{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T06:48:12Z","timestamp":1784616492941,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Alexander von Humboldt Foundation"},{"name":"Conseil r\u00e9gional de Bourgogne-Franche-Comt\u00e9"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611970","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3455-3464","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["Object Segmentation by Mining Cross-Modal Semantics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7772-4152","authenticated-orcid":false,"given":"Zongwei","family":"Wu","sequence":"first","affiliation":[{"name":"Computer Vision Lab, CAIDAS & IFI, University of Wurzburg, Wurzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3953-6472","authenticated-orcid":false,"given":"Jingjing","family":"Wang","sequence":"additional","affiliation":[{"name":"Anhui University of Science and Technology, Huainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1396-0894","authenticated-orcid":false,"given":"Zhuyun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Burgundy, CNRS, ICB, Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5985-7470","authenticated-orcid":false,"given":"Zhaochong","family":"An","sequence":"additional","affiliation":[{"name":"CVL, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-9343","authenticated-orcid":false,"given":"Qiuping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Ningbo University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6916-1273","authenticated-orcid":false,"given":"C\u00e9dric","family":"Demonceaux","sequence":"additional","affiliation":[{"name":"University of Burgundy, CNRS, ICB, Dijon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8667-9656","authenticated-orcid":false,"given":"Guolei","family":"Sun","sequence":"additional","affiliation":[{"name":"CVL, ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1478-0402","authenticated-orcid":false,"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[{"name":"Computer Vision Lab, CAIDAS and IFI, University of Wurzburg, Wurzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Depth perception in augmented reality: The effects of display, shadow, and position","author":"Adams Haley","unstructured":"Haley Adams, Jeanine Stefanucci, Sarah Creem-Regehr, and Bobby Bodenheimer. 2022. Depth perception in augmented reality: The effects of display, shadow, and position. In IEEE VR. IEEE."},{"key":"e_1_3_2_1_2_1","volume-title":"Transfusion: Robust lidar-camera fusion for 3d object detection with transformers","author":"Bai Xuyang","year":"2022","unstructured":"Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu, and Chiew-Lan Tai. 2022. Transfusion: Robust lidar-camera fusion for 3d object detection with transformers. In IEEE\/CVF CVPR."},{"key":"e_1_3_2_1_3_1","volume-title":"Thermal infrared sensors: theory, optimisation and practice","author":"Budzier Helmut","unstructured":"Helmut Budzier and Gerald Gerlach. 2011. Thermal infrared sensors: theory, optimisation and practice. John Wiley & Sons."},{"key":"e_1_3_2_1_4_1","volume-title":"Modality-Induced Transfer-Fusion Network for RGB-D and RGB-T Salient Object Detection","author":"Chen Gang","year":"2022","unstructured":"Gang Chen, Feng Shao, Xiongli Chai, Hangwei Chen, Qiuping Jiang, Xiangchao Meng, and Yo-Sung Ho. 2022a. Modality-Induced Transfer-Fusion Network for RGB-D and RGB-T Salient Object Detection. IEEE TCSVT (2022)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202241"},{"key":"e_1_3_2_1_6_1","volume-title":"Reimagining the Stadium Spectator Experience using Augmented Reality and Visual Positioning System","author":"Cheng Kelvin","unstructured":"Kelvin Cheng, Kensuke Koda, and Soh Masuko. 2022a. Reimagining the Stadium Spectator Experience using Augmented Reality and Visual Positioning System. In IEEE ISMAR-Adjunct. IEEE."