{"id":"https://openalex.org/W7164833046","doi":"https://doi.org/10.1145/3805622.3810703","title":"SliceCSRef: Dual-Level Semantic Alignment for Robust Speech Referring Expression Comprehension","display_name":"SliceCSRef: Dual-Level Semantic Alignment for Robust Speech Referring Expression Comprehension","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164833046","doi":"https://doi.org/10.1145/3805622.3810703"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810703","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101151037","display_name":"Lihong Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihong Huang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen university, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-5656-5476","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen university, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086801574","display_name":"Sheng-hua Zhong","orcid":"https://orcid.org/0000-0002-7524-5999"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng-Hua Zhong","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7524-5999","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052243076","display_name":"Qiao Yan","orcid":"https://orcid.org/0000-0003-0412-0416"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Yan","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0412-0416","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052775723","display_name":"Zhijiao Xiao","orcid":"https://orcid.org/0000-0002-9664-821X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijiao Xiao","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-9664-821X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-4242-4840","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94856323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1308","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.414000004529953,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.414000004529953,"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":0.2644999921321869,"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/T12031","display_name":"Speech and dialogue systems","score":0.09430000185966492,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6272000074386597},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6154999732971191},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.45719999074935913},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4571000039577484},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41659998893737793},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3874000012874603},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.385699987411499},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6291000247001648},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6272000074386597},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6154999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310999751091003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.45719999074935913},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810703","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5449020862579346,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2109255472","https://openalex.org/W2470673105","https://openalex.org/W2489434015","https://openalex.org/W2696967604","https://openalex.org/W2936774411","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W3016970897","https://openalex.org/W3035097537","https://openalex.org/W3042011474","https://openalex.org/W3112077297","https://openalex.org/W3174965650","https://openalex.org/W3176445421","https://openalex.org/W3196899058","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4214490042","https://openalex.org/W4284898017","https://openalex.org/W4309181071","https://openalex.org/W4312956471","https://openalex.org/W4386071707","https://openalex.org/W4386590759","https://openalex.org/W4392903801","https://openalex.org/W4404037229","https://openalex.org/W4404356490","https://openalex.org/W4413943358","https://openalex.org/W4416011362","https://openalex.org/W4416036354"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"Referring":[1],"Expression":[2],"Comprehension":[3],"(SREC)":[4],"aims":[5],"to":[6,14,44],"localize":[7],"the":[8],"object":[9],"in":[10],"an":[11],"image":[12],"referred":[13],"by":[15],"a":[16,57],"spoken":[17],"natural":[18],"language":[19],"query.":[20],"However,":[21],"raw":[22],"speech":[23,80,118],"is":[24],"continuous":[25],"and":[26,28,112,119],"noisy,":[27],"prior":[29],"ASR-free":[30],"methods":[31],"that":[32,61,76,104],"align":[33],"full":[34],"utterances":[35],"with":[36,82],"transcripts":[37],"using":[38],"only":[39],"global":[40],"supervision":[41,95],"can":[42],"overfit":[43],"spurious":[45],"correlations,":[46],"limiting":[47],"fine-grained":[48,94],"grounding.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54],"propose":[55],"SliceCSRef,":[56],"robust":[58],"SREC":[59],"framework":[60],"improves":[62,114],"generalization":[63],"via":[64],"dual-level":[65],"semantic":[66],"alignment.":[67],"Beyond":[68],"utterance-level":[69],"speech\u2013text":[70],"alignment,":[71],"SliceCSRef":[72,105],"introduces":[73],"slice-wise":[74],"alignment":[75],"pairs":[77],"randomly":[78],"sampled":[79],"segments":[81],"weakly":[83],"matched":[84],"transcript":[85],"spans":[86],"based":[87],"on":[88,100],"their":[89],"relative":[90],"temporal":[91],"positions,":[92],"providing":[93],"without":[96],"additional":[97],"annotations.":[98],"Experiments":[99],"six":[101],"benchmarks":[102],"show":[103],"achieves":[106],"state-of-the-art":[107],"performance":[108],"under":[109,116],"standard":[110],"settings":[111],"consistently":[113],"robustness":[115],"truncated":[117],"playback-speed":[120],"variations.":[121]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}