{"id":"https://openalex.org/W2889799754","doi":"https://doi.org/10.1109/icip.2018.8451692","title":"Joint Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation","display_name":"Joint Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation","publication_year":2018,"publication_date":"2018-09-07","ids":{"openalex":"https://openalex.org/W2889799754","doi":"https://doi.org/10.1109/icip.2018.8451692","mag":"2889799754"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2018.8451692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","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/A5028027585","display_name":"Xuhuan Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuhuan Duan","raw_affiliation_strings":["Xi\u2019 an Jiaotong University","Xi' an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019 an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi' an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350774","display_name":"Le Wang","orcid":"https://orcid.org/0000-0001-6636-6396"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Wang","raw_affiliation_strings":["Xi\u2019 an Jiaotong University","Xi' an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019 an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi' an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090829176","display_name":"Changbo Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbo Zhai","raw_affiliation_strings":["Xi\u2019 an Jiaotong University","Xi' an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019 an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi' an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi\u2019 an Jiaotong University","Xi' an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019 an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi' an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756983","display_name":"Qilin Zhang","orcid":"https://orcid.org/0000-0002-7917-9749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qilin Zhang","raw_affiliation_strings":["HERE Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HERE Technologies","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113948735","display_name":"Zhenxing Niu","orcid":"https://orcid.org/0000-0003-1660-5138"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenxing Niu","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081114810","display_name":"Gang Hua","orcid":"https://orcid.org/0000-0001-9522-6157"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gang Hua","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5028027585"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.9542,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81138136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"918","last_page":"922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9944000244140625,"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/segmentation","display_name":"Segmentation","score":0.8027143478393555},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.7253004312515259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7122218012809753},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6614948511123657},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6326302289962769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6287433505058289},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5900633335113525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5300238728523254},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4552636444568634},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4400380253791809},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.056282490491867065}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8027143478393555},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.7253004312515259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7122218012809753},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6614948511123657},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6326302289962769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6287433505058289},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5900633335113525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5300238728523254},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4552636444568634},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4400380253791809},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.056282490491867065},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2018.8451692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W88469699","https://openalex.org/W1522734439","https://openalex.org/W1772076007","https://openalex.org/W1797109199","https://openalex.org/W1947481528","https://openalex.org/W1989348325","https://openalex.org/W2044113068","https://openalex.org/W2046561909","https://openalex.org/W2113708607","https://openalex.org/W2118246710","https://openalex.org/W2131720600","https://openalex.org/W2143516773","https://openalex.org/W2156303437","https://openalex.org/W2463175074","https://openalex.org/W2463824207","https://openalex.org/W2471143248","https://openalex.org/W2472970127","https://openalex.org/W2508191294","https://openalex.org/W2593722617","https://openalex.org/W2607566495","https://openalex.org/W2611596598","https://openalex.org/W2736596806","https://openalex.org/W2739077193","https://openalex.org/W2767198899","https://openalex.org/W2964214371","https://openalex.org/W2964253156","https://openalex.org/W3021229333","https://openalex.org/W3104979525","https://openalex.org/W6603540024","https://openalex.org/W6679724742","https://openalex.org/W6682864246"],"related_works":["https://openalex.org/W3166204570","https://openalex.org/W3121246613","https://openalex.org/W2132137594","https://openalex.org/W2093537624","https://openalex.org/W350499458","https://openalex.org/W2062170304","https://openalex.org/W4231562521","https://openalex.org/W4240240174","https://openalex.org/W2379610230","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Inspired":[0],"by":[1,75],"the":[2,37,45,55,93,96],"recent":[3],"spatio-temporal":[4,18],"action":[5,19,42,81,85],"localization":[6,82],"efforts":[7],"with":[8],"tubelets":[9],"(sequences":[10],"of":[11,24,26,40,47,63,95],"bounding":[12,64],"boxes),":[13],"we":[14],"present":[15],"a":[16],"new":[17],"detector":[20,33,57],"Segment-tube,":[21],"which":[22],"consists":[23],"sequences":[25],"per-frame":[27,59],"segmentation":[28,60],"masks.":[29],"The":[30],"proposed":[31,97],"Segment-tube":[32,56],"can":[34],"temporally":[35],"pinpoint":[36],"starting/ending":[38],"frame":[39],"each":[41],"class":[43],"in":[44,51],"presence":[46],"preceding/subsequent":[48],"interference":[49],"actions":[50],"untrimmed":[52],"videos.":[53],"Simultaneously,":[54],"produces":[58],"masks":[61],"instead":[62],"boxes,":[65],"offering":[66],"superior":[67],"spatial":[68,84],"accuracy":[69],"to":[70],"tubelets.":[71],"This":[72],"is":[73],"achieved":[74],"alternating":[76],"iterative":[77],"optimization":[78],"between":[79],"temporal":[80],"and":[83],"segmentation.":[86],"Experimental":[87],"results":[88],"on":[89],"multiple":[90],"datasets":[91],"validate":[92],"efficacy":[94],"detector.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}