"The":[63],"first":[65],"extracts":[66],"massive":[67],"object":[68,169],"proposals":[69,102],"and":[70,79,84,131,167],"then":[71,113],"infer":[72],"tag-related":[74,101],"ones":[75],"under":[76],"weak":[78],"strong":[80],"supervisions":[81,97,141],"from":[82],"linguistically":[83],"visually":[85],"similar":[86],"as":[88,90,139],"well":[89],"previously":[91],"annotated":[92],"objects.":[93],"By":[94],"representing":[95],"such":[96],"over-complete":[99],"dictionaries,":[100],"can":[103,163],"pop-out":[104],"according":[105],"their":[107],"sparse":[108],"coding":[109],"length,":[110],"which":[111,136],"converted":[114],"superpixels":[116,133],"binary":[118],"labels.":[119],"After":[120],"that,":[121],"human":[122],"annotators":[123],"participate":[124],"flipping":[129],"labels":[130],"dividing":[132],"clicks,":[135],"used":[138],"click":[140],"that":[142,160,171],"teaches":[143],"recover":[147],"false":[148],"positives/negatives":[149],"processing":[151],"same":[155],"tags.":[156],"Experimental":[157],"results":[158],"show":[159],"our":[161],"facilitate":[164],"consistent":[173],"those":[175],"LabelMe":[179],"toolbox.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}