{"id":"https://openalex.org/W4415537851","doi":"https://doi.org/10.1145/3746027.3754878","title":"Towards Space and Semantics: Object-Purified Representation Learning for Multi-Label Image Classification","display_name":"Towards Space and Semantics: Object-Purified Representation Learning for Multi-Label Image Classification","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537851","doi":"https://doi.org/10.1145/3746027.3754878"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5102009463","display_name":"Haifeng Zhao","orcid":"https://orcid.org/0000-0002-5300-0683"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haifeng Zhao","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-5300-0683","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuo Xu","orcid":"https://orcid.org/0009-0008-6655-9401"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Xu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-6655-9401","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040404599","display_name":"Leilei Ma","orcid":"https://orcid.org/0000-0001-8681-0765"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leilei Ma","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-8681-0765","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yufei Zhang","orcid":"https://orcid.org/0009-0003-3699-7703"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0003-3699-7703","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025684575","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0003-3860-5139"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-3860-5139","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068470874","display_name":"Dengdi Sun","orcid":"https://orcid.org/0000-0002-0164-7944"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengdi Sun","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-0164-7944","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, Anhui, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102009463"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1559327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3270","last_page":"3279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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":0.9950000047683716,"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/overfitting","display_name":"Overfitting","score":0.7142000198364258},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6736999750137329},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6061999797821045},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5006999969482422},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4975999891757965},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.49070000648498535},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48969998955726624},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4162999987602234}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7142000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7064999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884999871253967},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6736999750137329},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.49070000648498535},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":20,"referenced_works":["https://openalex.org/W2007972815","https://openalex.org/W2037227137","https://openalex.org/W2114315281","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W3034924978","https://openalex.org/W3109067582","https://openalex.org/W3135745701","https://openalex.org/W3205749498","https://openalex.org/W4214673031","https://openalex.org/W4220813865","https://openalex.org/W4285186657","https://openalex.org/W4293202648","https://openalex.org/W4320005661","https://openalex.org/W4376132965","https://openalex.org/W4377000427","https://openalex.org/W4380032284","https://openalex.org/W4381735275","https://openalex.org/W4392239625","https://openalex.org/W4399310901"],"related_works":[],"abstract_inverted_index":{"Multi-label":[0],"image":[1],"classification":[2,150],"requires":[3],"simultaneously":[4],"recognizing":[5],"multiple":[6,155],"objects":[7,37],"with":[8,96,121,158],"complex":[9],"interdependencies.":[10],"While":[11],"existing":[12],"attention-based":[13],"methods":[14],"are":[15],"prominent,":[16],"their":[17,134],"performance":[18],"is":[19],"hampered":[20],"by":[21],"two":[22],"forms":[23],"of":[24,57],"representation":[25],"entanglement:":[26],"1)":[27],"Spatial":[28],"entanglement,":[29,44,74,106],"where":[30,45],"contextual":[31,92],"interference":[32,93],"from":[33],"backgrounds":[34],"and":[35],"co-occurring":[36],"confuses":[38],"specific":[39],"object":[40,101],"representations;":[41],"2)":[42],"Semantic":[43],"models":[46,129],"overfit":[47],"label":[48],"co-occurrence":[49,130],"priors,":[50],"thereby":[51],"impairing":[52],"a":[53],"genuine":[54],"semantic":[55,105],"understanding":[56],"the":[58,77,109,122,139],"image.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64,75,107,137],"propose":[65,76],"an":[66],"Object-Purified":[67],"Representation":[68,79,141],"Learning":[69],"framework.":[70],"Concretely,":[71],"for":[72,91],"spatial":[73],"Spatial-wise":[78],"Purification":[80,112],"Module":[81,113,143],"that":[82,114,162],"employs":[83],"Spatial-Purified":[84],"Attention":[85],"to":[86,99,144],"eliminate":[87],"object-irrelevant":[88],"feature":[89],"activations":[90],"reduction,":[94],"combined":[95],"Spatial-Aware":[97],"Supervision":[98],"enhance":[100,146],"perception":[102],"capability.":[103],"For":[104],"develop":[108],"Semantic-wise":[110],"Association":[111],"synergistically":[115],"integrates":[116],"our":[117,163],"proposed":[118,164],"average":[119],"message":[120],"original":[123],"co-occurrence-based":[124],"message.":[125],"This":[126],"design":[127,138],"effectively":[128],"relationships":[131],"while":[132],"preventing":[133],"overemphasis.":[135],"Furthermore,":[136],"Bidirectional":[140],"Refinement":[142],"efficiently":[145],"representations,":[147],"further":[148],"boosting":[149],"performance.":[151,168],"Extensive":[152],"experiments":[153],"on":[154],"benchmark":[156],"datasets":[157],"different":[159],"configurations":[160],"demonstrate":[161],"method":[165],"achieves":[166],"state-of-the-art":[167]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}