Bin Ren

Email / Google Scholar / Github / Twitter

Bin Ren (任斌)

I am a second-year Ph.D. student in the Italian National Artificial Intelligence Program co-organized by the University of Pisa, Italy, and the University of Trento, Italy. I am in the Multimedia and Human Understanding Group (MHUG) advised by Prof. Dr. Nicu Sebe and Prof. Dr. Rita Cucchiara. Currently, I am an academic visiting student at the Computer Vision Lab (CVL) of ETH Zürich, and under the supervision of Prof. Dr. Luc Van Gool.

My research interests lie in the intersection of computer vision, deep learning. Recently I work on low-level computer vision tasks and exploring the usage of the generative models.

Prior to my Ph.D. studies, I received my master's degree (2021) under the supvision of Prof. Hong Liu in computer applied technology at the School of Electronics and Computer Engineering, Peking University, China, and received my B.Eng. degree (2016) in the College of Mechanical and Electrical Engineering, Central South University, China.

News

2024/03: I joined INSAIT in Sofia as a research intern.
2024/02: We are organizing the NTIRE2024 Efficient Super-Resolution Challenge! Come and join via: https://cvlai.net/ntire/2024/!
2024/01: Our paper "A survey on 3d skeleton-based action recognition using learning method" has been accepted as oral by Cyborg and Bionic Systems (CBS) in 2024.
2023/11: Our paper "Modiff: Action-conditioned 3d motion generation with denoising diffusion probabilistic models" has been accepted as oral by ICASSP24 in 2023.
2023/08: Our paper "Spatio-Temporal Graph Diffusion for Text-Driven Human Motion Generation" has been accepted as oral by BMVC in 2023.
2023/08: Our paper "Cloth Interactive Transformer for Virtual Try-On" has been accepted by ACM ToMM in 2023.
2023/08: I joined the Computer Vision Lab (CVL) of ETH Zürich in Switzerland as a 6-month academic visiting Ph.D. Student.
2023/03: Our paper "Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers" has been accepted by CVPR2023.
2023/02: Our paper "PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation" has been accepted by ICASSP2023.
2022/10: Our paper "Deep Unsupervised Key Frame Extraction for Efficient Video Classification" has been accepted by TOMM in 2022.
2021/10: Our paper "Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation" has been accepted by BMVC2021 as oral.

Activities

2023/09: I will join the ELLIS Summer School on Large-Scale AI for Research and Industry, in Modena, Italy!
2022/07: I joined the ICVSS2022, in Sicily, Italy!
2022/07: I joined The first Italian National AI&Society Ph.D. Summer School, in Pisa, Italy.

Publications

Cloth Interactive Transformer for Virtual Try-On
Bin Ren, Hao Tang, Fanyang Meng, Runwei Ding, Philip Hs Torr, Nicu Sebe
Transactions on Multimedia Computing Communications and Applications (ACM ToMM), 2023
paper / code / bibtex

Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
Bin Ren, Yahui Liu, Yue Song, Wei Bi, Rita Cucchiara, Nicu Sebe, Wei Wang
Computer Vision and Pattern Recognition (CVPR), 2023
paper / code / bibtex

PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation
Bin Ren, Hao Tang, Yiming Wang, Xia Li, Wei Wang, Nicu Sebe
International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
paper / code / bibtex