{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:10:59Z","timestamp":1767337859693,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072232"],"award-info":[{"award-number":["62072232"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Project of Jiangsu Province","award":["BE2022138"],"award-info":[{"award-number":["BE2022138"]}]},{"name":"the Program B for Outstanding Ph.D. candidate of Nanjing University"},{"name":"the Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"name":"the Fundamental Research Funds for the Central Universities","award":["021714380026"],"award-info":[{"award-number":["021714380026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3595916.3626441","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T16:34:41Z","timestamp":1704126881000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["RGB-D Tracking via Hierarchical Modality Aggregation and Distribution Network"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7697-9630","authenticated-orcid":false,"given":"Boyue","family":"Xu","sequence":"first","affiliation":[{"name":"Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8592-0505","authenticated-orcid":false,"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8111-7339","authenticated-orcid":false,"given":"Ruichao","family":"Hou","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3731-7294","authenticated-orcid":false,"given":"Jia","family":"Bei","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3092-424X","authenticated-orcid":false,"given":"Tongwei","family":"Ren","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1391-1762","authenticated-orcid":false,"given":"Gangshan","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,1]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3066854"},{"key":"e_1_3_2_1_2_1","volume-title":"Fully-Convolutional Siamese Networks for Object Tracking. In European Conference on Computer Vision Workshops.","author":"Bertinetto L.","year":"2016","unstructured":"L. Bertinetto , J. Valmadre , Joo\u00a0 F. Henriques , A. Vedaldi , and Phs Torr . 2016 . Fully-Convolutional Siamese Networks for Object Tracking. In European Conference on Computer Vision Workshops. L. Bertinetto, J. Valmadre, Joo\u00a0F. Henriques, A. Vedaldi, and Phs Torr. 2016. Fully-Convolutional Siamese Networks for Object Tracking. In European Conference on Computer Vision Workshops."},{"volume-title":"Learning Discriminative Model Prediction for Tracking. In IEEE International Conference on Computer Vision.","author":"Bhat G.","key":"e_1_3_2_1_3_1","unstructured":"G. Bhat , M. Danelljan , L.\u00a0 V. Gool , and R. Timofte . 2019 . Learning Discriminative Model Prediction for Tracking. In IEEE International Conference on Computer Vision. G. Bhat, M. Danelljan, L.\u00a0V. Gool, and R. Timofte. 2019. Learning Discriminative Model Prediction for Tracking. In IEEE International Conference on Computer Vision."},{"volume-title":"High Performance Visual Tracking with Siamese Region Proposal Network. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Bo L.","key":"e_1_3_2_1_4_1","unstructured":"L. Bo , J. Yan , W. Wei , Z. Zheng , and X. Hu . 2018 . High Performance Visual Tracking with Siamese Region Proposal Network. In IEEE Conference on Computer Vision and Pattern Recognition. L. Bo, J. Yan, W. Wei, Z. Zheng, and X. Hu. 2018. High Performance Visual Tracking with Siamese Region Proposal Network. In IEEE Conference on Computer Vision and Pattern Recognition."},{"volume-title":"Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. In British Machine Vision Conference.","author":"Camplani M.","key":"e_1_3_2_1_5_1","unstructured":"M. Camplani , S. Hannuna , M. Mirmehdi , D. Damen , A. Paiement , L. Tao , and T. Burghardt . 2015 . Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. In British Machine Vision Conference. M. Camplani, S. Hannuna, M. Mirmehdi, D. Damen, A. Paiement, L. Tao, and T. Burghardt. 2015. Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. In British Machine Vision Conference."