},{"key":"e_1_3_2_1_7_1","volume-title":"Depth-induced Gap-reducing Network for RGB-D Salient Object Detection: An Interaction, Guidance and Refinement Approach","author":"Cheng Xiaolong","year":"2022","unstructured":"Xiaolong Cheng, Xuan Zheng, Jialun Pei, He Tang, Zehua Lyu, and Chuanbo Chen. 2022b. Depth-induced Gap-reducing Network for RGB-D Salient Object Detection: An Interaction, Guidance and Refinement Approach. IEEE TMM (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection","author":"Cong Runmin","year":"2022","unstructured":"Runmin Cong, Qinwei Lin, Chen Zhang, Chongyi Li, Xiaochun Cao, Qingming Huang, and Yao Zhao. 2022a. CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection. IEEE TIP (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"Does thermal really always matter for RGB-T salient object detection? IEEE TMM","author":"Cong Runmin","year":"2022","unstructured":"Runmin Cong, Kepu Zhang, Chen Zhang, Feng Zheng, Yao Zhao, Qingming Huang, and Sam Kwong. 2022b. Does thermal really always matter for RGB-T salient object detection? IEEE TMM (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"Camouflaged object detection","author":"Fan Deng-Ping","unstructured":"Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen, and Ling Shao. 2020a. Camouflaged object detection. In IEEE CVPR."},{"key":"e_1_3_2_1_11_1","first-page":"2075","article-title":"Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks","volume":"32","author":"Fan Deng-Ping","year":"2021","unstructured":"Deng-Ping Fan, Zheng Lin, Zhao Zhang, Menglong Zhu, and Ming-Ming Cheng. 2021. Rethinking RGB-D salient object detection: Models, datasets, and large-scale benchmarks. IEEE TNNLS, Vol. 32, 5 (2021), 2075--2089.","journal-title":"IEEE TNNLS"},{"key":"e_1_3_2_1_12_1","unstructured":"Deng-Ping Fan Yingjie Zhai Ali Borji Jufeng Yang and Ling Shao. 2020b. BBS-Net: RGB-D salient object detection with a bifurcated backbone strategy network. In ECCV."},{"key":"e_1_3_2_1_13_1","volume-title":"JL-DCF: Joint learning and densely-cooperative fusion framework for RGB-D salient object detection","author":"Fu Keren","unstructured":"Keren Fu, Deng-Ping Fan, Ge-Peng Ji, and Qijun Zhao. 2020. JL-DCF: Joint learning and densely-cooperative fusion framework for RGB-D salient object detection. In IEEE CVPR."},{"key":"e_1_3_2_1_14_1","volume-title":"Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction","author":"He Chunming","unstructured":"Chunming He, Kai Li, Yachao Zhang, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. 2023. Camouflaged Object Detection with Feature Decomposition and Edge Reconstruction. In IEEE CVPR."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep residual learning for image recognition","author":"He Kaiming","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In IEEE CVPR."},{"key":"e_1_3_2_1_16_1","volume-title":"Ffb6d: A full flow bidirectional fusion network for 6d pose estimation","author":"He Yisheng","unstructured":"Yisheng He, Haibin Huang, Haoqiang Fan, Qifeng Chen, and Jian Sun. 2021. Ffb6d: A full flow bidirectional fusion network for 6d pose estimation. In IEEE CVPR."},{"key":"e_1_3_2_1_17_1","first-page":"1911","article-title":"Glass segmentation with RGB-thermal image pairs","volume":"32","author":"Huo Dong","year":"2023","unstructured":"Dong Huo, Jian Wang, Yiming Qian, and Yee-Hong Yang. 2023. Glass segmentation with RGB-thermal image pairs. IEEE TTP, Vol. 32 (2023), 1911--1926.","journal-title":"IEEE TTP"},{"key":"e_1_3_2_1_18_1","first-page":"1","article-title":"Real-time one-stream semantic-guided refinement network for RGB-Thermal salient object detection","volume":"71","author":"Huo Fushuo","year":"2022","unstructured":"Fushuo Huo, Xuegui Zhu, Qian Zhang, Ziming Liu, and Wenchao Yu. 2022. Real-time one-stream semantic-guided refinement network for RGB-Thermal salient object detection. IEEE TIM, Vol. 71 (2022), 1--12.","journal-title":"IEEE TIM"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Wei Ji Jingjing Li Shuang Yu Miao Zhang Yongri Piao Shunyu Yao Qi Bi Kai Ma Yefeng Zheng Huchuan Lu et al. 2021. Calibrated RGB-D Salient Object Detection. In IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"e_1_3_2_1_20_1","volume-title":"Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way","author":"Jia Qi","unstructured":"Qi Jia, Shuilian Yao, Yu Liu, Xin Fan, Risheng Liu, and Zhongxuan Luo. 2022. Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way. In IEEE CVPR."},{"key":"e_1_3_2_1_21_1","first-page":"3376","article-title":"CDNet: Complementary depth network for RGB-D salient object detection","volume":"30","author":"Jin Wen-Da","year":"2021","unstructured":"Wen-Da Jin, Jun Xu, Qi Han, Yi Zhang, and Ming-Ming Cheng. 2021. CDNet: Complementary depth network for RGB-D salient object detection. IEEE TIP, Vol. 30 (2021), 3376--3390.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_22_1","volume-title":"Depth saliency based on anisotropic center-surround difference","author":"Ju Ran","unstructured":"Ran Ju, Ling Ge, Wenjing Geng, Tongwei Ren, and Gangshan Wu. 2014. Depth saliency based on anisotropic center-surround difference. In IEEE ICIP."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.04.006"},{"key":"e_1_3_2_1_24_1","unstructured":"Hyemin Lee and Daijin Kim. 2018. Salient region-based online object tracking. In WACV."},{"key":"e_1_3_2_1_25_1","volume-title":"SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection. In ECCV.","author":"Lee Minhyeok","year":"2022","unstructured":"Minhyeok Lee, Chaewon Park, Suhwan Cho, and Sangyoun Lee. 2022. SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection. In ECCV."},{"key":"e_1_3_2_1_26_1","volume-title":"Uncertainty-aware joint salient object and camouflaged object detection","author":"Li Aixuan","unstructured":"Aixuan Li, Jing Zhang, Yunqiu Lv, Bowen Liu, Tong Zhang, and Yuchao Dai. 2021b. Uncertainty-aware joint salient object and camouflaged object detection. In IEEE CVPR."},{"key":"e_1_3_2_1_27_1","first-page":"3528","article-title":"Hierarchical Alternate Interaction Network for RGB-D Salient Object Detection","volume":"30","author":"Li Gongyang","year":"2021","unstructured":"Gongyang Li, Zhi Liu, Minyu Chen, Zhen Bai, Weisi Lin, and Haibin Ling. 2021a. Hierarchical Alternate Interaction Network for RGB-D Salient Object Detection. IEEE TIP, Vol. 30 (2021), 3528--3542.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_28_1","unstructured":"Gongyang Li Zhi Liu Linwei Ye Yang Wang and Haibin Ling. 2020. Cross-modal weighting network for RGB-D salient object detection. In ECCV."},{"key":"e_1_3_2_1_29_1","volume-title":"Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff. arXiv preprint arXiv:2301.06679","author":"Li Jia","year":"2023","unstructured":"Jia Li, Shengye Qiao, Zhirui Zhao, Chenxi Xie, Xiaowu Chen, and Changqun Xia. 2023. Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff. arXiv preprint arXiv:2301.06679 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Scribble-Supervised RGB-T Salient Object Detection. arXiv preprint arXiv:2303.09733","author":"Liu Zhengyi","year":"2023","unstructured":"Zhengyi Liu, Xiaoshen Huang, Guanghui Zhang, Xianyong Fang, Linbo Wang, and Bin Tang. 2023. Scribble-Supervised RGB-T Salient Object Detection. arXiv preprint arXiv:2303.09733 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"A convnet for the","author":"Liu Zhuang","year":"2020","unstructured":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. 2022. A convnet for the 2020s. In IEEE\/CVF CVPR."