{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:33:11Z","timestamp":1783823591013,"version":"3.55.0"},"reference-count":129,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Bytedance","award":["CT20250811106734"],"award-info":[{"award-number":["CT20250811106734"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3624601","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:14:22Z","timestamp":1761930862000},"page":"7079-7092","source":"Crossref","is-referenced-by-count":9,"title":["Text-Controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2530-2725","authenticated-orcid":false,"given":"Xinghan","family":"Wang","sequence":"first","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8295-6018","authenticated-orcid":false,"given":"Zixi","family":"Kang","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7815-3750","authenticated-orcid":false,"given":"Yadong","family":"Mu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108708"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038362"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3334954"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3308750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3405712"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378886"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3226410"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3230249"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3129117"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051495"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3056895"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104182"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3207577"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2738562"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27973"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00871"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref34","first-page":"1","article-title":"MotionGPT: Human motion as a foreign language","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref35","article-title":"Iterative motion editing with natural language","author":"Goel","year":"2023","journal-title":"arXiv:2312.11538"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref37","first-page":"13981","article-title":"FineMoGen: Fine-grained spatio-temporal motion generation and editing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref38","first-page":"9312","article-title":"Motion question answering via modular motion programs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Endo"},{"key":"ref39","first-page":"11846","article-title":"Detecting moments and highlights in videos via natural language queries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lei"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00139"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548007"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25439"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref53","first-page":"14959","article-title":"HUMANISE: Language-conditioned human motion generation in 3D scenes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref54","article-title":"AvatarGPT: All-in-one framework for motion understanding, planning, generation and beyond","author":"Zhou","year":"2023","journal-title":"arXiv:2311.16468"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612289"},{"key":"ref57","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref58","article-title":"VL-Mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024","journal-title":"arXiv:2403.13600"},{"key":"ref59","article-title":"Cobra: Extending mamba to multi-modal large language model for efficient inference","author":"Zhao","year":"2024","journal-title":"arXiv:2403.14520"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref61","first-page":"25268","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lin"},{"key":"ref62","article-title":"HOI-diff: Text-driven synthesis of 3D human-object interactions using diffusion models","author":"Peng","year":"2023","journal-title":"arXiv:2312.06553"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref69","article-title":"Pretrained diffusion models for unified human motion synthesis","author":"Ma","year":"2022","journal-title":"arXiv:2212.02837"},{"key":"ref70","first-page":"15497","article-title":"Act as you wish: Fine-grained control of motion diffusion model with hierarchical semantic graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Jin"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01381"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00219"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611887"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27974"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27988"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28443"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref85","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv:2303.01418"},{"key":"ref86","article-title":"Nerm: Learning neural representations for high-framerate human motion synthesis","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Wei"},{"key":"ref87","article-title":"OmniControl: Control any joint at any time for human motion generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592069"},{"key":"ref92","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv:2111.00396"},{"key":"ref93","first-page":"1474","article-title":"HiPPO: Recurrent memory with optimal polynomial projections","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref94","article-title":"Simplified state space layers for sequence modeling","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Smith"},{"key":"ref95","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Dao"},{"key":"ref96","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv:2206.13947"},{"key":"ref97","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref98","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref99","article-title":"Liquid structural state-space models","author":"Hasani","year":"2022","journal-title":"arXiv:2209.12951"},{"key":"ref100","article-title":"How to train your HiPPO: State space models with generalized orthogonal basis projections","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Gu"},{"key":"ref101","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv:2405.21060"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"ref103","article-title":"Semi-Mamba-UNet: Pixel-level contrastive and pixel-level cross-supervised visual Mamba-based UNet for semi-supervised medical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2402.07245"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3767748"},{"key":"ref105","article-title":"U-Mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2401.04722"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref108","article-title":"PointMamba: A simple state space model for point cloud analysis","author":"Liang","year":"2024","journal-title":"arXiv:2402.10739"},{"key":"ref109","article-title":"Vivim: A video vision mamba for medical video segmentation","author":"Yang","year":"2024","journal-title":"arXiv:2401.14168"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref111","article-title":"Video Mamba suite: State space model as a versatile alternative for video understanding","author":"Chen","year":"2024","journal-title":"arXiv:2403.09626"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102779"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672044"},{"key":"ref114","article-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024","journal-title":"arXiv:2402.00789"},{"key":"ref115","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref116","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"ref118","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref119","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref125","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"ref128","first-page":"29192","article-title":"Embracing consistency: A one-stage approach for spatio-temporal video grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref129","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11223702.pdf?arnumber=11223702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:12:57Z","timestamp":1762539177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":129,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3624601","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}