|
Zhuo Li
I am currently a researcher at WeChat Tencent . Prior to this, I received my Master's degree from Institute of Computing Technology, Chinese Academy of Science, and Bachelor's degree in Computer Science from Northwestern Polytechnical University.
I'm interested in computer vision, machine learning, and optimization. Recently, I focus on the intersection of vision, learning, and robotics, especially 3D Human Pose Estimation, Human Motion Generation and Virtual Humans.
Email /
LinkedIn /
Github
|
|
|
|
M³GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Mingshuang Luo,
Ruibing Hou ,
Zhuo Li,
Hong Chang,
Zimo Liu,
Yaowei Wang,
Shiguang Shan
NIPS, 2024
Code /
arXiv
M³GPT — an advanced Multimodal, Multitask framework for Motion comprehension and generation.
|
|
|
Rethinking the Optimization of Average Precision:
Only Penalizing Negative Instances before Positive Ones is Enough
Zhuo Li,
Weiqing Min,
Jiajun Song,
Yaohui Zhu,
Liping Kang,
Xiaoming Wei,
Xiaolin Wei,
Shuqiang Jiang
AAAI, 2022
Code /
arXiv
PNP Loss — a simple, effective and generalization-friendly loss function for image retrieval. The method was used in Meituan app for food image retrieval.
|
|
|
Towards food image retrieval via generalization-oriented sampling and loss function design
Jiajun Song* ,
Zhuo Li* ,
Weiqing Min,
Shuqiang Jiang
ToMM, 2023
Code /
arXiv
The method was used in Meituan for food image retrieval.
|
|
|
A Two-Stage Triplet Network Training Framework for Image Retrieval.
Weiqing Min,
Shuhuan Mei,
Zhuo Li,
Shuqiang Jiang
TMM, 2020
Code /
arXiv
|
|
|
LargeFineFoodAI:Large-Scale Fine-Grained Food Analysis
Website
LargeFineFoodAI — a worshop of large-scale fine-grained food analysis on ICCV 2021, including invited talks, presentation from accepted papers and a competition on large-scale food image recognition and retrieval.
|
|
|
Does deep stereo matching network really learn matching? A Rethinking.
Zhelun Shen,
Zhuo Li,
Yuchao Dai
Code /
arXiv /
Video
A rethinking of deep stereo matching network. Entropy Regulization and Offset Data Augmentation for deep stereo matching. The method won the Championship in Argoverse Stereo Competition on CVPR2021.
|
|