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3127149"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475601"},{"key":"e_1_3_2_1_34_1","volume-title":"Simultaneously localize, segment and rank the camouflaged objects","author":"Lv Yunqiu","unstructured":"Yunqiu Lv, Jing Zhang, Yuchao Dai, Aixuan Li, Bowen Liu, Nick Barnes, and Deng-Ping Fan. 2021. Simultaneously localize, segment and rank the camouflaged objects. In IEEE CVPR."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2556683"},{"key":"e_1_3_2_1_36_1","volume-title":"Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging","author":"Miangoleh S Mahdi H","unstructured":"S Mahdi H Miangoleh, Sebastian Dille, Long Mai, Sylvain Paris, and Yagiz Aksoy. 2021. Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging. In IEEE CVPR."},{"key":"e_1_3_2_1_37_1","volume-title":"Leveraging stereopsis for saliency analysis","author":"Niu Yuzhen","unstructured":"Yuzhen Niu, Yujie Geng, Xueqing Li, and Feng Liu. 2012. Leveraging stereopsis for saliency analysis. In IEEE CVPR."},{"key":"e_1_3_2_1_38_1","volume-title":"Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection","author":"Pang Youwei","unstructured":"Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, and Huchuan Lu. 2022. Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection. In IEEE CVPR."},{"key":"e_1_3_2_1_39_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.","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"e_1_3_2_1_40_1","volume-title":"Vision transformers for dense prediction","author":"Ranftl Ren\u00e9","unstructured":"Ren\u00e9 Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. 2021. Vision transformers for dense prediction. In IEEE ICCV."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_2_1_42_1","volume-title":"Mobilenetv2: Inverted residuals and linear bottlenecks","author":"Sandler Mark","unstructured":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In IEEE CVPR."},{"key":"e_1_3_2_1_43_1","volume-title":"Animal camouflage analysis: Chameleon database. Unpublished manuscript","author":"Skurowski Przemys\u0142aw","year":"2018","unstructured":"Przemys\u0142aw Skurowski, Hassan Abdulameer, J B\u0142aszczyk, Tomasz Depta, Adam Kornacki, and P Kozie\u0142. 2018. Animal camouflage analysis: Chameleon database. Unpublished manuscript, Vol. 2, 6 (2018), 7."},{"key":"e_1_3_2_1_44_1","first-page":"6124","article-title":"Improving RGB-D Salient Object Detection via Modality-Aware Decoder","volume":"31","author":"Song Mengke","year":"2022","unstructured":"Mengke Song, Wenfeng Song, Guowei Yang, and Chenglizhao Chen. 2022. Improving RGB-D Salient Object Detection via Modality-Aware Decoder. IEEE TIP, Vol. 31 (2022), 6124--6138.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Qingkun Song Li Ma JianKun Cao and Xiao Han. 2015. Image denoising based on mean filter and wavelet transform. In AITS.","DOI":"10.1109\/AITS.2015.17"},{"key":"e_1_3_2_1_46_1","first-page":"1714","article-title":"Hierarchical decoding network based on swin transformer for detecting salient objects in RGB-T images","volume":"29","author":"Sun Fan","year":"2022","unstructured":"Fan Sun, Wujie Zhou, Lv Ye, and Lu Yu. 2022. Hierarchical decoding network based on swin transformer for detecting salient objects in RGB-T images. IEEE SPL, Vol. 29 (2022), 1714--1718.","journal-title":"IEEE SPL"},{"key":"e_1_3_2_1_47_1","volume-title":"Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion","author":"Sun Peng","unstructured":"Peng Sun, Wenhu Zhang, Huanyu Wang, Songyuan Li, and Xi Li. 2021. Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion. In IEEE CVPR."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Chris Sweeney Greg Izatt and Russ Tedrake. 2019. A supervised approach to predicting noise in depth images. In ICRA.","DOI":"10.1109\/ICRA.2019.8793820"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202563"},{"key":"e_1_3_2_1_50_1","volume-title":"Disentangled high quality salient object detection","author":"Tang Lv","unstructured":"Lv Tang, Bo Li, Yijie Zhong, Shouhong Ding, and Mofei Song. 2021. Disentangled high quality salient object detection. In IEEE\/CVF ICCV."