{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T07:34:57Z","timestamp":1766216097453,"version":"3.48.0"},"reference-count":39,"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","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\/iros60139.2025.11246298","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7826-7833","source":"Crossref","is-referenced-by-count":0,"title":["Task-Oriented Token Pruning for Efficient Object Detection and Segmentation"],"prefix":"10.1109","author":[{"given":"Hao","family":"Liang","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of AI Safety, Institute of Computing Technology,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meina","family":"Kan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of AI Safety, Institute of Computing Technology,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of AI Safety, Institute of Computing Technology,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of AI Safety, Institute of Computing Technology,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref4","first-page":"13 937","article-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"34","author":"Rao","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00264"},{"article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bolya","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Frankle","key":"ref11"},{"article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume-title":"International Conference on Learning Representations (ICLR)","author":"Han","key":"ref12"},{"article-title":"Snip: single-shot network pruning based on connection sensitivity","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lee","key":"ref13"},{"key":"ref14","first-page":"20 378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Sanh","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.43"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"article-title":"Fitnets: Hints for thin deep nets","volume-title":"International Conference on Learning Representations (ICLR)","author":"Romero","key":"ref18"},{"article-title":"Knowledge distillation via softmax regression representation learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"article-title":"Evit: Expediting vision transformers via token reorganizations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01521"},{"article-title":"Paumer: Patch pausing transformer for semantic segmentation","volume-title":"British Machine Vision Conference (BMVC)","author":"Courdier","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00184"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01493"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3327511"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"article-title":"Vision transformer adapter for dense predictions","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen","key":"ref37"},{"key":"ref38","first-page":"10 347","article-title":"Training data-efficient image transformers distillation through attention","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","volume":"139","author":"Touvron"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","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\/11246298.pdf?arnumber=11246298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T07:30:45Z","timestamp":1766215845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246298","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}