{"id":"https://openalex.org/W4401936978","doi":"https://doi.org/10.1145/3664524.3675362","title":"Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion","display_name":"Small Object Detection by DETR via Information Augmentation and Adaptive Feature Fusion","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4401936978","doi":"https://doi.org/10.1145/3664524.3675362"},"language":"en","primary_location":{"id":"doi:10.1145/3664524.3675362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664524.3675362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2024 ACM ICMR Workshop on Multimodal Video Retrieval","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/A5102160054","display_name":"Ji Huang","orcid":"https://orcid.org/0009-0005-0178-6046"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ji Huang","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070559820","display_name":"Tianrui Li","orcid":"https://orcid.org/0000-0001-7780-104X"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Li","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China"],"affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, China and Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102160054"],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":null,"apc_paid":null,"fwci":4.6945,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96029498,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.998199999332428,"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":0.998199999332428,"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":0.9855999946594238,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9797999858856201,"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":0.6945973038673401},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6286349296569824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5559984445571899},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5148712396621704},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5142697691917419},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5085006952285767},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.4982261657714844},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49162036180496216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4649793803691864},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4359857141971588},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3649612069129944},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3246856927871704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945973038673401},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6286349296569824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559984445571899},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5148712396621704},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5142697691917419},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5085006952285767},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.4982261657714844},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49162036180496216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4649793803691864},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4359857141971588},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3649612069129944},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3246856927871704},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664524.3675362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664524.3675362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2024 ACM ICMR Workshop on Multimodal Video Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2074351619","https://openalex.org/W2117539524","https://openalex.org/W2184962292","https://openalex.org/W2565639579","https://openalex.org/W2767014298","https://openalex.org/W2963037989","https://openalex.org/W2963125010","https://openalex.org/W2964241181","https://openalex.org/W2971148076","https://openalex.org/W3013211776","https://openalex.org/W3034971973","https://openalex.org/W3036098256","https://openalex.org/W3096609285","https://openalex.org/W3142696599","https://openalex.org/W3157042932","https://openalex.org/W3160439413","https://openalex.org/W3168997536","https://openalex.org/W3171660447","https://openalex.org/W4225595226","https://openalex.org/W4294805043","https://openalex.org/W4312312588","https://openalex.org/W4377241880","https://openalex.org/W4386076325"],"related_works":["https://openalex.org/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2353265673","https://openalex.org/W2031175860","https://openalex.org/W2152662039","https://openalex.org/W3088112989","https://openalex.org/W2392793229","https://openalex.org/W2355579697","https://openalex.org/W4360871138"],"abstract_inverted_index":{"Small":[0],"object":[1,21,99,162,187],"detection":[2,188],"algorithms":[3],"face":[4],"the":[5,15,44,53,82,85,95,102,118,147,175,185],"challenge":[6],"of":[7,47,97,108,143],"achieving":[8],"both":[9,88],"accuracy":[10,96],"and":[11,65,90,155],"real-time":[12,20],"performance.":[13],"Although":[14],"RT-DETR":[16,39,103],"model":[17,148,173],"excels":[18],"in":[19],"detection,":[22],"its":[23,157],"performance":[24],"degrades":[25],"when":[26],"detecting":[27,71],"small":[28,72,98],"objects.":[29,73],"To":[30,124],"address":[31],"this,":[32,126],"we":[33,80,127],"propose":[34],"two":[35],"key":[36],"improvements.":[37],"First,":[38],"currently":[40],"relies":[41],"solely":[42],"on":[43,184],"last":[45],"layer":[46],"backbone":[48],"features":[49,163],"for":[50,70],"input":[51,83],"to":[52,84,139,149,159],"transformer.":[54],"However,":[55],"this":[56],"approach":[57],"overlooks":[58],"important":[59],"detailed":[60,91],"information":[61,77],"such":[62],"as":[63],"edges":[64],"textures":[66],"that":[67,170],"are":[68],"essential":[69],"By":[74],"introducing":[75],"an":[76,129],"augmentation":[78],"method,":[79],"enrich":[81],"transformer":[86],"with":[87,111],"semantic":[89],"information,":[92],"thus":[93],"improving":[94],"detection.":[100],"Second,":[101],"decoder":[104],"treats":[105],"feature":[106,131,141,153],"maps":[107,154],"different":[109,144,165],"levels":[110],"equal":[112],"weight,":[113],"which":[114],"doesn\u2019t":[115],"effectively":[116],"handle":[117],"intricate":[119],"relationships":[120],"within":[121],"multi-scale":[122,152],"information.":[123],"overcome":[125],"introduce":[128],"adaptive":[130],"fusion":[132],"algorithm.":[133],"This":[134],"algorithm":[135],"assigns":[136],"learnable":[137],"parameters":[138],"each":[140],"map":[142],"levels,":[145],"enabling":[146],"adaptively":[150],"fuse":[151],"improve":[156],"ability":[158],"accurately":[160],"capture":[161],"across":[164],"scales.":[166],"Experimental":[167],"results":[168],"show":[169],"our":[171],"proposed":[172],"outperforms":[174],"latest":[176],"DETR":[177],"model,":[178],"establishing":[179],"a":[180],"new":[181],"state-of-the-art":[182],"benchmark":[183],"aquarium":[186],"dataset.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}