{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:24:33Z","timestamp":1773771873629,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475192","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T10:23:20Z","timestamp":1634552600000},"page":"2645-2653","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation"],"prefix":"10.1145","author":[{"given":"Xiaoqi","family":"Zhao","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwei","family":"Pang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxing","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology & Pengcheng Lab, Dalian&Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Ning An Xiao-Guang Zhao and Zeng-Guang Hou. 2016. Online RGB-D tracking via detection-learning-segmentation. In ICPR. 1231--1236.  Ning An Xiao-Guang Zhao and Zeng-Guang Hou. 2016. Online RGB-D tracking via detection-learning-segmentation. In ICPR. 1231--1236.","DOI":"10.1109\/ICPR.2016.7899805"},{"key":"e_1_3_2_2_2_1","volume-title":"Segflow: Joint learning for video object segmentation and optical flow. In ICCV. 686--695.","author":"Cheng Jingchun","year":"2017","unstructured":"Jingchun Cheng , Yi-Hsuan Tsai , Shengjin Wang , and Ming-Hsuan Yang . 2017 . Segflow: Joint learning for video object segmentation and optical flow. In ICCV. 686--695. Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang, and Ming-Hsuan Yang. 2017. Segflow: Joint learning for video object segmentation and optical flow. In ICCV. 686--695."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2632856.2632866"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"e_1_3_2_2_5_1","volume-title":"Imagenet: A large-scale hierarchical image database. In CVPR. 248--255.","author":"Deng Jia","year":"2009","unstructured":"Jia Deng , Wei Dong , Richard Socher , Li-Jia Li , Kai Li , and Li Fei-Fei . 2009 . Imagenet: A large-scale hierarchical image database. In CVPR. 248--255. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. 248--255."},{"key":"e_1_3_2_2_6_1","volume-title":"Exploiting geometric constraints on dense trajectories for motion saliency. arXiv preprint arXiv:1909.13258","author":"Faisal Muhammad","year":"2019","unstructured":"Muhammad Faisal , Ijaz Akhter , Mohsen Ali , and Richard Hartley . 2019. Exploiting geometric constraints on dense trajectories for motion saliency. arXiv preprint arXiv:1909.13258 ( 2019 ). Muhammad Faisal, Ijaz Akhter, Mohsen Ali, and Richard Hartley. 2019. Exploiting geometric constraints on dense trajectories for motion saliency. arXiv preprint arXiv:1909.13258 (2019)."},{"key":"e_1_3_2_2_7_1","volume-title":"Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks. arXiv preprint arXiv:1907.06781","author":"Fan Deng-Ping","year":"2019","unstructured":"Deng-Ping Fan , Zheng Lin , Jia-Xing Zhao , Yun Liu , Zhao Zhang , Qibin Hou , Menglong Zhu , and Ming-Ming Cheng . 2019. Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks. arXiv preprint arXiv:1907.06781 ( 2019 ). Deng-Ping Fan, Zheng Lin, Jia-Xing Zhao, Yun Liu, Zhao Zhang, Qibin Hou, Menglong Zhu, and Ming-Ming Cheng. 2019. Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks. arXiv preprint arXiv:1907.06781 (2019)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_2_9_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Qibin Hou Ming-Ming Cheng Xiaowei Hu Ali Borji Zhuowen Tu and Philip HS Torr. 2017. Deeply supervised salient object detection with short connections. In CVPR. 3203--3212.  Qibin Hou Ming-Ming Cheng Xiaowei Hu Ali Borji Zhuowen Tu and Philip HS Torr. 2017. Deeply supervised salient object detection with short connections. In CVPR. 3203--3212.","DOI":"10.1109\/CVPR.2017.563"},{"key":"e_1_3_2_2_11_1","volume-title":"Liteflownet: A lightweight convolutional neural network for optical flow estimation. In CVPR. 8981--8989.","author":"Hui Tak-Wai","year":"2018","unstructured":"Tak-Wai Hui , Xiaoou Tang , and Chen Change Loy . 2018 . Liteflownet: A lightweight convolutional neural network for optical flow estimation. In CVPR. 8981--8989. Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. 