Publications
2024
Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Lu Jiang, Ming-Hsuan Yang, "Text-Driven Image Editing via Learnable Regions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
[PDF] [Project Page]
Chi-Hsi Kung, Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting Chen, "Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
2023
Yi-Lun Lee, Yi-Hsuan Tsai, Wei-Chen Chiu, Chen-Yu Lee, "Multimodal Prompting with Missing Modalities for Visual Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
2022
Bolivar Solarte*, Chin-Hsuan Wu*, Yueh-Cheng Liu, Yi-Hsuan Tsai, Min Sun, "360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning", Conference on Neural Information Processing Systems (NeurIPS), 2022.
[PDF] [Project Page]
Yu-Ting Yen, Chia-Ni Lu, Wei-Chen Chiu, Yi-Hsuan Tsai, "3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling", European Conference on Computer Vision (ECCV), 2022.
[PDF] [Project Page] [Code]
Dongwan Kim, Yi-Hsuan Tsai, Yumin Suh, Masoud Faraki, Sparsh Garg, Manmohan Chandraker, Bohyung Han, "Learning Semantic Segmentation from Multiple Datasets with Label Shifts", European Conference on Computer Vision (ECCV), 2022.
Zaid Tasneem, Giovanni Milione, Yi-Hsuan Tsai, Xiang Yu, Ashok Veeraraghavan, Manmohan Chandraker, Francesco Pittaluga, "Learning Phase Mask for Privacy-Preserving Passive Depth Estimation", European Conference on Computer Vision (ECCV), 2022.
[PDF]
Meng-Shiun Tsai*, Pei-Ze Chiang*, Yi-Hsuan Tsai, Wei-Chen Chiu, "Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement", IEEE International Conference on Intelligent Robots and Systems (IROS), 2022.
[preprint PDF]
Yi-Wen Chen, Yi-Hsuan Tsai, Ming-Hsuan Yang, "Understanding Synonymous Referring Expressions via Contrastive Features", International Journal of Computer Vision (IJCV), 2022.
[PDF]
Bolivar Solarte, Yueh-Cheng Liu, Chin-Hsuan Wu, Yi-Hsuan Tsai, Min Sun, "360-DFPE: Leveraging Monocular 360-Layouts for Direct Floor Plan Estimation", IEEE Robotics and Automation Letters, 2022.
[PDF] [Project Page] [Code and Dataset]
Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang, Samuel Schulter, Buyu Liu, Sparsh Garg, In So Kweon, Kuk-Jin Yoon, "MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[PDF] [Project Page]
Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker, "On Generalizing Beyond Domains in Cross-Domain Continual Learning", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[PDF]
Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Masoud Faraki, Ramin Moslemi, Manmohan Chandraker, Yun Fu, "Learning to Learn across Diverse Data Biases in Deep Face Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[PDF]
Yufeng Wang, Yi-Hsuan Tsai, Wei-Chih Hung, Wenrui Ding, Shuo Liu, Ming-Hsuan Yang, "Semi-supervised Multi-task Learning for Semantics and Depth", IEEE Winter Conference on Applications of Computer Vision (WACV), 2022.
[PDF]
2021
Donghyun Kim, Yi-Hsuan Tsai, Bingbing Zhuang, Xiang Yu, Stan Sclaroff, Kate Saenko, Manmohan Chandraker, "Learning Cross-modal Contrastive Features for Video Domain Adaptation", IEEE International Conference on Computer Vision (ICCV), 2021.
[PDF]
Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai, "LED2-Net: Monocular 360˚ Layout Estimation via Differentiable Depth", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. (Oral)
[PDF] [Project Page] [Code]
Masoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh, Manmohan Chandraker, "Cross-Domain Similarity Learning for Face Recognition in Unseen Domains", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[PDF]
Bolivar Solarte, Chin-Hsuan Wu, Kuan-Wei Lu, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun, "Robust 360-8PA: Redesigning the Normalized 8-point Algorithm for 360-FoV Images", IEEE International Conference on Robotics and Automation (ICRA), 2021.