},{"key":"e_1_3_2_1_6_1","volume-title":"Transformer Tracking. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Chen Xin","year":"2021","unstructured":"Xin Chen , Bin Yan , Jiawen Zhu , Dong Wang , Xiaoyun Yang , and Huchuan Lu . 2021 . Transformer Tracking. In IEEE Conference on Computer Vision and Pattern Recognition. Xin Chen, Bin Yan, Jiawen Zhu, Dong Wang, Xiaoyun Yang, and Huchuan Lu. 2021. Transformer Tracking. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_7_1","volume-title":"Mixformer: End-to-end Tracking with Iterative Mixed Attention. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Cui Yutao","year":"2022","unstructured":"Yutao Cui , Cheng Jiang , Limin Wang , and Gangshan Wu . 2022 . Mixformer: End-to-end Tracking with Iterative Mixed Attention. In IEEE Conference on Computer Vision and Pattern Recognition. Yutao Cui, Cheng Jiang, Limin Wang, and Gangshan Wu. 2022. Mixformer: End-to-end Tracking with Iterative Mixed Attention. In IEEE Conference on Computer Vision and Pattern Recognition."},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition.","author":"Danelljan M.","key":"e_1_3_2_1_8_1","unstructured":"M. Danelljan , G. Bhat , F.\u00a0 S. Khan , and M. Felsberg . 2020. ATOM: Accurate Tracking by Overlap Maximization . In IEEE Conference on Computer Vision and Pattern Recognition. M. Danelljan, G. Bhat, F.\u00a0S. Khan, and M. Felsberg. 2020. ATOM: Accurate Tracking by Overlap Maximization. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_9_1","first-page":"5541","article-title":"Siamese Network for RGB-D Salient Object Detection and Beyond","volume":"44","author":"Fu Keren","year":"2021","unstructured":"Keren Fu , Deng-Ping Fan , Ge-Peng Ji , Qijun Zhao , Jianbing Shen , and Ce Zhu . 2021 . Siamese Network for RGB-D Salient Object Detection and Beyond . IEEE Transactions on Pattern Analysis and Machine Intelligence 44 , 9 (2021), 5541 \u2013 5559 . Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao, Jianbing Shen, and Ce Zhu. 2021. Siamese Network for RGB-D Salient Object Detection and Beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 5541\u20135559.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_10_1","volume-title":"Salient Object Detection for RGB-D Image Via Saliency Evolution. In IEEE International Conference on Multimedia and Expo.","author":"Guo Jingfan","year":"2016","unstructured":"Jingfan Guo , Tongwei Ren , and Jia Bei . 2016 . Salient Object Detection for RGB-D Image Via Saliency Evolution. In IEEE International Conference on Multimedia and Expo. Jingfan Guo, Tongwei Ren, and Jia Bei. 2016. Salient Object Detection for RGB-D Image Via Saliency Evolution. In IEEE International Conference on Multimedia and Expo."},{"key":"e_1_3_2_1_11_1","volume-title":"Radar and Lidar Target Signatures of Various Object Types and Evaluation of Extended Object Tracking Methods for Autonomous Driving Applications. In International Conference on Information Fusion.","author":"Haag Stefan","year":"2018","unstructured":"Stefan Haag , Bharanidhar Duraisamy , Wolfgang Koch , and J\u00fcrgen Dickmann . 2018 . Radar and Lidar Target Signatures of Various Object Types and Evaluation of Extended Object Tracking Methods for Autonomous Driving Applications. In International Conference on Information Fusion. Stefan Haag, Bharanidhar Duraisamy, Wolfgang Koch, and J\u00fcrgen Dickmann. 2018. Radar and Lidar Target Signatures of Various Object Types and Evaluation of Extended Object Tracking Methods for Autonomous Driving Applications. In International Conference on Information Fusion."},{"volume-title":"Hierarchical Multi-modal Fusion FCN with Attention Model for RGB-D Tracking. In IEEE International Conference on Cloud Engineering.","year":"2018","key":"e_1_3_2_1_12_1","unstructured":"Harika, Narumanchi, Dishant, Goyal, Nitesh, Emmadi, Praveen, and Gauravaram. 2018 . Hierarchical Multi-modal Fusion FCN with Attention Model for RGB-D Tracking. In IEEE International Conference on Cloud Engineering. Harika, Narumanchi, Dishant, Goyal, Nitesh, Emmadi, Praveen, and Gauravaram. 