2018. Liteflownet: A lightweight convolutional neural network for optical flow estimation. In CVPR. 8981--8989."},{"key":"e_1_3_2_2_12_1","volume-title":"Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In CVPR. 2117--2126.","author":"Jain Suyog Dutt","year":"2017","unstructured":"Suyog Dutt Jain , Bo Xiong , and Kristen Grauman . 2017 . Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In CVPR. 2117--2126. Suyog Dutt Jain, Bo Xiong, and Kristen Grauman. 2017. Fusionseg: Learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In CVPR. 2117--2126."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475261"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Ran Ju Ling Ge Wenjing Geng Tongwei Ren and Gangshan Wu. 2014. Depth saliency based on anisotropic center-surround difference. In ICIP. 1115--1119.  Ran Ju Ling Ge Wenjing Geng Tongwei Ren and Gangshan Wu. 2014. Depth saliency based on anisotropic center-surround difference. In ICIP. 1115--1119.","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"e_1_3_2_2_15_1","unstructured":"Yeong Jun Koh and Chang-Su Kim. 2017. Primary object segmentation in videos based on region augmentation and reduction. In CVPR. 3442--3450.  Yeong Jun Koh and Chang-Su Kim. 2017. Primary object segmentation in videos based on region augmentation and reduction. In CVPR. 3442--3450."},{"key":"e_1_3_2_2_16_1","unstructured":"Siyang Li Bryan Seybold Alexey Vorobyov Xuejing Lei and C-C Jay Kuo. 2018. Unsupervised video object segmentation with motion-based bilateral networks. In ECCV. 207--223.  Siyang Li Bryan Seybold Alexey Vorobyov Xuejing Lei and C-C Jay Kuo. 2018. Unsupervised video object segmentation with motion-based bilateral networks. In ECCV. 207--223."},{"key":"e_1_3_2_2_17_1","unstructured":"Tsung-Yi Lin Piotr Doll\u00e1r Ross Girshick Kaiming He Bharath Hariharan and Serge Belongie. 2017. Feature pyramid networks for object detection. In CVPR. 2117--2125.  Tsung-Yi Lin Piotr Doll\u00e1r Ross Girshick Kaiming He Bharath Hariharan and Serge Belongie. 2017. Feature pyramid networks for object detection. In CVPR. 2117--2125."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6056-8"},{"key":"e_1_3_2_2_19_1","volume-title":"Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579","author":"Liu Wei","year":"2015","unstructured":"Wei Liu , Andrew Rabinovich , and Alexander C Berg . 2015 . Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579 (2015). Wei Liu, Andrew Rabinovich, and Alexander C Berg. 2015. Parsenet: Looking wider to see better. arXiv preprint arXiv:1506.04579 (2015)."},{"key":"e_1_3_2_2_20_1","unstructured":"Xiankai Lu Wenguan Wang Chao Ma Jianbing Shen Ling Shao and Fatih Porikli. 2019. See more know more: Unsupervised video object segmentation with co-attention siamese networks. In CVPR. 3623--3632.  Xiankai Lu Wenguan Wang Chao Ma Jianbing Shen Ling Shao and Fatih Porikli. 2019. See more know more: Unsupervised video object segmentation with co-attention siamese networks. In CVPR. 3623--3632."},{"key":"e_1_3_2_2_21_1","volume-title":"CDTB: A color and depth visual object tracking dataset and benchmark. In ICCV. 10013--10022.","author":"Lukezic Alan","year":"2019","unstructured":"Alan Lukezic , Ugur Kart , Jani Kapyla , Ahmed Durmush , Joni-Kristian Kamarainen , Jiri Matas , and Matej Kristan . 2019 . CDTB: A color and depth visual object tracking dataset and benchmark. In ICCV. 10013--10022. Alan Lukezic, Ugur Kart, Jani Kapyla, Ahmed Durmush, Joni-Kristian Kamarainen, Jiri Matas, and Matej Kristan. 2019. CDTB: A color and depth visual object tracking dataset and benchmark. In ICCV. 10013--10022."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354877"},{"key":"e_1_3_2_2_23_1","volume-title":"RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes. arXiv preprint arXiv:2004.06267","author":"Ocal Mertalp","year":"2020","unstructured":"Mertalp Ocal and Armin Mustafa . 2020. RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes. arXiv preprint arXiv:2004.06267 ( 2020 ). Mertalp Ocal and Armin Mustafa. 