{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:06Z","timestamp":1777865466838,"version":"3.51.4"},"reference-count":43,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088102,U24A20325,12326608"],"award-info":[{"award-number":["62088102,U24A20325,12326608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01748","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction"],"prefix":"10.1109","author":[{"given":"Mang","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanping","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhe","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenli","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Ningbo University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"ref4","first-page":"794","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","volume-title":"International conference on machine learning","author":"Chen","year":"2018"},{"key":"ref5","article-title":"Multi-task learning with deep neural networks: A survey","volume":"abs\/2009.09796","author":"Crawshaw","year":"2020","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Daniel","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref9","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"ref10","article-title":"Efficiently modeling long sequences with structured state spaces","volume":"abs\/2111.00396","author":"Gu","year":"2021","journal-title":"CoRR"},{"key":"ref11","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref15","article-title":"Multi-task learning with 3d-aware regularization","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_18"},{"key":"ref17","article-title":"Vmamba: Visual state space model","volume":"abs\/2401.10166","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref19","article-title":"Swiss army knife: Synergizing biases in knowledge from vision foundation models for multi-task learning","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"ref21","article-title":"Long range language modeling via gated state spaces","author":"Mehta","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref23","article-title":"Multitask learning as a bargaining game","author":"Navon","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref26","article-title":"Ema-net: Efficient multitask affinity learning for dense scene predictions","author":"Sinodinos","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Simplified state space layers for sequence modeling","volume":"abs\/2208.04933","author":"Smith","year":"2022","journal-title":"CoRR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00818"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3292995"},{"key":"ref33","article-title":"Plainmamba: Improving non-hierarchical mamba in visual recognition","volume":"abs\/2403.17695","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref34","article-title":"Adaptive stochastic gradient algorithm for blackbox multi-objective learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ye","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_30"},{"key":"ref36","article-title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ye","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3397031"},{"key":"ref38","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Rethinking of feature interaction for multi-task learning on dense prediction","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3425540"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00457"},{"key":"ref43","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"ICML"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444868.pdf?arnumber=11444868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:37:20Z","timestamp":1777531040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01748","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}