Profiles2021-2024
Songcen Xu
Huawei Noah's Ark Lab
15Papers
0Last author
46Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion ModelsAuthor 4 of 6CVPR 2024
- Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion ModelAuthor 9 of 10CVPR 2024
- Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling NetworkAuthor 4 of 6ICCV 2023 · 70 citations
- PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video RetrievalAuthor 7 of 9ICCV 2023 · 25 citations
- Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only ImagesAuthor 8 of 10ICCV 2023 · 20 citations
- UnifiedGesture: A Unified Gesture Synthesis Model for Multiple SkeletonsAuthor 8 of 11ACM MM 2023 · 17 citations
- Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the WildAuthor 8 of 9NeurIPS 2023 · 13 citations
- HiVLP: Hierarchical Interactive Video-Language Pre-TrainingAuthor 4 of 8ICCV 2023 · 6 citations
- CLIPPING: Distilling CLIP-Based Models with a Student Base for Video-Language RetrievalAuthor 5 of 8CVPR 2023
- Co-speech Gesture Synthesis by Reinforcement Learning with Contrastive Pretrained RewardsAuthor 6 of 7CVPR 2023
- Instance Segmentation in 3D Scenes using Semantic Superpoint Tree NetworksAuthor 3 of 5ICCV 2021 · 170 citations
- DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose ConsistencyAuthor 4 of 6ICCV 2021 · 169 citations
- Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution AlignmentAuthor 3 of 4AAAI 2021 · 13 citations
- Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEAuthor 3 of 4CVPR 2021
- Multiple Instance Active Learning for Object DetectionAuthor 4 of 5CVPR 2021