[PDF] [Project Page] [Code]
2020
Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker, "Adaptation Across Extreme Variations using Unlabeled Bridges", Proceedings of British Machine Vision Conference (BMVC), 2020.
[PDF]
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang, "Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization", Proceedings of British Machine Vision Conference (BMVC), 2020.
[PDF]
Sujoy Paul, Yi-Hsuan Tsai, Samuel Schulter, Amit K. Roy-Chowdhury, Manmohan Chandraker, "Domain Adaptive Semantic Segmentation Using Weak Labels", European Conference on Computer Vision (ECCV), 2020.
[PDF] [Project Page]
Cheng-Chun Hsu, Yi-Hsuan Tsai, Yen-Yu Lin, Ming-Hsuan Yang, "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector", European Conference on Computer Vision (ECCV), 2020.
[PDF] [Project Page] [Code]
Xiangyun Zhao, Samuel Schulter, Gaurav Sharma, Yi-Hsuan Tsai, Manmohan Chandraker, Ying Wu, "Object Detection with a Unified Label Space from Multiple Datasets", European Conference on Computer Vision (ECCV), 2020.
Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai, "BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
[PDF] [Project Page] [Code]
Ning-Hsu Wang, Bolivar Solarte, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun, "360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume", IEEE International Conference on Robotics and Automation (ICRA), 2020.
[preprint PDF] [Project Page] [Code]
Jong-Chyi Su, Yi-Hsuan Tsai, Kihyuk Sohn, Buyu Liu, Subhransu Maji, Manmohan Chandraker, "Active Adversarial Domain Adaptation", IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.
[preprint PDF] [Project Page]
Han-Kai Hsu, Chun-Han Yao, Yi-Hsuan Tsai, Wei-Chih Hung, Hung-Yu Tseng, Maneesh Singh, Ming-Hsuan Yang, "Progressive Domain Adaptation for Object Detection", IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.
[preprint PDF] [Code]
Taihong Xiao, Yi-Hsuan Tsai, Kihyuk Sohn, Manmohan Chandraker, Ming-Hsuan Yang, "Adversarial Learning of Privacy-Preserving and Task-Oriented Representations", AAAI Conference on Artificial Intelligence (AAAI), 2020.
[preprint PDF] [Project Page]
Yi-Wen Chen, Yi-Hsuan Tsai, Yen-Yu Lin, Ming-Hsuan Yang, "VOSTR: Video Object Segmentation via Transferable Representations", International Journal of Computer Vision (IJCV), 2020.
2019
Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter, Manmohan Chandraker, "Domain Adaptation for Structured Output via Discriminative Patch Representations", IEEE International Conference on Computer Vision (ICCV), 2019. (Oral)
Yi-Wen Chen, Yi-Hsuan Tsai, Tiantian Wang, Yen-Yu Lin, Ming-Hsuan Yang, "Referring Expression Object Segmentation with Caption-Aware Consistency", Proceedings of British Machine Vision Conference (BMVC), 2019.
[preprint PDF] [Supp] [Project Page]
Haifang Qin, Weixiang Hong, Wei-Chih Hung, Yi-Hsuan Tsai, Ming-Hsuan Yang, "A Top-Down Unified Framework for Instance-level Human Parsing", Proceedings of British Machine Vision Conference (BMVC), 2019.
[preprint PDF] [Supp] [Project Page]
Tsun-Hsuan Wang, Hou-Ning Hu, Chieh Hubert Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun, "3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization", IEEE International Conference on Intelligent Robots and Systems (IROS), 2019.
[preprint PDF] [Code] [Project Page]
Hsueh-Ying Lai, Yi-Hsuan Tsai, Wei-Chen Chiu, "Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[preprint PDF] [Code] [Project Page]
Tsun-Hsuan Wang, Fu-En Wang, Juan-Ting Lin, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun, "Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation", IEEE International Conference on Robotics and Automation (ICRA), 2019.