2018. Hierarchical Multi-modal Fusion FCN with Attention Model for RGB-D Tracking. In IEEE International Conference on Cloud Engineering."},{"key":"e_1_3_2_1_13_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"He Kaiming","year":"2016","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016 . Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"e_1_3_2_1_15_1","volume-title":"MIRNet: A Robust RGBT Tracking Jointly with Multi-Modal Interaction and Refinement. In IEEE International Conference on Multimedia and Expo.","author":"Hou Ruichao","year":"2022","unstructured":"Ruichao Hou , Tongwei Ren , and Gangshan Wu . 2022 . MIRNet: A Robust RGBT Tracking Jointly with Multi-Modal Interaction and Refinement. In IEEE International Conference on Multimedia and Expo. Ruichao Hou, Tongwei Ren, and Gangshan Wu. 2022. MIRNet: A Robust RGBT Tracking Jointly with Multi-Modal Interaction and Refinement. In IEEE International Conference on Multimedia and Expo."},{"key":"e_1_3_2_1_16_1","volume-title":"MTNet: Learning Modality-aware Representation with Transformer for RGBT Tracking. In IEEE International Conference on Multimedia and Expo.","author":"Hou Ruichao","year":"2023","unstructured":"Ruichao Hou , Boyue Xu , Tongwei Ren , and Gangshan Wu . 2023 . MTNet: Learning Modality-aware Representation with Transformer for RGBT Tracking. In IEEE International Conference on Multimedia and Expo. Ruichao Hou, Boyue Xu, Tongwei Ren, and Gangshan Wu. 2023. MTNet: Learning Modality-aware Representation with Transformer for RGBT Tracking. In IEEE International Conference on Multimedia and Expo."},{"volume-title":"Jointly Learning Heterogeneous Features for RGB-D Activity Recognition. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Hu F.","key":"e_1_3_2_1_17_1","unstructured":"J.\u00a0 F. Hu , W.\u00a0 S. Zheng , J. Lai , and J. Zhang . 2015 . Jointly Learning Heterogeneous Features for RGB-D Activity Recognition. In IEEE Conference on Computer Vision and Pattern Recognition. J.\u00a0F. Hu, W.\u00a0S. Zheng, J. Lai, and J. Zhang. 2015. Jointly Learning Heterogeneous Features for RGB-D Activity Recognition. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_18_1","volume-title":"Depth Masked Discriminative Correlation Filter. In International Conference on Pattern Recognition.","author":"Kart U\u011fur","year":"2018","unstructured":"U\u011fur Kart , Joni-Kristian K\u00e4m\u00e4r\u00e4inen , Ji\u0159\u00ed Matas , Lixin Fan , and Francesco Cricri . 2018 . Depth Masked Discriminative Correlation Filter. In International Conference on Pattern Recognition. U\u011fur Kart, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Ji\u0159\u00ed Matas, Lixin Fan, and Francesco Cricri. 2018. Depth Masked Discriminative Correlation Filter. In International Conference on Pattern Recognition."},{"key":"e_1_3_2_1_19_1","volume-title":"European Conference on Computer Vision Workshops.","author":"Kart Uur","year":"2019","unstructured":"Uur Kart , Joni\u00a0Kristian Kmrinen , and Ji\u00ed Matas . 2019 . How to Make an RGBD Tracker? . In European Conference on Computer Vision Workshops. Uur Kart, Joni\u00a0Kristian Kmrinen, and Ji\u00ed Matas. 2019. How to Make an RGBD Tracker?. In European Conference on Computer Vision Workshops."},{"key":"e_1_3_2_1_20_1","volume-title":"The Ninth Visual Object Tracking Vot2021 Challenge Results. In IEEE International Conference on Computer Vision.","author":"Kristan Matej","year":"2021","unstructured":"Matej Kristan , Ji\u0159\u00ed Matas , Ale\u0161 Leonardis , Michael Felsberg , Roman Pflugfelder , Joni-Kristian K\u00e4m\u00e4r\u00e4inen , Hyung\u00a0Jin Chang , Martin Danelljan , Luka Cehovin , Alan Luke\u017ei\u010d , 2021 . The Ninth Visual Object Tracking Vot2021 Challenge Results. In IEEE International Conference on Computer Vision. Matej Kristan, Ji\u0159\u00ed Matas, Ale\u0161 Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, Hyung\u00a0Jin Chang, Martin Danelljan, Luka Cehovin, Alan Luke\u017ei\u010d, 2021. The Ninth Visual Object Tracking Vot2021 Challenge Results. In IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops.","author":"Kristan Matej","year":"2019","unstructured":"Matej Kristan , Jiri Matas , Ales Leonardis , Michael Felsberg , Roman Pflugfelder , Joni-Kristian Kamarainen , Luka \u02c7 Cehovin\u00a0Zajc , Ondrej Drbohlav , Alan Lukezic , Amanda Berg , 2019 . The Seventh Visual Object Tracking VOT2019 Challenge Results . In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops. Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian Kamarainen, Luka \u02c7Cehovin\u00a0Zajc, Ondrej Drbohlav, Alan Lukezic, Amanda Berg, 2019. The Seventh Visual Object Tracking VOT2019 Challenge Results. In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops."},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition.","author":"Li B.","key":"e_1_3_2_1_22_1","unstructured":"B. Li , W. Wu , Q. Wang , F. Zhang , J. Xing , and J. Yan . 2020. SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks . In IEEE Conference on Computer Vision and Pattern Recognition. B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, and J. Yan. 2020. SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_23_1","volume-title":"Swintrack: A Simple and Strong Baseline for Transformer Tracking. In Advances in Neural Information Processing Systems.","author":"Lin Liting","year":"2022","unstructured":"Liting Lin , Heng Fan , Zhipeng Zhang , Yong Xu , and Haibin Ling . 2022 . Swintrack: A Simple and Strong Baseline for Transformer Tracking. In Advances in Neural Information Processing Systems. Liting Lin, Heng Fan, Zhipeng Zhang, Yong Xu, and Haibin Ling. 2022. Swintrack: A Simple and Strong Baseline for Transformer Tracking. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","first-page":"6305","DOI":"10.1109\/TCYB.2020.2980618","article-title":"Performance Evaluation Methodology for Long-term Single-object Tracking","volume":"51","author":"Luke\u017ai\u010d Alan","year":"2020","unstructured":"Alan Luke\u017ai\u010d , Luka\u00a0\u010cehovin Zajc , Tom\u00e1\u0161 Voj\u00ed\u0159 , Ji\u0159\u00ed Matas , and Matej Kristan . 2020 . Performance Evaluation Methodology for Long-term Single-object Tracking . IEEE Transactions on Cybernetics 51 , 12 (2020), 6305 \u2013 6318 . Alan Luke\u017ai\u010d, Luka\u00a0\u010cehovin Zajc, Tom\u00e1\u0161 Voj\u00ed\u0159, Ji\u0159\u00ed Matas, and Matej Kristan. 2020. Performance Evaluation Methodology for Long-term Single-object Tracking. IEEE Transactions on Cybernetics 51, 12 (2020), 6305\u20136318.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"e_1_3_2_1_25_1","unstructured":"Yongsen Mao Yiming Zhang Hanxiao Jiang Angel Chang and Manolis Savva. 2022. MultiScan: Scalable RGBD Scanning for 3D Environments with Articulated Objects. In Advances in Neural Information Processing Systems.  Yongsen Mao Yiming Zhang Hanxiao Jiang Angel Chang and Manolis Savva. 2022. MultiScan: Scalable RGBD Scanning for 3D Environments with Articulated Objects. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_26_1","volume-title":"IEEE International Conference on Computer Vision.","author":"Mayer Christoph","year":"2021","unstructured":"Christoph Mayer , Martin Danelljan , Danda\u00a0Pani Paudel , and Luc Van\u00a0Gool . 2021 . Learning Target Candidate Association to Keep Track of What Not to Track . In IEEE International Conference on Computer Vision. Christoph Mayer, Martin Danelljan, Danda\u00a0Pani Paudel, and Luc Van\u00a0Gool. 2021. Learning Target Candidate Association to Keep Track of What Not to Track. In IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_27_1","volume-title":"The Eighth Visual Object Tracking VOT2020 Challenge Results. In European Conference on Computer Vision Workshops.","author":"Memarmoghadam A.","year":"2021","unstructured":"A. Memarmoghadam . 2021 . The Eighth Visual Object Tracking VOT2020 Challenge Results. In European Conference on Computer Vision Workshops. A. Memarmoghadam. 