{"id":"https://openalex.org/W4415539763","doi":"https://doi.org/10.1145/3746027.3754765","title":"Accelerating Long Video Understanding via Compressed Scene Graph-Enabled Chain-of-Thought","display_name":"Accelerating Long Video Understanding via Compressed Scene Graph-Enabled Chain-of-Thought","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539763","doi":"https://doi.org/10.1145/3746027.3754765"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754765","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754765","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004553847","display_name":"Tao Ling","orcid":"https://orcid.org/0000-0001-9301-8610"},"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":true,"raw_author_name":"Tao Ling","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030157399","display_name":"Siping Shi","orcid":"https://orcid.org/0000-0002-5555-417X"},"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":"Siping Shi","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100411794","display_name":"Dan Wang","orcid":"https://orcid.org/0000-0002-0921-2726"},"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":"Dan Wang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004553847"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30656189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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/T11714","display_name":"Multimodal Machine Learning 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/T10812","display_name":"Human Pose and Action Recognition","score":0.9969000220298767,"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/object","display_name":"Object (grammar)","score":0.3037000000476837},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.2906999886035919},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2703999876976013},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2639000117778778},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26159998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104999780654907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5403000116348267},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754765","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 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754765","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 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":10,"referenced_works":["https://openalex.org/W2963184176","https://openalex.org/W3175961224","https://openalex.org/W4312936847","https://openalex.org/W4387968052","https://openalex.org/W4387968589","https://openalex.org/W4393161084","https://openalex.org/W4402727443","https://openalex.org/W4402727624","https://openalex.org/W4403791417","https://openalex.org/W4403792398"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}