{"id":"https://openalex.org/W7123339419","doi":"https://doi.org/10.1109/tcsvt.2026.3652634","title":"Hierarchical Semantics Interaction for Compressed Video Action Recognition","display_name":"Hierarchical Semantics Interaction for Compressed Video Action Recognition","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123339419","doi":"https://doi.org/10.1109/tcsvt.2026.3652634"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3652634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652634","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5061011497","display_name":"Jinxin Guo","orcid":"https://orcid.org/0000-0002-9509-0496"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxin Guo","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-9509-0496","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397772","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-2690-7180"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0003-2690-7180","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122892499","display_name":"Huaiwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiwen Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-3183-9218","affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104023861","display_name":"S-B Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengsheng Qian","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9488-2208","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039349437","display_name":"Chunqiang Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8343-9665","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.0433121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"5877","last_page":"5892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9853000044822693,"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":0.9853000044822693,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0017000000225380063,"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":0.0012000000569969416,"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/semantics","display_name":"Semantics (computer science)","score":0.6485999822616577},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4941999912261963},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.43700000643730164},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.39329999685287476},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.32690000534057617},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.29739999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317000269889832},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6481000185012817},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.43700000643730164},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41920000314712524},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3652634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3652634","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1383338027","display_name":null,"funder_award_id":"62206137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1406082945","display_name":null,"funder_award_id":"62206200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1498893086","display_name":null,"funder_award_id":"62036012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2054266076","display_name":null,"funder_award_id":"62576179","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2280626339","display_name":null,"funder_award_id":"62276257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4236698393","display_name":null,"funder_award_id":"NJYT23105","funder_id":"https://openalex.org/F4320327830","funder_display_name":"Research Program of Science and Technology at Universities of Inner Mongolia Autonomous Region"},{"id":"https://openalex.org/G5121922098","display_name":null,"funder_award_id":"62532004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5391925069","display_name":null,"funder_award_id":"62462049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5992941106","display_name":null,"funder_award_id":"62576246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327830","display_name":"Research Program of Science and Technology at Universities of Inner Mongolia Autonomous Region","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Directly":[0],"recognizing":[1],"action":[2,67,246],"based":[3],"on":[4,23,230],"compressed":[5,24,54,73,125,244],"video":[6,25,74,126,245],"shows":[7],"significant":[8],"advantages,":[9],"such":[10],"as":[11],"low":[12],"storage":[13],"demands,":[14],"efficient":[15,145],"decoding,":[16],"and":[17,33,36,43,61,89,94,130,158,164,168,194,198,210,233],"fast":[18],"inference":[19],"speeds.":[20],"Existing":[21],"methods":[22],"achieve":[26],"promising":[27],"performance":[28,101],"by":[29,177],"separately":[30],"modeling":[31,80,123],"spatial":[32,160,193],"motion":[34,95],"cues":[35],"directly":[37],"fusing":[38],"recognition":[39],"results":[40],"of":[41,53,66,72,81,124,156,162,239],"I-frames":[42,60,88,209],"P-frames.":[44],"However,":[45],"these":[46,109],"approaches":[47],"overlook":[48],"the":[49,64,78,153,159,188,205,237],"following":[50],"inherent":[51],"attributes":[52],"videos:":[55],"1)":[56],"Temporal":[57],"misalignment":[58],"between":[59,87,192,208],"P-frames":[62,157],"impairs":[63],"accuracy":[65],"recognition.":[68,247],"2)":[69],"Spatiotemporal":[70],"sparsity":[71],"frames":[75],"severely":[76],"hinders":[77],"semantic":[79,122,174,206,241],"complex":[82],"actions.":[83],"3)":[84],"Semantic":[85],"discrepancy":[86],"P-frames,":[90,211],"which":[91],"capture":[92],"appearance":[93],"information":[96,155,161],"respectively,":[97],"leads":[98],"to":[99,138,186],"suboptimal":[100],"when":[102],"they":[103],"are":[104],"fused":[105],"directly.":[106],"To":[107,172,203],"address":[108],"challenges,":[110],"we":[111,142,179,212],"propose":[112,143,180,213],"a":[113,133,181,214],"Hierarchical":[114],"Semantics":[115],"Interaction":[116],"Network":[117],"(HSINet)":[118],"that":[119,150,219],"ensures":[120],"refined":[121],"through":[127],"alignment,":[128],"interaction,":[129],"calibration":[131,217],"within":[132],"hierarchical":[134,240],"fusion":[135],"framework.":[136],"Specifically,":[137],"resolve":[139],"temporal":[140,147,195],"misalignment,":[141],"an":[144],"cross-modal":[146,182],"alignment":[148,170],"module":[149,185,218],"fully":[151],"combines":[152],"spatiotemporal":[154,201],"I-frames,":[163],"includes":[165],"both":[166],"pre-alignment":[167],"fine":[169],"stages.":[171],"mitigate":[173],"degradation":[175],"caused":[176],"sparsity,":[178],"semantics":[183,190],"interaction":[184,191,242],"provide":[187],"multi-scale":[189],"representation":[196],"learning":[197],"enhance":[199],"representations\u2019":[200],"awareness.":[202],"calibrate":[204],"imbalance":[207,216],"modal":[215],"optimizing":[220],"directional":[221],"differences":[222],"via":[223],"cosine":[224],"similarity":[225],"in":[226],"hyperspherical":[227],"space.":[228],"Experiments":[229],"HMDB-51,":[231],"UCF-101,":[232],"Kinetics-400":[234],"benchmarks,":[235],"demonstrate":[236],"effectiveness":[238],"for":[243]},"counts_by_year":[],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2026-01-14T00:00:00"}