2020. RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes. arXiv preprint arXiv:2004.06267 (2020)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.242"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Youwei Pang Lihe Zhang Xiaoqi Zhao and Huchuan Lu. 2020 a. Hierarchical dynamic filtering network for RGB-D salient object detection. In ECCV. 235--252.  Youwei Pang Lihe Zhang Xiaoqi Zhao and Huchuan Lu. 2020 a. Hierarchical dynamic filtering network for RGB-D salient object detection. In ECCV. 235--252.","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Youwei Pang Xiaoqi Zhao Lihe Zhang and Huchuan Lu. 2020 b. Multi-Scale Interactive Network for Salient Object Detection. In CVPR. 9413--9422.  Youwei Pang Xiaoqi Zhao Lihe Zhang and Huchuan Lu. 2020 b. Multi-Scale Interactive Network for Salient Object Detection. In CVPR. 9413--9422.","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.223"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Houwen Peng Bing Li Weihua Xiong Weiming Hu and Rongrong Ji. 2014. RGBD salient object detection: A benchmark and algorithms. In ECCV. 92--109.  Houwen Peng Bing Li Weihua Xiong Weiming Hu and Rongrong Ji. 2014. RGBD salient object detection: A benchmark and algorithms. In ECCV. 92--109.","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"e_1_3_2_2_29_1","volume-title":"Markus Gross, and Alexander Sorkine-Hornung.","author":"Perazzi Federico","year":"2016","unstructured":"Federico Perazzi , Jordi Pont-Tuset , Brian McWilliams , Luc Van Gool , Markus Gross, and Alexander Sorkine-Hornung. 2016 . A benchmark dataset and evaluation methodology for video object segmentation. In CVPR. 724--732. Federico Perazzi, Jordi Pont-Tuset, Brian McWilliams, Luc Van Gool, Markus Gross, and Alexander Sorkine-Hornung. 2016. A benchmark dataset and evaluation methodology for video object segmentation. In CVPR. 724--732."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Yongri Piao Wei Ji Jingjing Li Miao Zhang and Huchuan Lu. 2019. Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection. In ICCV. 7254--7263.  Yongri Piao Wei Ji Jingjing Li Miao Zhang and Huchuan Lu. 2019. Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection. In ICCV. 7254--7263.","DOI":"10.1109\/ICCV.2019.00735"},{"key":"e_1_3_2_2_31_1","volume-title":"Superdepth: Self-supervised, super-resolved monocular depth estimation. In ICRA. 9250--9256.","author":"Pillai Sudeep","year":"2019","unstructured":"Sudeep Pillai , Rarecs Ambrucs , and Adrien Gaidon . 2019 . Superdepth: Self-supervised, super-resolved monocular depth estimation. In ICRA. 9250--9256. Sudeep Pillai, Rarecs Ambrucs, and Adrien Gaidon. 2019. Superdepth: Self-supervised, super-resolved monocular depth estimation. In ICRA. 9250--9256."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354924"},{"key":"e_1_3_2_2_33_1","unstructured":"Xuebin Qin Zichen Zhang Chenyang Huang Chao Gao Masood Dehghan and Martin Jagersand. 2019. BASNet: Boundary-Aware Salient Object Detection. In CVPR. 7479--7489.  Xuebin Qin Zichen Zhang Chenyang Huang Chao Gao Masood Dehghan and Martin Jagersand. 2019. BASNet: Boundary-Aware Salient Object Detection. In CVPR. 7479--7489."},{"key":"e_1_3_2_2_34_1","volume-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","author":"Ranftl Ren\u00e9","year":"2020","unstructured":"Ren\u00e9 Ranftl , Katrin Lasinger , David Hafner , Konrad Schindler , and Vladlen Koltun . 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer . IEEE TPAMI ( 2020 ). Ren\u00e9 Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. 2020. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE TPAMI (2020)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Anurag Ranjan and Michael J Black. 2017. Optical flow estimation using a spatial pyramid network. In CVPR. 4161--4170.  Anurag Ranjan and Michael J Black. 2017. Optical flow estimation using a spatial pyramid network. In CVPR. 4161--4170.","DOI":"10.1109\/CVPR.2017.291"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19040750"},{"key":"e_1_3_2_2_37_1","unstructured":"Mennatullah Siam Chen Jiang Steven Lu Laura Petrich Mahmoud Gamal Mohamed Elhoseiny and Martin Jagersand. 2019. Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting. In ICRA. 50--56.  