{"id":"https://openalex.org/W3048145096","doi":"https://doi.org/10.1145/3394171.3413691","title":"Single-Shot Two-Pronged Detector with Rectified IoU Loss","display_name":"Single-Shot Two-Pronged Detector with Rectified IoU Loss","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3048145096","doi":"https://doi.org/10.1145/3394171.3413691","mag":"3048145096"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.03511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Keyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyang Wang","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":1.6232,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.89249281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1311","last_page":"1319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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/T10036","display_name":"Advanced Neural Network 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9965000152587891,"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/object","display_name":"Object (grammar)","score":0.6966999769210815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.608299970626831},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5171999931335449},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39329999685287476},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.38119998574256897},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.3353999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379000186920166},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6330000162124634},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.608299970626831},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44359999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38119998574256897},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413691","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.03511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03511","pdf_url":"https://arxiv.org/pdf/2008.03511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.03511","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03511","pdf_url":"https://arxiv.org/pdf/2008.03511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2193145675","https://openalex.org/W2504335775","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2899607431","https://openalex.org/W2962721361","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963068995","https://openalex.org/W2963113370","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963604034","https://openalex.org/W2963786238","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2984016429","https://openalex.org/W2984816230","https://openalex.org/W2988452521","https://openalex.org/W2989604896","https://openalex.org/W3012573144"],"related_works":[],"abstract_inverted_index":{"In":[0,83],"the":[1,13,38,46,71,95,109,122,126,129,161,165,173,182,193,199,221,233,242,252,261],"CNN":[2],"based":[3,209],"object":[4,19,22,154],"detectors,":[5,23,172],"feature":[6],"pyramids":[7],"are":[8,34],"widely":[9],"exploited":[10],"to":[11,36,54,78,93,138,160,195,219],"alleviate":[12],"problem":[14],"of":[15,41,48,60,67,112,118,128,175,223,226,235,244,256,263],"scale":[16],"variation":[17],"across":[18],"instances.":[20],"These":[21],"which":[24,74,106,148,249],"strengthen":[25],"features":[26,114,120,144],"via":[27],"a":[28,64,88,134],"top-down":[29],"pathway":[30],"and":[31,103,115,145,167,266],"lateral":[32],"connections,":[33],"mainly":[35],"enrich":[37,108],"semantic":[39,110],"information":[40,69,111,117],"low-level":[42,113,146],"features,":[43,61,73,147],"but":[44],"ignore":[45],"enhancement":[47],"high-level":[49,72,119,143],"features.":[50],"This":[51,190],"can":[52,107,250],"lead":[53],"an":[55,206],"imbalance":[56,163],"between":[57,142,164],"different":[58,98,156],"levels":[59],"in":[62,70,100,170,203],"particular":[63],"serious":[65],"lack":[66],"detailed":[68,116],"makes":[75],"it":[76],"difficult":[77],"get":[79],"accurate":[80],"bounding":[81],"boxes.":[82],"this":[84],"paper,":[85],"we":[86,132],"introduce":[87],"novel":[89],"two-pronged":[90,130],"transductive":[91],"idea":[92],"explore":[94],"relationship":[96],"among":[97],"layers":[99],"both":[101],"backward":[102],"forward":[104],"directions,":[105],"at":[121,155],"same":[123],"time.":[124],"Under":[125],"guidance":[127],"idea,":[131],"propose":[133],"Two-Pronged":[135],"Network":[136],"(TPNet)":[137],"achieve":[139],"bidirectional":[140],"transfer":[141],"is":[149,178,217],"useful":[150],"for":[151],"accurately":[152],"detecting":[153],"scales.":[157],"Furthermore,":[158],"due":[159],"distribution":[162],"hard":[166,183,200],"easy":[168],"samples":[169],"single-stage":[171],"gradient":[174],"localization":[176,188,210,254],"loss":[177,231],"always":[179],"dominated":[180],"by":[181],"examples":[184,236,245],"that":[185],"have":[186],"poor":[187],"accuracy.":[189],"will":[191],"enable":[192],"model":[194],"be":[196],"biased":[197],"toward":[198],"samples.":[201,227],"So":[202],"our":[204,264],"TPNet,":[205],"adaptive":[207],"IoU":[208,214,230,239],"loss,":[211,216],"named":[212],"Rectified":[213,229],"(RIoU)":[215],"proposed":[218],"rectify":[220],"gradients":[222,234,243],"each":[224],"kind":[225],"The":[228],"increases":[232],"with":[237,246],"high":[238],"while":[240],"suppressing":[241],"low":[247],"IoU,":[248],"improve":[251],"overall":[253],"accuracy":[255],"model.":[257],"Extensive":[258],"experiments":[259],"demonstrate":[260],"superiority":[262],"TPNet":[265],"RIoU":[267],"loss.":[268]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-08-13T00:00:00"}