Multimodal Structured Document Understanding and MLLM Generated Document Detection
https://conf.csig.org.cn/10403.html, CSIG MMLM tutorial, Beijing, China
Talks and presentations
3D General Representations: Discussions on how to learn from multi-dataset to obtain the general representations
https://www.163.com/dy/article/I9JGVH470511CQLG.html, Tutorial for 3D pre-training, Shanghai, China
Tutorial-3: Introduction of UDA and SSDA Modules in 3DTrans
Tutorial, Onstie: TBC & Online: TBC, Shanghai, China
Tutorial-2: Uni3D Introduction and 3DTrans repo for Multi-dataset Training
Tutorial, Onstie: Tencent Conference & Weichat & Bilibili Website, Shanghai, China
Tutorial-1: Re-thinking on Model Unified Representation Learning and Generalization in Autonomous Driving Scenarios
Tutorial, Onstie: Tencent Conference & Bilibili Website, Shanghai, China
Research on Multi-dataset Pre-training and Single-dataset Active Learning Methods under 3D Perception Scene
Discussion, Room 8, Level 12, L1 Building, Shanghai, China
Thesis Defense
Talk, Online, Shanghai, China
Oral Presentation on ACM MM-2021
Talk, International Expo Center, Chengdu, China
National Scholarship Defense
Talk, Room 425, Science building, Handan Campus, Fudan University, Shanghai, China
Valse Report on Domain Adaptive Object Detection
Talk, Exhibition Hall 3C, International Expo Center, Hangzhou, China