Mennatullah Siam Chen Jiang Steven Lu Laura Petrich Mahmoud Gamal Mohamed Elhoseiny and Martin Jagersand. 2019. Video object segmentation using teacher-student adaptation in a human robot interaction (hri) setting. In ICRA. 50--56."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Hongmei Song Wenguan Wang Sanyuan Zhao Jianbing Shen and Kin-Man Lam. 2018. Pyramid dilated deeper convlstm for video salient object detection. In ECCV. 715--731.  Hongmei Song Wenguan Wang Sanyuan Zhao Jianbing Shen and Kin-Man Lam. 2018. Pyramid dilated deeper convlstm for video salient object detection. In ECCV. 715--731.","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"D Sun X Yang MY Liu and J Kautz. 2018. PWC-Net: CNNs for Optical Flow Using Pyramid Warping and Cost Volume. In CVPR. 8934--8943.  D Sun X Yang MY Liu and J Kautz. 2018. PWC-Net: CNNs for Optical Flow Using Pyramid Warping and Cost Volume. In CVPR. 8934--8943.","DOI":"10.1109\/CVPR.2018.00931"},{"key":"e_1_3_2_2_40_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In ECCV. 402--419.","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng . 2020 . Raft: Recurrent all-pairs field transforms for optical flow. In ECCV. 402--419. Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In ECCV. 402--419."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017a. Learning motion patterns in videos. In CVPR. 3386--3394.  Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017a. Learning motion patterns in videos. In CVPR. 3386--3394.","DOI":"10.1109\/CVPR.2017.64"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017b. Learning video object segmentation with visual memory. In ICCV. 4481--4490.  Pavel Tokmakov Karteek Alahari and Cordelia Schmid. 2017b. Learning video object segmentation with visual memory. In ICCV. 4481--4490.","DOI":"10.1109\/ICCV.2017.480"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Yi-Hsuan Tsai Guangyu Zhong and Ming-Hsuan Yang. 2016. Semantic co-segmentation in videos. In ECCV. 760--775.  Yi-Hsuan Tsai Guangyu Zhong and Ming-Hsuan Yang. 2016. Semantic co-segmentation in videos. In ECCV. 760--775.","DOI":"10.1007\/978-3-319-46493-0_46"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Tiantian Wang Lihe Zhang Shuo Wang Huchuan Lu Gang Yang Xiang Ruan and Ali Borji. 2018. Detect globally refine locally: A novel approach to saliency detection. In CVPR. 3127--3135.  Tiantian Wang Lihe Zhang Shuo Wang Huchuan Lu Gang Yang Xiang Ruan and Ali Borji. 2018. Detect globally refine locally: A novel approach to saliency detection. In CVPR. 3127--3135.","DOI":"10.1109\/CVPR.2018.00330"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Wenguan Wang Xiankai Lu Jianbing Shen David J Crandall and Ling Shao. 2019 a. Zero-shot video object segmentation via attentive graph neural networks. In ICCV. 9236--9245.  Wenguan Wang Xiankai Lu Jianbing Shen David J Crandall and Ling Shao. 2019 a. Zero-shot video object segmentation via attentive graph neural networks. In ICCV. 9236--9245.","DOI":"10.1109\/ICCV.2019.00933"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"Weiyue Wang and Ulrich Neumann. 2018. Depth-aware cnn for rgb-d segmentation. In ECCV. 135--150.  Weiyue Wang and Ulrich Neumann. 2018. Depth-aware cnn for rgb-d segmentation. In ECCV. 135--150.","DOI":"10.1007\/978-3-030-01252-6_9"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Wenguan Wang Jianbing Shen and Fatih Porikli. 2015. Saliency-aware geodesic video object segmentation. In CVPR. 3395--3402.  Wenguan Wang Jianbing Shen and Fatih Porikli. 2015. Saliency-aware geodesic video object segmentation. In CVPR. 3395--3402.","DOI":"10.1109\/CVPR.2015.7298961"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Wenguan Wang Hongmei Song Shuyang Zhao Jianbing Shen Sanyuan Zhao Steven CH Hoi and Haibin Ling. 2019 b. Learning unsupervised video object segmentation through visual attention. In CVPR. 3064--3074.  