{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T02:19:04Z","timestamp":1783045144742,"version":"3.54.6"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62261160576"],"award-info":[{"award-number":["62261160576"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573369"],"award-info":[{"award-number":["62573369"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["4252026"],"award-info":[{"award-number":["4252026"]}]},{"DOI":"10.13039\/501100025517","name":"Big Data Computing Center, Southeast University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100025517","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhishan Young Scholar Program of SEU, Fundamental Research Funds for the Central Universities of China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3657171","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:28Z","timestamp":1769634088000},"page":"1846-1857","source":"Crossref","is-referenced-by-count":2,"title":["Dissecting RGB-D Learning for Improved Multi-Modal Fusion"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3138-505X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7226-6946","authenticated-orcid":false,"given":"Haoran","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3535-3119","authenticated-orcid":false,"given":"Yunshu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8057-4949","authenticated-orcid":false,"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6253-3564","authenticated-orcid":false,"given":"Yongjian","family":"Deng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.06.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature25443"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2920602"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.549"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.533"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00788"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2990341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3154931"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00098"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01144"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.134"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref20","first-page":"23902","article-title":"LawDIS: Language-Window-based controllable dichotomous image segmentation","volume-title":"Proc. ICCV","author":"Yan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3291595"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00910"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2682981"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.161"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2891104"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00464"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.324"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01452-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33937"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.03.002"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29546"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3375342"},{"key":"ref34","article-title":"Visualizing higher-layer features of a deep network","volume":"1341","author":"Erhan","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.09.007"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref37","first-page":"484","article-title":"Understanding neural networks through deep visualization","volume-title":"Proc. ICML Workshop","author":"Yosinski"},{"key":"ref38","first-page":"3387","article-title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","volume-title":"Proc. NeurIPS","volume":"29","author":"Nguyen"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00007"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref41","first-page":"50323","article-title":"Where we have arrived in proving the emergence of sparse interaction primitives in DNNs","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref42","first-page":"23780","article-title":"Defining and extracting generalizable interaction primitives from DNNs","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29655"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3358410"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1419-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01942"},{"key":"ref47","first-page":"41283","article-title":"Towards the difficulty for a deep neural network to learn concepts of different complexities","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02030"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02581"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref52","first-page":"81046","article-title":"Interpreting clip\u2019s image representation via text-based decomposition","volume-title":"Proc. ICLR","author":"Gandelsman"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2576"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681712"},{"key":"ref55","article-title":"ResiDual transformer alignment with spectral decomposition","volume-title":"Proc. TMLR","author":"Basile"},{"key":"ref56","first-page":"84042","article-title":"On the role of attention heads in large language model safety","volume-title":"Proc. ICLR","author":"Zhou"},{"key":"ref57","first-page":"73329","article-title":"NeurFlow: Interpreting neural networks through neuron groups and functional interactions","volume-title":"Proc. ICLR","author":"Cao"},{"key":"ref58","first-page":"57880","article-title":"Efficient automated circuit discovery in transformers using contextual decomposition","volume-title":"Proc. ICLR","author":"Hsu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.471"},{"key":"ref60","first-page":"25244","article-title":"Discovering influential neuron path in vision transformers","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0768"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106239"},{"key":"ref63","article-title":"MultiViz: Towards visualizing and understanding multimodal models","volume-title":"Proc. ICLR","author":"Liang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref65","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume-title":"Proc. NeurIPS","author":"Huang"},{"key":"ref66","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. ICML","author":"Kornblith"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7244"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611200"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01837"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11367375.pdf?arnumber=11367375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:11:07Z","timestamp":1771362667000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11367375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3657171","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}