Biography
I am now a master student (year 2) from IIG group in Tsinghua University, supervised by Prof. Yujiu Yang. I received my bachelor degree in Department of Automation from Tsinghua University in 2021. My major research interests are MultiModal Learning. Recently, I focus on VLP(Vision Language Pre-training) and some downstream tasks, such as VQA(Visual Question Answering) and VTG(Video Temporal Grounding).
Recent News
Selected Publications
-
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
-
MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model
-
MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering
Awards
- 2023.7, Tencent Rhino-Bird Research Scholarship
Internship
- 2022.6~Present, AMAI, Department of Data Platform, Tencent
Professional Activities
- Conference Reviewer: ACM MM.
- Journal Reviewer: Pattern Recognition (PR).
(Last updated on May 11, 2023)