},{"key":"e_1_3_2_1_51_1","first-page":"5678","article-title":"Multi-interactive dual-decoder for RGB-thermal salient object detection","volume":"30","author":"Tu Zhengzheng","year":"2021","unstructured":"Zhengzheng Tu, Zhun Li, Chenglong Li, Yang Lang, and Jin Tang. 2021. Multi-interactive dual-decoder for RGB-thermal salient object detection. IEEE TIP, Vol. 30 (2021), 5678--5691.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_52_1","first-page":"3752","article-title":"Weakly alignment-free RGBT salient object detection with deep correlation network","volume":"31","author":"Tu Zhengzheng","year":"2022","unstructured":"Zhengzheng Tu, Zhun Li, Chenglong Li, and Jin Tang. 2022a. Weakly alignment-free RGBT salient object detection with deep correlation network. IEEE TIP, Vol. 31 (2022), 3752--3764.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_53_1","volume-title":"RGBT salient object detection: A large-scale dataset and benchmark","author":"Tu Zhengzheng","year":"2022","unstructured":"Zhengzheng Tu, Yan Ma, Zhun Li, Chenglong Li, Jieming Xu, and Yongtao Liu. 2022b. RGBT salient object detection: A large-scale dataset and benchmark. IEEE TMM (2022)."},{"key":"e_1_3_2_1_54_1","first-page":"160","article-title":"RGB-T image saliency detection via collaborative graph learning","volume":"22","author":"Tu Zhengzheng","year":"2019","unstructured":"Zhengzheng Tu, Tian Xia, Chenglong Li, Xiaoxiao Wang, Yan Ma, and Jin Tang. 2019. RGB-T image saliency detection via collaborative graph learning. IEEE TMM, Vol. 22, 1 (2019), 160--173.","journal-title":"IEEE TMM"},{"key":"e_1_3_2_1_55_1","volume-title":"Densefusion: 6d object pose estimation by iterative dense fusion","author":"Wang Chen","unstructured":"Chen Wang, Danfei Xu, Yuke Zhu, Roberto Mart\u00edn-Mart\u00edn, Cewu Lu, Li Fei-Fei, and Silvio Savarese. 2019. Densefusion: 6d object pose estimation by iterative dense fusion. In IEEE CVPR."},{"key":"e_1_3_2_1_56_1","first-page":"1285","article-title":"Learning Discriminative Cross-Modality Features for RGB-D Saliency Detection","volume":"31","author":"Wang Fengyun","year":"2022","unstructured":"Fengyun Wang, Jinshan Pan, Shoukun Xu, and Jinhui Tang. 2022a. Learning Discriminative Cross-Modality Features for RGB-D Saliency Detection. IEEE TIP, Vol. 31 (2022), 1285--1297.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_57_1","volume-title":"RGB-T saliency detection benchmark: Dataset, baselines, analysis and a novel approach","author":"Wang Guizhao","unstructured":"Guizhao Wang, Chenglong Li, Yunpeng Ma, Aihua Zheng, Jin Tang, and Bin Luo. 2018. RGB-T saliency detection benchmark: Dataset, baselines, analysis and a novel approach. In IGTA. Springer."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3099120"},{"key":"e_1_3_2_1_59_1","first-page":"415","article-title":"Pvt v2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang Wenhai","year":"2022","unstructured":"Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2022c. Pvt v2: Improved baselines with pyramid vision transformer. CVMJ, Vol. 8, 3 (2022), 415--424.","journal-title":"CVMJ"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3123548"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3263111"},{"key":"e_1_3_2_1_62_1","unstructured":"Zongwei Wu Guillaume Allibert Christophe Stolz Chao Ma and C\u00e9dric Demonceaux. 2021. Modality-Guided Subnetwork for Salient Object Detection. In 3DV."},{"key":"e_1_3_2_1_63_1","volume-title":"Danda Pani Paudel, and C\u00e9dric Demonceaux","author":"Wu Zongwei","year":"2022","unstructured":"Zongwei Wu, Shriarulmozhivarman Gobichettipalayam, Brahim Tamadazte, Guillaume Allibert, Danda Pani Paudel, and C\u00e9dric Demonceaux. 2022a. Robust RGB-D Fusion for Saliency Detection. In 3DV."