最后更新于:2024年5月13日 10:00
Last updated on: 2024-05-13 10:00
Welcome
👋 Hi! My name is Junyao Hu (胡钧耀). I’m a first year PhD student of Nankai University (南开大学). I’m advised by Professor Jufeng Yang (杨巨峰) in Computer Vision Lab (计算机视觉实验室).
🔍 My research interests include deep learning and computer vision, particularly focusing on:
- 🤔Image sentiment analysis: image emotion label classification, ranking, and distribution learning.
- 🏃Video understanding: video prediction, action recognition.
- 🔮Visual generative AI: image/video diffusion model application.
- 💞Psychology interdisciplinary research: early screening of autism spectrum disorder.
🥰 You can contact with me in following ways: Github / Email (hujunyao@mail.nankai.edu.cn) / WeChat (ID: LittleDream_hjy, and the QR code is in the picture above). Please feel free to make any suggestions. Any questions and inquiries about my work and study life are welcome.
🎞️ I am trying to operate my self-media Chinese channel for training my expression ability, sharing my scientific research and life experience, and bringing useful knowledge to everyone. Updates may not be frequent, and I will strive for quality. You can see me on Bilibili (@-胡椒椒椒)。
📃 More details are shown on my CV page.
News
2024-02-27 😋 Accepted A paper was accepted to CVPR 2024.
2023-09-01 ✒️ Study I start my Ph.D. studying at Nankai University under the supervision of Prof. Jufeng Yang.
2023-07-15 ✒️ Study I end my undergraduate life at China University of Mining and Technology, thanks to all the teachers and friends around me, especially my parents!
2023-06-10 💼 Activity I attend the VALSE 2023 conference at Wuxi, China.
Selected Publications
If you want to view my all publications, click here.
Note: #
= Equal Contribution , *
= Corresponding Author.
CVPR24 ExtDM: Distribution extrapolation diffusion model for video prediction
Zhicheng Zhang#, Junyao Hu#, Wentao Cheng*, Danda Paudel, Jufeng Yang
TL;DR: We present ExtDM, a new diffusion model that extrapolates video content from current frames by accurately modeling distribution shifts towards future frames.
📘 CVPR 📃 Paper 📃 中译版 📦 Code ⚒️ Project 📊 Poster 📅 Slide 🎞️ Bilibili 🎞️ YouTube
Details
Abstract: Video prediction is a challenging task due to its nature of uncertainty, especially for forecasting a long period. To model the temporal dynamics, advanced methods benefit from the recent success of diffusion models, and repeatedly refine the predicted future frames with 3D spatiotemporal U-Net. However, there exists a gap between the present and future and the repeated usage of U-Net brings a heavy computation burden. To address this, we propose a diffusion-based video prediction method that predicts future frames by extrapolating the present distribution of features, namely ExtDM. Specifically, our method consists of three components: (i) a motion autoencoder conducts a bijection transformation between video frames and motion cues; (ii) a layered distribution adaptor module extrapolates the present features in the guidance of Gaussian distribution; (iii) a 3D U-Net architecture specialized for jointly fusing guidance and features among the temporal dimension by spatiotemporal-window attention. Extensive experiments on five popular benchmarks covering short- and long-term video prediction verify the effectiveness of ExtDM.BibTex1 |
|
😅 I’m still working … I can still learn …. Zzz … 😴
Projects
- Tasks_for_Rookies
How to get started with computer vision research. - common_metrics_on_video_quality
You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos. - academic-project-page-template-vue
A project template powered by Vue (in development).
Academic Services
Reviewer
- Conference: CVPR’24 (Outstanding Reviewer) , ACMMM’23
- Transaction: TMM’23
Other
Datawhale: Promotion Ambassador
Mini Sora: Community Contributor
SmartFlow: Community Contributor
Teaching Assistant for High School Student Talent Plan 2024
- Instruct high school students to learn computer basics and create interesting projects.
- Homework and anwer analysis: ⚒️ Project 🎞️ Video