2021. The Eighth Visual Object Tracking VOT2020 Challenge Results. In European Conference on Computer Vision Workshops."},{"key":"e_1_3_2_1_28_1","volume-title":"Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Nam Hyeonseob","year":"2016","unstructured":"Hyeonseob Nam and Bohyung Han . 2016 . Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. In IEEE Conference on Computer Vision and Pattern Recognition. Hyeonseob Nam and Bohyung Han. 2016. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/01691864.2020.1819874","article-title":"Online Multi-sensor Calibration Based on Moving Object Tracking","volume":"35","author":"Per\u0161i\u0107 J","year":"2021","unstructured":"J Per\u0161i\u0107 , L Petrovi\u0107 , I Markovi\u0107 , and I Petrovi\u0107 . 2021 . Online Multi-sensor Calibration Based on Moving Object Tracking . Advanced Robotics 35 , 3 - 4 (2021), 130\u2013140. J Per\u0161i\u0107, L Petrovi\u0107, I Markovi\u0107, and I Petrovi\u0107. 2021. Online Multi-sensor Calibration Based on Moving Object Tracking. Advanced Robotics 35, 3-4 (2021), 130\u2013140.","journal-title":"Advanced Robotics"},{"key":"e_1_3_2_1_30_1","volume-title":"DAL: A Deep Depth-aware Long-term Tracker. In International Conference on Pattern Recognition.","author":"Qian Yanlin","year":"2021","unstructured":"Yanlin Qian , Song Yan , Alan Luke\u017ei\u010d , Matej Kristan , Joni-Kristian K\u00e4m\u00e4r\u00e4inen , and Ji\u0159\u00ed Matas . 2021 . DAL: A Deep Depth-aware Long-term Tracker. In International Conference on Pattern Recognition. Yanlin Qian, Song Yan, Alan Luke\u017ei\u010d, Matej Kristan, Joni-Kristian K\u00e4m\u00e4r\u00e4inen, and Ji\u0159\u00ed Matas. 2021. DAL: A Deep Depth-aware Long-term Tracker. In International Conference on Pattern Recognition."},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"28","author":"Ren S.","year":"2017","unstructured":"S. Ren , K. He , R. Girshick , and J. Sun . 2017 . Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks . IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (2017), 1 \u2013 9 . S. Ren, K. He, R. Girshick, and J. Sun. 2017. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 28 (2017), 1\u20139.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"volume-title":"RGB-D Salient Object Detection: A Review","author":"Ren Tongwei","key":"e_1_3_2_1_32_1","unstructured":"Tongwei Ren and Ao Zhang . 2019. RGB-D Salient Object Detection: A Review . Springer International Publishing , Cham , 203\u2013220. Tongwei Ren and Ao Zhang. 2019. RGB-D Salient Object Detection: A Review. Springer International Publishing, Cham, 203\u2013220."},{"key":"e_1_3_2_1_33_1","unstructured":"A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A.\u00a0N. Gomez L. Kaiser and I. Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems.  A. Vaswani N. Shazeer N. Parmar J. Uszkoreit L. Jones A.\u00a0N. Gomez L. Kaiser and I. Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_34_1","volume-title":"Cbam: Convolutional Block Attention Module. In European Conference on Computer Vision.","author":"Woo Sanghyun","year":"2018","unstructured":"Sanghyun Woo , Jongchan Park , Joon-Young Lee , and In\u00a0So Kweon . 2018 . Cbam: Convolutional Block Attention Module. In European Conference on Computer Vision. Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In\u00a0So Kweon. 2018. Cbam: Convolutional Block Attention Module. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"24161","DOI":"10.1109\/JSEN.2022.3218601","article-title":"Link-RGBD: Cross-guided Feature Fusion Network for RGBD Semantic Segmentation","volume":"22","author":"Wu Peng","year":"2022","unstructured":"Peng Wu , Runze Guo , Xiaozhong Tong , Shaojing Su , Zhen Zuo , Bei Sun , and Junyu Wei . 2022 . Link-RGBD: Cross-guided Feature Fusion Network for RGBD Semantic Segmentation . IEEE Sensors Journal 22 , 24 (2022), 24161 \u2013 24175 . Peng Wu, Runze Guo, Xiaozhong Tong, Shaojing Su, Zhen Zuo, Bei Sun, and Junyu Wei. 2022. Link-RGBD: Cross-guided Feature Fusion Network for RGBD Semantic Segmentation. IEEE Sensors Journal 22, 24 (2022), 24161\u201324175.