2018
Yi-Wen Chen, Yi-Hsuan Tsai, Chu-Ya Yang, Yen-Yu Lin, Ming-Hsuan Yang, "Unseen Object Segmentation in Videos via Transferable Representations", Asian Conference on Computer Vision (ACCV), 2018. (Oral)
Best Student Paper Honorable Mention
Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, Ming-Hsuan Yang, "Adversarial Learning for Semi-supervised Semantic Segmentation", Proceedings of British Machine Vision Conference (BMVC), 2018.
Yi-Hsuan Tsai*, Wei-Chih Hung*, Samuel Schulter, Kihyuk Sohn, Ming-Hsuan Yang, Manmohan Chandraker, "Learning to Adapt Structured Output Space for Semantic Segmentation", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight) (* indicates equal contribution)
[preprint PDF] [Supp] [Project Page] (3rd place in the VISDA 2017 Challenge)
Jingchun Cheng, Yi-Hsuan Tsai, Wei-Chih Hung, Shengjin Wang, Ming-Hsuan Yang, "Fast and Accurate Online Video Object Segmentation via Tracking Parts", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight)
[preprint PDF] [Supp] [Project Page]
Yi-Hsuan Tsai, Ming-Yu Liu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz, "Learning Binary Residual Representations for Domain-Specific Video Streaming", AAAI Conference on Artificial Intelligence (AAAI), 2018.
[preprint PDF] [Project Page] [Blog]
Guangyu Zhong, Yi-Hsuan Tsai, Sifei Liu, Zhixun Su, Ming-Hsuan Yang, "Learning Video-Story Composition via Recurrent Neural Network", IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.
[preprint PDF] [Supp] [Project Page]
2017
Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang, Ming-Hsuan Yang, "SegFlow: Joint Learning for Video Object Segmentation and Optical Flow", Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017.
Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang, "Scene Parsing with Global Context Embedding", Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017.
[preprint PDF] [Supp] [Project Page]
Jingchun Cheng, Sifei Liu, Yi-Hsuan Tsai, Wei-Chih Hung, Shalini De Mello, Jinwei Gu, Jan Kautz, Shengjin Wang, Ming-Hsuan Yang, "Learning to Segment Instances in Videos with Spatial Propagation Network", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2017.
Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan Yang, "Deep Image Harmonization", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[preprint PDF] [Supp] [Project Page] (Implemented in Photoshop Mix)
2016
Guangyu Zhong*, Yi-Hsuan Tsai*, Ming-Hsuan Yang, "Weakly-supervised Video Scene Co-parsing", Asian Conference on Computer Vision (ACCV), 2016. (Oral) (* indicates equal contribution)
[PDF] [More Results] [Video]
Yi-Hsuan Tsai*, Guangyu Zhong*, Ming-Hsuan Yang, "Semantic Co-segmentation in Videos", European Conference on Computer Vision (ECCV), 2016. (* indicates equal contribution)
[PDF] [Supp] [Project Page]
Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Ming-Hsuan Yang, "Sky is Not the Limit: Semantic-Aware Sky Replacement", ACM Transactions on Graphics (SIGGRAPH), 2016.
[PDF (high-res)] [PDF (low-res)] [Slide] [Project Page] (Demo in Adobe MAX)
[Supp (high-res)] [Supp (low-res)] [Scene Parsing Model] [Sky Image Dataset]
Yi-Hsuan Tsai, Ming-Hsuan Yang, Michael J. Black, "Video Segmentation via Object Flow", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Spotlight)
2015 and before
Yi-Hsuan Tsai, Onur Hamsici, Ming-Hsuan Yang, "Adaptive Region Pooling for Object Detection", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
Jimei Yang, Yi-Hsuan Tsai, Ming-Hsuan Yang, "Exemplar Cut", Proceedings of IEEEInternational Conference on Computer Vision (ICCV), 2013.
[PDF] [More Results] [Code]
Yi-Hsuan Tsai, Jimei Yang, Ming-Hsuan Yang, "Decomposed Learning for Joint Object Segmentation and Categorization", Proceedings of British Machine Vision Conference (BMVC), 2013.