Profiles2021-2024
Chunhua Shen
Zhejiang University
15Papers
9Last author
23Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue DataAuthor 7 of 9ACL Findings 2024 · 8 citations
- Conditional Positional Encodings for Vision TransformersAuthor 5 of 5ICLR 2023 · 406 citations
- Metric3D: Towards Zero-shot Metric 3D Prediction from A Single ImageAuthor 8 of 9ICCV 2023 · 388 citations
- Robust Geometry-Preserving Depth Estimation Using Differentiable RenderingAuthor 8 of 9ICCV 2023 · 7 citations
- SegViT: Semantic Segmentation with Plain Vision TransformersAuthor 6 of 7NeurIPS 2022 · 242 citations
- DENSE: Data-Free One-Shot Federated LearningAuthor 7 of 8NeurIPS 2022 · 202 citations
- Fully Convolutional One-Stage 3D Object Detection on LiDAR Range ImagesAuthor 5 of 5NeurIPS 2022 · 168 citations
- Catching Both Gray and Black Swans: Open-set Supervised Anomaly DetectionAuthor 3 of 3CVPR 2022 · 163 citations
- Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face RecognitionAuthor 5 of 7NeurIPS 2022 · 84 citations
- Text-Adaptive Multiple Visual Prototype Matching for Video-Text RetrievalAuthor 7 of 7NeurIPS 2022 · 52 citations
- Multi-dataset Training of Transformers for Robust Action RecognitionAuthor 4 of 4NeurIPS 2022 · 14 citations
- Twins: Revisiting the Design of Spatial Attention in Vision TransformersAuthor 8 of 8NeurIPS 2021 · 1,388 citations
- Dynamic Neural Representational Decoders for High-Resolution Semantic SegmentationAuthor 4 of 4NeurIPS 2021 · 23 citations
- FATNN: Fast and Accurate Ternary Neural Networks*Author 3 of 3ICCV 2021 · 22 citations
- FCPose: Fully Convolutional Multi-Person Pose Estimation With Dynamic Instance-Aware ConvolutionsAuthor 4 of 4CVPR 2021
