{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:28:50Z","timestamp":1775744930253,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247585","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"4107-4114","source":"Crossref","is-referenced-by-count":1,"title":["HAMF: A Hybrid Attention-Mamba Framework for Joint Scene Context Understanding and Future Motion Representation Learning"],"prefix":"10.1109","author":[{"given":"Xiaodong","family":"Mei","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingbing","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3167103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3370039"},{"key":"ref6","article-title":"Scene transformer: A unified architecture for predicting multiple agent trajectories","author":"Ngiam","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160984"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"ref10","first-page":"6531","article-title":"Motion transformer with global intention localization and local movement refinement","volume":"35","author":"Shi","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3383"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02106"},{"key":"ref14","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"2019"},{"key":"ref15","first-page":"203","article-title":"Multimodal trajectory prediction conditioned on lane-graph traversals","volume-title":"Conference on Robot Learning","author":"Deo"},{"key":"ref16","article-title":"Tnt: Target-driven trajectory prediction","volume-title":"Conference on Robot Learning","author":"Zhao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"ref18","article-title":"Learning to predict vehicle trajectories with model-based planning","volume-title":"5th Annual Conference on Robot Learning","author":"Song"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref21","article-title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","author":"Ye","year":"2023","journal-title":"ICLR"},{"key":"ref22","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref24","article-title":"Multiple futures prediction","author":"Tang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981037"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298301"},{"key":"ref27","article-title":"Real-time motion prediction via heterogeneous polyline transformer with relative pose encoding","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01447"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611364"},{"key":"ref31","article-title":"Pluto: Pushing the limit of imitation learning-based planning for autonomous driving","author":"Cheng","year":"2024"},{"key":"ref32","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2025","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33131"},{"key":"ref35","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref36","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160468"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2484"},{"key":"ref39","article-title":"Qml for argoverse 2 motion forecasting challenge","author":"Su","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3311351"},{"key":"ref41","article-title":"Banet: Motion forecasting with boundary aware network","author":"Zhang","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3262150"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref44","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Forty-first International Conference on Machine Learning","author":"Zhu"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247585.pdf?arnumber=11247585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:38:44Z","timestamp":1766061524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247585\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247585","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}