Wenqi Jia

Hey! 😊

I am a first-year PhD student in Computer Science at the Georgia Institute of Technology (GaTech) and currently working with Prof. James Rehg. I received my B.Eng from the Hong Kong Polytechnic University, majoring in Electronic and Information Engineering. I was working in Signal Processing Lab with Prof. Kin-Man Lam as an undergraduate research assistant since my sophomore year.

Email  /  Google Scholar  /  Twitter  /  Github  /  LinkedIn

profile photo
Research

My research interests lie in Computer Vision and Machine Learning. I’m particularly interested in hand-object interaction under the First-Person perspective and aim to leverage Egocentric Vision to model daily activities and social behaviors to help understand the interaction between humans and their surrounding world.

News

08.2022   One journal paper accepted by TNNLS! πŸŽ‰
07.2022   One paper accepted by ECCV '22 Hi Israel!! πŸŽ‰βœ‘οΈ
06.2022   I attended CVPR 22 in person and got covid πŸ˜•
04.2022   I've accepted my CS PhD offer at Georgia Tech! 🐝🐝🐝
04.2022   Our Ego4D challenges are alive now! Come join us on the leaderboard! πŸ†πŸš©
03.2022   Our Ego4D paper has been accepted by CVPR '22 and selected for an oral presentation! πŸ₯‚

Publications
Generative Adversarial Network for Future Hand Segmentation from Egocentric Video
Wenqi Jia*, Miao Liu, James Rehg
ECCV, 2022
project page / paper /  code /  supplement / video /  bibtex

(⇐ Move your cursor on the image for a short demo video!)

Ego4D: Around the World in 3,000 Hours of Egocentric Video
Kristen Grauman, et al.
CVPR, 2022   (Oral)
project page / paper / code / dataset / video / bibtex

Paying More Attention to Motion: Attention Distillation for Learning Video Representations
Miao Liu, Wenqi Jia, Xin Chen, Yun Zhang, Yin Li, James Rehg
IJCV, 2021   (Special Issue) (under review)
arXiv / code / bibtex
Holistic-Guided Disentangled Learning With Cross-Video Semantics Mining for Concurrent First-Person and Third-Person Activity Recognition
Tianshan Liu, Wenqi Jia, Rui Zhao, Kin-Man Lam, Jun Kong
TNNLS, 2022
paper / bibtex
Feature Redundancy Mining: Deep Light-Weight Image Super-Resolution Model
Jun Xiao, Wenqi Jia, Kin-Man Lam
ICASSP, 2021
paper / bibtex

Deep progressive convolutional neural network for blind super-resolution with multiple degradations
Jun Xiao, Rui Zhao, Shun-Cheung Lai, Wenqi Jia, Kin-Man Lam
ICIP, 2019
paper / bibtex

View extrapolation with multiplane images works better if you reason about disocclusions and disparity sampling frequencies.

Academic Service and Honor
  • Reviewer πŸ”Ž, CVPR '22, ECCV '22
  • First Runner Up πŸ₯ˆ, IEEE Video and Image Processing Cup (VIP Cup) 2017
Volunteer Work
  • Certified First Responder πŸš‘, Hong Kong Red Cross, Jun 2015 - Jun 2019
  • General Secretary πŸ€Ήβ€β™€οΈ, Exploring Hong Kong Community (EHKC), Jan 2017 - Jan 2018
  • International Volunteer 🀝, Service Learning Project in Cambodia, Jun 2016
Fun facts about me!
  • Obviously I love travelling around the world: πŸ±β€πŸš€


  • I'm Chinese and if you wonder what's the correct pronunciation of my name (with the tones!), try to say the brand "Givenchy"in British accent 🀣
  • I play the piano 🎹 & very into classical music
  • I love Renaissance art and Surrealism! During the pandemic I was admitted as a Master of Arts in Art History at the University of Hong Kong (but didn't enrol cause I decided to be focused on my passion in Computer Science first πŸ‘©β€πŸ’»)
  • I learned my Japanese through Anime (NARUTO is my favorite πŸ”₯)
  • Je parle un peu franΓ§ais (a beginner who likes to say Je ne sais pas) 🧐