Wenguan Wang Hongmei Song Shuyang Zhao Jianbing Shen Sanyuan Zhao Steven CH Hoi and Haibin Ling. 2019 b. Learning unsupervised video object segmentation through visual attention. In CVPR. 3064--3074.","DOI":"10.1109\/CVPR.2019.00318"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454359"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Lu Zhang Jianming Zhang Zhe Lin Radomir Mech Huchuan Lu and You He. 2020. Unsupervised Video Object Segmentation with Joint Hotspot Tracking. In ECCV. 490--506.  Lu Zhang Jianming Zhang Zhe Lin Radomir Mech Huchuan Lu and You He. 2020. Unsupervised Video Object Segmentation with Joint Hotspot Tracking. In ECCV. 490--506.","DOI":"10.1007\/978-3-030-58568-6_29"},{"key":"e_1_3_2_2_52_1","volume-title":"Amulet: Aggregating multi-level convolutional features for salient object detection. In ICCV. 202--211.","author":"Zhang Pingping","year":"2017","unstructured":"Pingping Zhang , Dong Wang , Huchuan Lu , Hongyu Wang , and Xiang Ruan . 2017 . Amulet: Aggregating multi-level convolutional features for salient object detection. In ICCV. 202--211. Pingping Zhang, Dong Wang, Huchuan Lu, Hongyu Wang, and Xiang Ruan. 2017. Amulet: Aggregating multi-level convolutional features for salient object detection. In ICCV. 202--211."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Zhenyu Zhang Zhen Cui Chunyan Xu Yan Yan Nicu Sebe and Jian Yang. 2019. Pattern-affinitive propagation across depth surface normal and semantic segmentation. In CVPR. 4106--4115.  Zhenyu Zhang Zhen Cui Chunyan Xu Yan Yan Nicu Sebe and Jian Yang. 2019. Pattern-affinitive propagation across depth surface normal and semantic segmentation. In CVPR. 4106--4115.","DOI":"10.1109\/CVPR.2019.00423"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413855"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"crossref","unstructured":"Shengyu Zhao Yilun Sheng Yue Dong Eric I Chang Yan Xu etal 2020 b. MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask. In CVPR. 6278--6287.  Shengyu Zhao Yilun Sheng Yue Dong Eric I Chang Yan Xu et al. 2020 b. MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask. In CVPR. 6278--6287.","DOI":"10.1109\/CVPR42600.2020.00631"},{"key":"e_1_3_2_2_56_1","volume-title":"2020 a","author":"Zhao Xiaoqi","unstructured":"Xiaoqi Zhao , Youwei Pang , Lihe Zhang , Huchuan Lu , and Lei Zhang . 2020 a . Suppress and balance: A simple gated network for salient object detection. In ECCV. 35--51. Xiaoqi Zhao, Youwei Pang, Lihe Zhang, Huchuan Lu, and Lei Zhang. 2020 a. Suppress and balance: A simple gated network for salient object detection. In ECCV. 35--51."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Xiaoqi Zhao Lihe Zhang Youwei Pang Huchuan Lu and Lei Zhang. 2020 c. A single stream network for robust and real-time rgb-d salient object detection. In ECCV. 646--662.  Xiaoqi Zhao Lihe Zhang Youwei Pang Huchuan Lu and Lei Zhang. 2020 c. A single stream network for robust and real-time rgb-d salient object detection. In ECCV. 646--662.","DOI":"10.1007\/978-3-030-58542-6_39"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","unstructured":"Mingmin Zhen Shiwei Li Lei Zhou Jiaxiang Shang Haoan Feng Tian Fang and Long Quan. 2020. Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation. In ECCV. 445--462.  Mingmin Zhen Shiwei Li Lei Zhou Jiaxiang Shang Haoan Feng Tian Fang and Long Quan. 2020. Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation. In ECCV. 445--462.","DOI":"10.1007\/978-3-030-58583-9_27"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"crossref","unstructured":"Tianfei Zhou Shunzhou Wang Yi Zhou Yazhou Yao Jianwu Li and Ling Shao. 2020. Motion-Attentive Transition for Zero-Shot Video Object Segmentation. In AAAI. 3.  Tianfei Zhou Shunzhou Wang Yi Zhou Yazhou Yao Jianwu Li and Ling Shao. 2020. Motion-Attentive Transition for Zero-Shot Video Object Segmentation. In AAAI. 3.","DOI":"10.1609\/aaai.v34i07.7008"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475192","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:47Z","timestamp":1750193327000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":59,"alternative-id":["10.1145\/3474085.3475192","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475192","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}