{"id":"https://openalex.org/W7124920295","doi":"https://doi.org/10.1109/cbmi66578.2025.11339307","title":"TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos*","display_name":"TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos*","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124920295","doi":"https://doi.org/10.1109/cbmi66578.2025.11339307"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5093436454","display_name":"Ioannis Kontostathis","orcid":"https://orcid.org/0009-0007-5311-8167"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Ioannis Kontostathis","raw_affiliation_strings":["ITI, CERTH,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"ITI, CERTH,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123415276","display_name":"Evlampios Apostolidis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Evlampios Apostolidis","raw_affiliation_strings":["ITI, CERTH,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"ITI, CERTH,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"last","author":{"id":null,"display_name":"Vasileios Mezaris","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasileios Mezaris","raw_affiliation_strings":["ITI, CERTH,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"ITI, CERTH,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093436454"],"corresponding_institution_ids":["https://openalex.org/I4210093649"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69065212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9922999739646912,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9922999739646912,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.000699999975040555,"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":0.0006000000284984708,"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/viewport","display_name":"Viewport","score":0.5756999850273132},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5210999846458435},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5209000110626221},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5098999738693237},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48350000381469727},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37380000948905945},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.32249999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555999755859375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7229999899864197},{"id":"https://openalex.org/C2778090530","wikidata":"https://www.wikidata.org/wiki/Q2523931","display_name":"Viewport","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5503000020980835},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5209000110626221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C202227193","wikidata":"https://www.wikidata.org/wiki/Q6345568","display_name":"Kadir\u2013Brady saliency detector","level":4,"score":0.2874999940395355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.2685000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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":42,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2565955132","https://openalex.org/W2593745480","https://openalex.org/W2798665861","https://openalex.org/W2799064164","https://openalex.org/W2884414611","https://openalex.org/W2895640967","https://openalex.org/W2957912435","https://openalex.org/W2963503775","https://openalex.org/W2963691181","https://openalex.org/W2964312929","https://openalex.org/W2986056979","https://openalex.org/W2994176602","https://openalex.org/W3000351820","https://openalex.org/W3020127778","https://openalex.org/W3034304805","https://openalex.org/W3034515714","https://openalex.org/W3082657571","https://openalex.org/W3088260685","https://openalex.org/W3133631111","https://openalex.org/W3205786327","https://openalex.org/W3210096385","https://openalex.org/W4282947363","https://openalex.org/W4312724358","https://openalex.org/W4319301164","https://openalex.org/W4321021980","https://openalex.org/W4379113548","https://openalex.org/W4385976096","https://openalex.org/W4386597095","https://openalex.org/W4390873163","https://openalex.org/W4391287710","https://openalex.org/W4392911121","https://openalex.org/W4399154304","https://openalex.org/W4402715853","https://openalex.org/W4402742408","https://openalex.org/W4404853649","https://openalex.org/W4405869276","https://openalex.org/W4406266286","https://openalex.org/W4411274274","https://openalex.org/W4412605363","https://openalex.org/W4415536390"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,17,44],"deal":[4],"with":[5],"the":[6,19,38,58,70,101,110,114],"task":[7],"of":[8,26,31,69,116],"text-driven":[9,131],"saliency":[10,41,54,132],"detection":[11,133],"in":[12,34,134],"360\u00b0":[13],"videos.":[14],"For":[15],"this,":[16],"introduce":[18],"TSV360":[20,111],"dataset":[21],"which":[22],"includes":[23],"16,000":[24],"triplets":[25],"ERP":[27],"frames,":[28,36],"textual":[29],"descriptions":[30],"salient":[32],"objects/events":[33],"these":[35],"and":[37,46,56,85,91,106,124],"associated":[39],"ground-truth":[40],"maps.":[42],"Following,":[43],"extend":[45],"adapt":[47],"a":[48,65,78,87,92,120],"SOTA":[49,79,121],"visual-based":[50,122],"approach":[51,123],"for":[52,82],"360\u00b0video":[53],"detection,":[55],"develop":[57],"TSalV360":[59,117],"method":[60,76],"that":[61],"takes":[62],"into":[63],"account":[64],"user-provided":[66],"text":[67],"description":[68],"desired":[71],"objects":[72],"and/or":[73],"events.":[74],"This":[75],"leverages":[77],"vision-language":[80],"model":[81],"data":[83,103],"representation":[84],"integrates":[86],"similarity":[88],"estimation":[89],"module":[90],"viewport":[93],"spatio-temporal":[94],"cross-attention":[95],"mechanism,":[96],"to":[97,119,128],"discover":[98],"dependencies":[99],"between":[100],"different":[102],"modalities.":[104],"Quantitative":[105],"qualitative":[107],"evalu-ations":[108],"using":[109],"dataset,":[112],"showed":[113],"competitiveness":[115],"compared":[118],"documented":[125],"its":[126],"competency":[127],"perform":[129],"customized":[130],"360\u00b0videos.":[135]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-21T00:00:00"}