Biography
I am a 5-th year Ph.D. Candidate in School of Computer Science at Fudan University supervised by Prof. Zuxuan Wu and Prof. Yu-Gang Jiang. I am a member of the Fudan Vision and Learning Laboratory. Before this, I recieved my BS degree in Computer Science from the Fudan University with Prof. Yu-Gang Jiang in 2020. My research interests are in computer vision and deep learning. My current research particularly focuses on large-scale video understanding and multimodal learning.
I'm set to graduate in 2025 and actively exploring job opporunities in both industry and academia. If you are interested in working with me, please feel free to email me.
Publication
- GenRec: Unifying Video Generation and Recognition with Diffusion Models.
Neural Information Processing Systems (NeuIPS), 2024
- Imbalanced gradients: a subtle cause of overestimated adversarial robustness.
Machine Learning, 2024
- Building an Open-Vocabulary Video CLIP model with Better Architectures, Optimization and Data.
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
- Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization.
International Conference on Machine Learning (ICML), Hawaii, USA, July, 2023
- To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning.
Technical Report, 2023
- HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition.
Transactions on Multimedia Computing, Communications and Applications (TOMM), 2023
- Semi-supervised Vision Transformers.
European Conference on Computer Vision (ECCV), Tel Aviv, Israel, Sept., 2022
- Cross-domain Contrastive Learning for Unsupervised Domain Adaptation.
Transactions on Multimedia (TMM), 2021
- VideoLT: Large-scale Long-tailed Video Recognition.
International Conference on Computer Vision (ICCV), Virtual, Oct., 2021
- A Multimodal Framework for Video Ads Understanding.
International Conference on Multimedia (ACM MM), Chengdu, Oct., 2021
- Exploring the Consistency of Segment-level and Video-level Predictions for Improved Temporal Concept Localization in Videos.
International Conference on Computer Vision Workshop (ICCV workshop), Korean, Oct., 2019
Hornors & Awards
- First Class Award Scholarship of Fudan University, Dec., 2023
- Venustech Scholarship, Nov., 2021
- Tencent Advertising Algorithm Competition, Leader, Ranked 3rd, Aug., 2021
- First Class Award Graduation Scholarship of Fudan University, Apr. 2020
- Google YouTube-8M Video Understanding Challenge, Leader, Ranked 2nd, Oct. 2019
Professional Service
- Reviewer for CVPR2023, AAAI2023, NeurIPS2023