Tongjia Chen 陈同嘉

Pronounced like 'TomJade', or you can just call me Tom :)

I'm an incoming CS Ph.D. student at the University of Western Australia (UWA), under the supervision of Prof. Ajmal Mian.

I was fortunate to have been working closely with Dr. Chen Chen on multi-modality video understanding.

Email  /  Github  /  Google Scholar  /  LinkedIn

profile photo
News

[2024-02] Our paper OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition was accepted at CVPR 2024. See you in Seattle!

[2023-06] We won the 1st place of the AQTC Challenge at CVPR@23 LOng-form VidEo Understanding and Generation (LOVEU) Workshop.

[2023-02] Our paper AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers was accepted at CVPR 2023.

Preprints
Motion-Grounded Video Reasoning: Understanding and Perceiving Motion at Pixel Level
Andong Deng, Tongjia Chen, Shoubin Yu, Taojiannan Yang, Lincoln Spencer, Yapeng Tian, Ajmal Mian, Mohit Bansal, Chen Chen
Preprint, 2024
Project / arXiv
Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling
Yong He, Hongshan Yu, Muhammad Ibrahim, Xiaoyan Liu, Tongjia Chen, Anwaar Ulhaq, Ajmal Mian
Preprint, 2024
arXiv
Publications
OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
Tongjia Chen, Hongshan Yu, Zhengeng Yang, Zechuan Li, Wei Sun, Chen Chen
CVPR 2024
Project / Code / arXiv
First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment
Tongjia Chen, Hongshan Yu, Zhengeng Yang, Ming Li, Zechuan Li, Jingwen Wang, Wei Miao, Wei Sun, Chen Chen
Tech Report, LOVEU Workshop, CVPR 2023
Code / Certificate
AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers
Zechuan Li, Hongshan Yu, Zhengeng Yang, Tongjia Chen, Naveed Akhtar
CVPR 2023
Project / Code / Video
Awards

1st place of the AQTC Challenge at CVPR@23 LOng-form VidEo Understanding and Generation (LOVEU) Workshop. 2023

Academic Excellence Scholarship of HNU (Top 20%). 2021, 2022

Academic Excellence Scholarship of CUG (Top 10%). 2017-2020

Talks

Time: 2023.6.18

Title: First Place Solution to the CVPR'2023 AQTC Challenge: A Function-Interaction Centric Approach with Spatiotemporal Visual-Language Alignment

Source: LOng-form VidEo Understanding and Generation (LOVEU) Workshop, CVPR 2023.

Video / Slides
Misc

CrossFitter / Culer / TIFOSI



Updated at Jul. 2024
Thanks Jon Barron for this amazing template.