{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:06:20Z","timestamp":1755219980640,"version":"3.43.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0118202"],"award-info":[{"award-number":["2022ZD0118202"]}]},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2119","U21B2037","U22B2051","62176222","62176223","62176226","62072386","62072387","62072389","62002305","62272401"],"award-info":[{"award-number":["624B2119","U21B2037","U22B2051","62176222","62176223","62176226","62072386","62072387","62072389","62002305","62272401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J01002","2022J06001"],"award-info":[{"award-number":["2021J01002","2022J06001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tpami.2025.3572240","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T13:56:30Z","timestamp":1749045390000},"page":"7704-7714","source":"Crossref","is-referenced-by-count":0,"title":["Spatial Re-Parameterization for N:M Sparsity"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-7030","authenticated-orcid":false,"given":"Yuxin","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1764-1894","authenticated-orcid":false,"given":"Mingbao","family":"Lin","sequence":"additional","affiliation":[{"name":"Skywork AI, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-3451","authenticated-orcid":false,"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref2","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"LeCun"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref4","first-page":"6382","article-title":"Global sparse momentum SGD for pruning very deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref8","first-page":"4119","article-title":"TETRIS: TilE-matching the tremendous irregular sparsity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ji"},{"key":"ref9","first-page":"17629","article-title":"Pruning filter in filter","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Meng"},{"article-title":"Learning N:M fine-grained structured sparse neural networks from scratch","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","key":"ref10"},{"article-title":"Channel permutations for N:M sparsity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pool","key":"ref11"},{"year":"2020","key":"ref12","article-title":"NVIDIA A100 tensor core GPU architecture"},{"article-title":"Learning best combination for efficient N:M sparsity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","key":"ref13"},{"article-title":"Sparse training via boosting pruning plasticity with neuroregeneration","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","article-title":"Learning sparse neural networks through $ l\\_{0}$l_0 regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Louizos","year":"2017"},{"article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","key":"ref18"},{"key":"ref19","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci"},{"article-title":"Sparse networks from scratch: Faster training without losing performance","year":"2019","author":"Dettmers","key":"ref20"},{"article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Zhu","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414654"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3197282"},{"key":"ref24","first-page":"20721","article-title":"DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref25","first-page":"41488","article-title":"Bi-directional masks for efficient N: M sparse training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref26","first-page":"21099","article-title":"Accelerated sparse neural training: A provable and efficient method to find N:M transposable masks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00200"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01166"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Molchanov","key":"ref32"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref33"},{"key":"ref34","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195774"},{"article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"article-title":"MMDetection: Open MMLab detection toolbox and benchmark","year":"2019","author":"Chen","key":"ref42"},{"key":"ref43","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref44","first-page":"2680","article-title":"Discovering neural wirings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wortsman"},{"key":"ref45","first-page":"5544","article-title":"Soft threshold weight reparameterization for learnable sparsity","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusupati"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11118328\/11023133.pdf?arnumber=11023133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:21Z","timestamp":1754588661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11023133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":45,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3572240","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}