{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:14Z","timestamp":1761894674447,"version":"build-2065373602"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209982","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Efficient RGBT Tracking via Heterogeneous Hierarchical Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Dengdi","family":"Sun","sequence":"first","affiliation":[{"name":"Anhui University,School of Artifcial Intelligence,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui University,School of Artifcial Intelligence,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"Anhui University,School of Artifcial Intelligence,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andong","family":"Lu","sequence":"additional","affiliation":[{"name":"Anhui University,School of Computer Science and Technology,Hefei,China,230601"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Deep adaptive fusion network for high performance rgbt tracking","volume-title":"ICCV workshops","author":"Zhu"},{"key":"ref2","first-page":"5019","article-title":"Rgbt tracking via noise-robust cross-modal ranking","volume":"33","author":"Tang","year":"2021","journal-title":"TNNLS"},{"key":"ref3","first-page":"1","article-title":"Multi-adapter rgbt tracking","author":"Zheng","year":"2019","journal-title":"ICCV Workshops"},{"issue":"4","key":"ref4","first-page":"725","article-title":"Weighted low-rank decomposition for robust grayscale-thermal foreground detection","volume":"27","author":"Zhang","year":"2016","journal-title":"TCSVT"},{"key":"ref5","first-page":"1","article-title":"Duality-gated mutual condition network for rgbt tracking","author":"Li","year":"2022","journal-title":"TNNLS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01310"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27852"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"ref10","article-title":"Breaking modality gap in RGBT tracking: Coupled knowledge distillation","author":"Li Y. Xiao A. Lu","year":"2024","journal-title":"ACM MM"},{"key":"ref11","first-page":"1","article-title":"Multi-modal fusion for end-to-end rgb-t tracking","volume-title":"ICCV Workshops","author":"Gonzalez-Garcia"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2020.2980735"},{"key":"ref13","first-page":"3335","article-title":"Jointly modeling motion and appearance cues for robust rgb-t tracking","volume":"30","author":"Bo","year":"2021","journal-title":"TIP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"ref15","first-page":"26551","article-title":"Sdstrack: Self-distillation symmetric adapter learning for multi-modal visual object tracking","author":"Qian","year":"2024","journal-title":"CVPR"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref16"},{"key":"ref17","first-page":"9060","article-title":"A2dele: Adaptive and attentive depth distiller for efficient rgb-d salient object detection","author":"Zhang","year":"2020","journal-title":"CVPR"},{"issue":"1","key":"ref18","first-page":"315","article-title":"Deep cross-modal representation learning and distillation for illumination-invariant pedestrian detection","volume":"32","author":"Zhao","year":"2021","journal-title":"TCSVT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s22166188"},{"key":"ref20","first-page":"803","article-title":"Low-cost multi-spectral scene analysis with modality distillation","author":"Lefevre","year":"2022","journal-title":"WACV"},{"key":"ref21","first-page":"4660","article-title":"Atom: Accurate tracking by overlap maximization","author":"Khan","year":"2019","journal-title":"CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref23","first-page":"1856","article-title":"Weighted sparse representation regularized graph learning for rgb-t object tracking","author":"Lu","year":"2017","journal-title":"ACM MM"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"ref25","first-page":"392","article-title":"Lasher: A large-scale high-diversity benchmark for rgbt tracking","volume":"31","author":"Jia","year":"2021","journal-title":"TIP"},{"key":"ref26","first-page":"85","article-title":"M5l: Multi-modal multi-margin metric learning for rgbt tracking","volume":"31","author":"Zhao","year":"2021","journal-title":"TIP"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1007\/s11263-021-01495-3","article-title":"Learning adaptive attribute-driven representation for real-time rgb-t tracking","volume":"129","author":"Lu","year":"2021","journal-title":"IJCV"},{"issue":"2","key":"ref28","first-page":"579","article-title":"Rgbt tracking by trident fusion network","volume":"32","author":"Tang","year":"2021","journal-title":"TCSVT"},{"key":"ref29","first-page":"1","article-title":"Mirnet: A robust rgbt tracking jointly with multi-modal interaction and refinement","author":"Ren","year":"2022","journal-title":"ICME"},{"key":"ref30","first-page":"12059","article-title":"Transformer rgbt tracking with spatio-temporal multimodal tokens","volume":"34","author":"Lu","year":"2024","journal-title":"TCSVT"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209982.pdf?arnumber=11209982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:10Z","timestamp":1761888790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209982","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}