News
(2025/09), one paper on exploiting SAM2 for camfoulaged video understanding is accepted to NeurIPS 2025.
(2025/08), I will be serving as an Area Chair for ICLR 2026.
(2025/06), three paper accepted to ICCV 2025 inclding one highlight paper.
(2025/06), will give an invited talk at ICCV 2025 Workshop CVAUI-AAMVEM.
(2025/03), one paper accepted to Visual Intelligence: camouflage video segmentation using foundation model SAM2.
(2025/02), two papers accepted to CVPR 2025: vision-language model for 3D point-cloud segmentation; video segmentation using mamba.
(2025/01), one paper on multi-modal 3D point-cloud segmentation is accepted to ICLR 2025 as spotlight paper (acceptance rate: 5.1%).
(2024/12), Guest editor of MIR special issue Multimodal Learning, Temporal Modeling, and Foundation Models for Video Understanding.
(2024/12), Three paper are accepted: SAM-aware few-shot segmentation to AAAI 2025, open-vocabulary video segmentation to TMM, video foundation model for medical 3D segmentation to MICCAI 2024 workshop.
(2024/06), Give an invited talk about video segmentation on The 3rd Pixel-level Video Understanding in the Wild @ CVPR2024.
(2024/04), one paper on video segmentation & visual attention is accepted to TPAMI!
(2024/02), one paper on 3D point-cloud segmentation & visual attention is accepted to CVPR 2024!
(2024/01), I successfully defended my PhD at CVL, ETH Zurich!
(2023/07), one paper on image synthesis & contrastive learning is accepted to TPAMI!
(2023/03), one paper on camouflaged scene understanding & visual attention is accepted to CVPR 2023 and one paper on image synthesis & contrastive learning is accepted to ICLR 2023!
(2022/07), one paper on video segmentation & visual attention is accepted to ECCV 2022!
(2022/04), one paper on video segmentation & visual attention is accepted to CVPR 2022 and one paper on image segmentation & visual attention is accepted TPAMI!
(2021/08), we obtain the best paper award in AIM in ICCV 2021!
(2021/08), two papers (one on multi-task learning, one on image restoration) are accepted to ICCV 2021!
(2021/04), one paper on multi-task learning is accepted to CVPR 2021!
(2020/08), two papers (one on image segmentation & visual attention, one on classification & visual attention) are accepted to ECCV 2020 and one paper on weak supervision is accepted to TPAMI!
(2020/06), Gave a presentation on LID workshop @ CVPR 2020.
(2020/06), we obtain the first prize in WSSS track of LID workshop in CVPR 2020 and the best paper award!
(2020/03), one paper on camouflage scene understanding is accepted to CVPR 2020!