{"id":"https://openalex.org/W4415535471","doi":"https://doi.org/10.1145/3746027.3758198","title":"MSC: A Marine Wildlife Dataset for Video Understanding with Grounded Segmentation and Clip-Level Captions","display_name":"MSC: A Marine Wildlife Dataset for Video Understanding with Grounded Segmentation and Clip-Level Captions","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535471","doi":"https://doi.org/10.1145/3746027.3758198"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3758198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758198","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051861607","display_name":"Quang-Trung Truong","orcid":"https://orcid.org/0000-0002-6242-2191"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Quang-Trung Truong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-6242-2191","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112123550","display_name":"Y. K. Wong","orcid":"https://orcid.org/0009-0007-4444-5502"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuk-Kwan Wong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0007-4444-5502","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015074993","display_name":"Vo Hoang Kim Tuyen Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I2802508454","display_name":"University of Medicine and Pharmacy at Ho Chi Minh City","ror":"https://ror.org/025kb2624","country_code":"VN","type":"education","lineage":["https://openalex.org/I2802508454"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Vo Hoang Kim Tuyen Dang","raw_affiliation_strings":["Ho Chi Minh University of Science, Ho Chi Minh, Vietnam"],"raw_orcid":"https://orcid.org/0009-0001-4000-2217","affiliations":[{"raw_affiliation_string":"Ho Chi Minh University of Science, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I2802508454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052477039","display_name":"Rinaldi Gotama","orcid":"https://orcid.org/0000-0001-5313-8589"},"institutions":[{"id":"https://openalex.org/I4210086164","display_name":"The Ocean Foundation","ror":"https://ror.org/00pw7tr34","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210086164"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rinaldi Gotama","raw_affiliation_strings":["Indo Ocean Foundation, Bali, Indonesia"],"raw_orcid":"https://orcid.org/0000-0001-5313-8589","affiliations":[{"raw_affiliation_string":"Indo Ocean Foundation, Bali, Indonesia","institution_ids":["https://openalex.org/I4210086164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024634557","display_name":"Duc Thanh Nguyen","orcid":"https://orcid.org/0000-0002-2285-2066"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Duc Thanh Nguyen","raw_affiliation_strings":["Deakin University, Burwood, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2285-2066","affiliations":[{"raw_affiliation_string":"Deakin University, Burwood, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027689970","display_name":"Sai-Kit Yeung","orcid":"https://orcid.org/0000-0001-7974-0607"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sai-Kit Yeung","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7974-0607","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong SAR, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5051861607"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.0362,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82103478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12621","last_page":"12628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning 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/T11714","display_name":"Multimodal Machine Learning 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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987999796867371,"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":0.9932000041007996,"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/closed-captioning","display_name":"Closed captioning","score":0.8126000165939331},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6028000116348267},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6025999784469604},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8126000165939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445999979972839},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6025999784469604},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248000025749207},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3746027.3758198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758198","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.04549","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.04549","pdf_url":"https://arxiv.org/pdf/2508.04549","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167670","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167670","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758198","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758198","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2963354481","https://openalex.org/W4361756747","https://openalex.org/W4390872914","https://openalex.org/W4390874273","https://openalex.org/W4390874575","https://openalex.org/W4399039297","https://openalex.org/W4402660125","https://openalex.org/W4402727018","https://openalex.org/W4402727764","https://openalex.org/W4402727770","https://openalex.org/W4402770330","https://openalex.org/W4404612908","https://openalex.org/W4413145449","https://openalex.org/W4413146410","https://openalex.org/W4413884133"],"related_works":[],"abstract_inverted_index":{"Marine":[0],"videos":[1],"present":[2],"significant":[3],"challenges":[4],"for":[5],"video":[6,28,65,72,95,101,109],"understanding":[7,73,96],"due":[8],"to":[9,40,42,85,92,113],"the":[10,16,22,43,46,77,106,124],"dynamics":[11],"of":[12,24,45,79,108,126],"marine":[13,47,53,63,94,100],"objects":[14],"and":[15,21,49,82,89,97,99,131],"surrounding":[17],"environment,":[18],"camera":[19],"motion,":[20],"complexity":[23],"underwater":[25],"scenes.":[26],"Existing":[27],"captioning":[29,66,127],"datasets,":[30],"typically":[31],"focused":[32],"on":[33],"generic":[34],"or":[35],"human-centric":[36],"domains,":[37],"often":[38],"fail":[39],"generalize":[41],"complexities":[44],"environment":[48],"gain":[50],"insights":[51],"about":[52],"life.":[54],"To":[55],"address":[56],"these":[57],"limitations,":[58],"we":[59,104],"propose":[60],"a":[61,70],"two-stage":[62],"object-oriented":[64],"pipeline.":[67],"We":[68],"introduce":[69],"comprehensive":[71],"benchmark":[74],"that":[75],"leverages":[76],"triplets":[78],"video,":[80],"text,":[81],"segmentation":[83],"masks":[84],"facilitate":[86],"visual":[87],"grounding":[88],"captioning,":[90],"leading":[91],"improved":[93],"analysis,":[98],"generation.":[102],"Additionally,":[103],"highlight":[105],"effectiveness":[107],"splitting":[110],"in":[111,118],"order":[112],"detect":[114],"salient":[115],"object":[116],"transitions":[117],"scene":[119],"changes,":[120],"which":[121],"significantly":[122],"enrich":[123],"semantics":[125],"content.":[128],"Our":[129],"dataset":[130],"code":[132],"have":[133],"been":[134],"released":[135],"at":[136],"https://msc.hkustvgd.com.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-25T00:00:00"}
