{"id":"https://openalex.org/W4416748675","doi":"https://doi.org/10.1109/iros60139.2025.11247585","title":"HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning","display_name":"HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748675","doi":"https://doi.org/10.1109/iros60139.2025.11247585"},"language":"en","primary_location":{"id":"doi:10.1109/iros60139.2025.11247585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056459205","display_name":"Xiaodong Mei","orcid":"https://orcid.org/0000-0002-4687-6345"},"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":"Xiaodong Mei","raw_affiliation_strings":["Hong Kong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371320","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-3700-3128"},"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":"Sheng Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068760747","display_name":"Jie Cheng","orcid":"https://orcid.org/0000-0002-1507-0074"},"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":"Jie Cheng","raw_affiliation_strings":["Hong Kong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018045538","display_name":"Yingbing Chen","orcid":"https://orcid.org/0000-0003-2004-9816"},"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":"Yingbing Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101871461","display_name":"Dan Xu","orcid":"https://orcid.org/0000-0002-4903-2199"},"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":"Dan Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48025511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4107","last_page":"4114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8427000045776367,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8427000045776367,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.030700000002980232,"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":0.017000000923871994,"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/context","display_name":"Context (archaeology)","score":0.6723999977111816},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6708999872207642},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5663999915122986},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5658000111579895},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.507099986076355},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45969998836517334},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4174000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6972000002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6723999977111816},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6708999872207642},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5658000111579895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.507099986076355},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros60139.2025.11247585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-149316","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-149316","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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W3034722190","https://openalex.org/W3096609285","https://openalex.org/W3108486966","https://openalex.org/W3204875639","https://openalex.org/W3214950490","https://openalex.org/W4226239849","https://openalex.org/W4312327685","https://openalex.org/W4360993665","https://openalex.org/W4383109074","https://openalex.org/W4383109107","https://openalex.org/W4385221361","https://openalex.org/W4386076672","https://openalex.org/W4386083117","https://openalex.org/W4386432277","https://openalex.org/W4390873034","https://openalex.org/W4392207805","https://openalex.org/W4401416666","https://openalex.org/W4402667889","https://openalex.org/W4403842425","https://openalex.org/W4409365576","https://openalex.org/W4415795959","https://openalex.org/W4415797216"],"related_works":[],"abstract_inverted_index":{"Motion":[0],"forecasting":[1,59,185],"represents":[2],"a":[3,56,106,114],"critical":[4],"challenge":[5],"in":[6,145],"autonomous":[7],"driving":[8],"systems,":[9],"requiring":[10],"accurate":[11,165],"prediction":[12],"of":[13,108],"surrounding":[14],"agents\u2019":[15],"future":[16,22,63,79,102,133,159],"trajectories.":[17,169],"While":[18],"existing":[19],"approaches":[20],"predict":[21],"motion":[23,58,64,80,103,134,160,184],"states":[24,89],"with":[25,66,98,187],"the":[26,41,45,51,67,75,86,99,127,138,142,146,152,157,164,188],"extracted":[27],"scene":[28,46,68,76,128],"context":[29,69,129],"feature":[30,47],"from":[31,40],"historical":[32],"agent":[33,88],"trajectories":[34],"and":[35,78,90,122,131,154,166,190],"road":[36],"layouts,":[37],"they":[38],"suffer":[39],"information":[42,92,130],"degradation":[43],"during":[44],"encoding.":[48],"To":[49],"address":[50],"limitation,":[52],"we":[53,112,140],"propose":[54],"HAMF,":[55],"novel":[57],"framework":[60],"that":[61,177],"learns":[62],"representations":[65],"encoding":[70],"jointly,":[71],"to":[72,125,149,162],"coherently":[73],"combine":[74],"understanding":[77],"state":[81],"prediction.":[82],"We":[83],"first":[84],"embed":[85],"observed":[87],"map":[91],"into":[93],"1D":[94],"token":[95],"sequences,":[96],"together":[97],"target":[100],"multi-modal":[101],"features":[104,135],"as":[105],"set":[107],"learnable":[109],"tokens.":[110],"Then":[111],"design":[113],"unified":[115],"Attention-based":[116],"encoder,":[117,139],"which":[118],"synergistically":[119],"combines":[120],"self-attention":[121],"cross-attention":[123],"mechanisms":[124],"model":[126,181],"aggregate":[132],"jointly.":[136],"Complementing":[137],"implement":[141],"Mamba":[143],"module":[144],"decoding":[147],"stage":[148],"further":[150],"preserve":[151],"consistency":[153],"correlations":[155],"among":[156],"learned":[158],"representations,":[161],"generate":[163],"diverse":[167],"final":[168],"Extensive":[170],"experiments":[171],"on":[172],"Argoverse":[173],"2":[174],"benchmark":[175],"demonstrate":[176],"our":[178],"hybrid":[179],"Attention-Mamba":[180],"achieves":[182],"state-of-the-art":[183],"performance":[186],"simple":[189],"lightweight":[191],"architecture.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}