},{"key":"e_1_3_2_1_64_1","volume-title":"Deng-Ping Fan, Jingjing Wang, Shuo Wang, C\u00e9dric Demonceaux, Radu Timofte, and Luc Van Gool.","author":"Wu Zongwei","year":"2022","unstructured":"Zongwei Wu, Danda Pani Paudel, Deng-Ping Fan, Jingjing Wang, Shuo Wang, C\u00e9dric Demonceaux, Radu Timofte, and Luc Van Gool. 2022b. Source-free Depth for Object Pop-out. arXiv preprint arXiv:2212.05370 (2022)."},{"key":"e_1_3_2_1_65_1","unstructured":"Zhenyu Wu Lin Wang Wei Wang Tengfei Shi Chenglizhao Chen Aimin Hao and Shuo Li. 2022c. Synthetic data supervised salient object detection. In ACM MM."},{"key":"e_1_3_2_1_66_1","volume-title":"Transformer Fusion for Indoor Rgb-D Semantic Segmentation. Available at SSRN 4251286","author":"Zongwei WU","year":"2022","unstructured":"Zongwei WU, Zhuyun ZHOU, Guillaume Allibert, Christophe Stolz, C\u00e9dric Demonceaux, and Chao Ma. 2022. Transformer Fusion for Indoor Rgb-D Semantic Segmentation. Available at SSRN 4251286 (2022)."},{"key":"e_1_3_2_1_67_1","volume-title":"Exploring Depth Contribution for Camouflaged Object Detection. arXiv e-prints","author":"Xiang Mochu","year":"2021","unstructured":"Mochu Xiang, Jing Zhang, Yunqiu Lv, Aixuan Li, Yiran Zhong, and Yuchao Dai. 2021. Exploring Depth Contribution for Camouflaged Object Detection. arXiv e-prints (2021), arXiv-2106."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2882156"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241196"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Senbo Yan Liang Peng Chuer Yu Zheng Yang Haifeng Liu and Deng Cai. 2022. Domain Reconstruction and Resampling for Robust Salient Object Detection. In ACM MM.","DOI":"10.1145\/3503161.3547927"},{"key":"e_1_3_2_1_71_1","volume-title":"Denseaspp for semantic segmentation in street scenes","author":"Yang Maoke","unstructured":"Maoke Yang, Kun Yu, Chi Zhang, Zhiwei Li, and Kuiyuan Yang. 2018. Denseaspp for semantic segmentation in street scenes. In IEEE CVPR."},{"key":"e_1_3_2_1_72_1","volume-title":"Gated channel transformation for visual recognition","author":"Yang Zongxin","unstructured":"Zongxin Yang, Linchao Zhu, Yu Wu, and Yi Yang. 2020. Gated channel transformation for visual recognition. In IEEE\/CVF CVPR."},{"key":"e_1_3_2_1_73_1","volume-title":"CamoFormer: Masked Separable Attention for Camouflaged Object Detection. arXiv preprint arXiv:2212.06570","author":"Yin Bowen","year":"2022","unstructured":"Bowen Yin, Xuying Zhang, Qibin Hou, Bo-Yuan Sun, Deng-Ping Fan, and Luc Van Gool. 2022. CamoFormer: Masked Separable Attention for Camouflaged Object Detection. arXiv preprint arXiv:2212.06570 (2022)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Chen Zhang Runmin Cong Qinwei Lin Lin Ma Feng Li Yao Zhao and Sam Kwong. 2021a. Cross-modality discrepant interaction network for RGB-D salient object detection. In ACM MM.","DOI":"10.1145\/3474085.3475364"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"crossref","unstructured":"Chen Zhang Runmin Cong Qinwei Lin Lin Ma Feng Li Yao Zhao and Sam Kwong. 2021b. Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection. In ACM MM.","DOI":"10.1145\/3474085.3475364"},{"key":"e_1_3_2_1_76_1","volume-title":"RGB-D Saliency Detection via Cascaded Mutual Information Minimization","author":"Zhang Jing","unstructured":"Jing Zhang, Deng-Ping Fan, Yuchao Dai, Xin Yu, Yiran Zhong, Nick Barnes, and Ling Shao. 2021c. RGB-D Saliency Detection via Cascaded Mutual Information Minimization. In IEEE ICCV."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"Miao Zhang Shuang Xu Yongri Piao Dongxiang Shi Shusen Lin and Huchuan Lu. 2022a. PreyNet: Preying on Camouflaged Objects. In ACM MM.","DOI":"10.1145\/3503161.3548178"},{"key":"e_1_3_2_1_78_1","volume-title":"C2DFNet: Criss-Cross Dynamic Filter Network for RGB-D Salient Object Detection","author":"Zhang Miao","year":"2022","unstructured":"Miao Zhang, Shunyu Yao, Beiqi Hu, Yongri Piao, and Wei Ji. 2022b. C2DFNet: Criss-Cross Dynamic Filter Network for RGB-D Salient Object Detection. IEEE TMM (2022)."