{"id":"https://openalex.org/W4415708250","doi":"https://doi.org/10.1109/icme59968.2025.11208907","title":"GASEM: Boosting Generalized and Actionable Parts Segmentation and Pose Estimation via Object Motion Perception","display_name":"GASEM: Boosting Generalized and Actionable Parts Segmentation and Pose Estimation via Object Motion Perception","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708250","doi":"https://doi.org/10.1109/icme59968.2025.11208907"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5000011106","display_name":"Liu Liu","orcid":"https://orcid.org/0000-0002-1755-8209"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liu Liu","raw_affiliation_strings":["Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108089034","display_name":"Ran Zhang","orcid":"https://orcid.org/0009-0008-2114-603X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Zhang","raw_affiliation_strings":["Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720681","display_name":"Wenbo Xu","orcid":"https://orcid.org/0000-0001-8704-1937"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Xu","raw_affiliation_strings":["Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011780655","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0003-1610-6056"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065138212","display_name":"Yiming Tang","orcid":"https://orcid.org/0000-0001-7665-421X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Tang","raw_affiliation_strings":["Hefei University of Technology"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448261","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0003-2853-5034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Institute of Dataspace"],"affiliations":[{"raw_affiliation_string":"Institute of Dataspace","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000011106"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39401275,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8654000163078308,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8654000163078308,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01979999989271164,"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":0.014499999582767487,"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/pose","display_name":"Pose","score":0.765999972820282},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7368999719619751},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6919000148773193},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.5956000089645386},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5195000171661377},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4945000112056732},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.45579999685287476},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.44440001249313354},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.42480000853538513}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8479999899864197},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.765999972820282},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7523000240325928},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7368999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189000248908997},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6919000148773193},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.5956000089645386},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.45579999685287476},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.44440001249313354},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3700999915599823},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.30469998717308044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C48575856","wikidata":"https://www.wikidata.org/wiki/Q852504","display_name":"Motion perception","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2961368225","https://openalex.org/W2962771259","https://openalex.org/W2963892972","https://openalex.org/W3034949383","https://openalex.org/W3035131925","https://openalex.org/W3035624836","https://openalex.org/W3120441392","https://openalex.org/W4206522166","https://openalex.org/W4214773923","https://openalex.org/W4226321491","https://openalex.org/W4312274934","https://openalex.org/W4312803310","https://openalex.org/W4312893019","https://openalex.org/W4383108731","https://openalex.org/W4386065846","https://openalex.org/W4386075519","https://openalex.org/W4386075656","https://openalex.org/W4401416532","https://openalex.org/W4403908274"],"related_works":[],"abstract_inverted_index":{"Category-level":[0],"object":[1,28,45],"understanding":[2],"has":[3],"progressed,":[4],"but":[5],"generalized":[6],"part":[7],"perception":[8],"remains":[9],"underexplored.":[10],"This":[11,98],"paper":[12],"introduces":[13],"GASEM,":[14],"a":[15,48,54,72],"framework":[16],"for":[17,58,68,78],"Generalizable":[18],"and":[19,24,40,61,85,109],"Actionable":[20],"Parts":[21],"GAPart":[22,59,80],"Segmentation":[23],"pose":[25,69],"Estimation":[26],"via":[27],"Motion":[29],"perception.":[30],"GASEM":[31,94],"utilizes":[32],"point-wise":[33],"motion":[34,46],"data":[35],"from":[36],"observed":[37],"point":[38],"clouds":[39],"cross-perspective":[41],"alignment":[42],"to":[43],"learn":[44],"using":[47],"scene":[49],"flow":[50],"model.":[51],"It":[52],"features":[53],"segmentation":[55,60],"proposal":[56],"architecture":[57],"an":[62],"Normalized":[63],"Object":[64],"Coordinate":[65],"Space(NPCS)":[66],"branch":[67],"estimation.":[70],"Additionally,":[71],"reinforcement":[73],"learning":[74],"agent":[75],"is":[76],"trained":[77],"robust":[79],"manipulation":[81],"in":[82,102],"both":[83],"simulations":[84],"real-world":[86],"environments.":[87],"Experiments":[88],"on":[89],"the":[90],"GAPartNet":[91],"dataset":[92],"show":[93],"outperforms":[95],"state-of-the-art":[96],"methods.":[97],"work":[99],"promises":[100],"advancements":[101],"embodied":[103],"intelligence":[104],"applications":[105],"like":[106],"robot-object":[107],"interaction":[108],"generalizable":[110],"manipulation.":[111],"Codes":[112],"are":[113],"available":[114],"at":[115],"https://github.com/Zirconium233/GASEM.":[116]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-30T00:00:00"}