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_3_2_1_36_1","volume-title":"IEEE International Conference on Computer Vision.","author":"Yan S.","year":"2021","unstructured":"S. Yan , J. Yang , J. Kpyl , F. Zheng , A. Leonardis , and J.\u00a0 K. Kmrinen . 2021 . DepthTrack : Unveiling the Power of RGBD Tracking . In IEEE International Conference on Computer Vision. S. Yan, J. Yang, J. Kpyl, F. Zheng, A. Leonardis, and J.\u00a0K. Kmrinen. 2021. DepthTrack : Unveiling the Power of RGBD Tracking. In IEEE International Conference on Computer Vision."},{"key":"e_1_3_2_1_37_1","volume-title":"Prompting for Multi-modal Tracking. In the ACM International Conference on Multimedia.","author":"Yang Jinyu","year":"2022","unstructured":"Jinyu Yang , Zhe Li , Feng Zheng , Ales Leonardis , and Jingkuan Song . 2022 . Prompting for Multi-modal Tracking. In the ACM International Conference on Multimedia. Jinyu Yang, Zhe Li, Feng Zheng, Ales Leonardis, and Jingkuan Song. 2022. Prompting for Multi-modal Tracking. In the ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_38_1","volume-title":"Joint Feature Learning and Relation Modeling for Tracking: A One-stream Framework. In European Conference on Computer Vision.","author":"Ye Botao","year":"2022","unstructured":"Botao Ye , Hong Chang , Bingpeng Ma , Shiguang Shan , and Xilin Chen . 2022 . Joint Feature Learning and Relation Modeling for Tracking: A One-stream Framework. In European Conference on Computer Vision. Botao Ye, Hong Chang, Bingpeng Ma, Shiguang Shan, and Xilin Chen. 2022. Joint Feature Learning and Relation Modeling for Tracking: A One-stream Framework. In European Conference on Computer Vision."},{"key":"e_1_3_2_1_39_1","volume-title":"Visual Prompt Multi-Modal Tracking. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Zhu Jiawen","year":"2023","unstructured":"Jiawen Zhu , Simiao Lai , Xin Chen , Dong Wang , and Huchuan Lu . 2023 . Visual Prompt Multi-Modal Tracking. In IEEE Conference on Computer Vision and Pattern Recognition. Jiawen Zhu, Simiao Lai, Xin Chen, Dong Wang, and Huchuan Lu. 2023. Visual Prompt Multi-Modal Tracking. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_40_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Zhu Xue-Feng","year":"2023","unstructured":"Xue-Feng Zhu , Tianyang Xu , Zhangyong Tang , Zucheng Wu , Haodong Liu , Xiao Yang , Xiao-Jun Wu , and Josef Kittler . 2023 . RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking . In AAAI Conference on Artificial Intelligence. Xue-Feng Zhu, Tianyang Xu, Zhangyong Tang, Zucheng Wu, Haodong Liu, Xiao Yang, Xiao-Jun Wu, and Josef Kittler. 2023. RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_41_1","volume-title":"Visual Object Tracking on Multi-modal RGB-D Videos: A Review. arXiv preprint arXiv:2201.09207","author":"Zhu Xue-Feng","year":"2022","unstructured":"Xue-Feng Zhu , Tianyang Xu , and Xiao-Jun Wu. 2022. Visual Object Tracking on Multi-modal RGB-D Videos: A Review. arXiv preprint arXiv:2201.09207 ( 2022 ), 1\u20135. Xue-Feng Zhu, Tianyang Xu, and Xiao-Jun Wu. 2022. Visual Object Tracking on Multi-modal RGB-D Videos: A Review. arXiv preprint arXiv:2201.09207 (2022), 1\u20135."}],"event":{"name":"MMAsia '23: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Tainan Taiwan","acronym":"MMAsia '23"},"container-title":["ACM Multimedia Asia 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3595916.3626441","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3595916.3626441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:35:56Z","timestamp":1750178156000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3595916.3626441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":41,"alternative-id":["10.1145\/3595916.3626441","10.1145\/3595916"],"URL":"https:\/\/doi.org\/10.1145\/3595916.3626441","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2024-01-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}