},{"key":"e_1_3_2_1_79_1","first-page":"1804","article-title":"Revisiting feature fusion for RGB-T salient object detection","volume":"31","author":"Zhang Qiang","year":"2020","unstructured":"Qiang Zhang, Tonglin Xiao, Nianchang Huang, Dingwen Zhang, and Jungong Han. 2020. Revisiting feature fusion for RGB-T salient object detection. IEEE TCSVT, Vol. 31, 5 (2020), 1804--1818.","journal-title":"IEEE TCSVT"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"crossref","unstructured":"Wenbo Zhang Ge-Peng Ji Zhuo Wang Keren Fu and Qijun Zhao. 2021d. Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection. In ACM MM.","DOI":"10.1145\/3474085.3475240"},{"key":"e_1_3_2_1_81_1","volume-title":"Pyramid scene parsing network","author":"Zhao Hengshuang","unstructured":"Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. 2017. Pyramid scene parsing network. In IEEE CVPR."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Jiawei Zhao Yifan Zhao Jia Li and Xiaowu Chen. 2020. Is depth really necessary for salient object detection?. In ACM MM.","DOI":"10.1145\/3394171.3413855"},{"key":"e_1_3_2_1_83_1","first-page":"7717","article-title":"RGB-D salient object detection with ubiquitous target awareness","volume":"30","author":"Zhao Yifan","year":"2021","unstructured":"Yifan Zhao, Jiawei Zhao, Jia Li, and Xiaowu Chen. 2021. RGB-D salient object detection with ubiquitous target awareness. IEEE TIP, Vol. 30 (2021), 7717--7731.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"crossref","unstructured":"Jiayuan Zhou Lijun Wang Huchuan Lu Kaining Huang Xinchu Shi and Bocong Liu. 2022. MVSalNet: Multi-view Augmentation for RGB-D Salient Object Detection. In ECCV.","DOI":"10.1007\/978-3-031-19818-2_16"},{"key":"e_1_3_2_1_85_1","volume-title":"Specificity-preserving RGB-D Saliency Detection","author":"Zhou Tao","unstructured":"Tao Zhou, Huazhu Fu, Geng Chen, Yi Zhou, Deng-Ping Fan, and Ling Shao. 2021a. Specificity-preserving RGB-D Saliency Detection. In IEEE ICCV."},{"key":"e_1_3_2_1_86_1","first-page":"1224","article-title":"ECFFNet: Effective and consistent feature fusion network for RGB-T salient object detection","volume":"32","author":"Zhou Wujie","year":"2021","unstructured":"Wujie Zhou, Qinling Guo, Jingsheng Lei, Lu Yu, and Jenq-Neng Hwang. 2021b. ECFFNet: Effective and consistent feature fusion network for RGB-T salient object detection. IEEE TCSVT, Vol. 32, 3 (2021), 1224--1235.","journal-title":"IEEE TCSVT"},{"key":"e_1_3_2_1_87_1","first-page":"957","article-title":"APNet: Adversarial learning assistance and perceived importance fusion network for all-day RGB-T salient object detection","volume":"6","author":"Zhou Wujie","year":"2021","unstructured":"Wujie Zhou, Yun Zhu, Jingsheng Lei, Jian Wan, and Lu Yu. 2021c. APNet: Adversarial learning assistance and perceived importance fusion network for all-day RGB-T salient object detection. IEEE TETCI, Vol. 6, 4 (2021), 957--968.","journal-title":"IEEE TETCI"},{"key":"e_1_3_2_1_88_1","first-page":"1329","article-title":"LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-thermal images","volume":"32","author":"Zhou Wujie","year":"2023","unstructured":"Wujie Zhou, Yun Zhu, Jingsheng Lei, Rongwang Yang, and Lu Yu. 2023. LSNet: Lightweight spatial boosting network for detecting salient objects in RGB-thermal images. IEEE TIP, Vol. 32 (2023), 1329--1340.","journal-title":"IEEE TIP"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611970","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:09:25Z","timestamp":1755821365000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":88,"alternative-id":["10.1145\/3581783.3611970","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611970","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}