Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).

Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR18, PAMI19)

[CVPR2023 Highlight] Marching-Primitives: Shape Abstraction from Signed Distance Function

Code for CVPR 2019 paper "Deep Metric Learning to Rank"

Code for CVPR 2018 paper "Hashing as Tie-Aware Learning to Rank"

Code for "Variational Autoencoders for Deforming 3D Mesh Models", CVPR 2018

An efficient and robust probabilistic approach for fitting superellipse to point clouds.

2018 Spring Course, Computer Vision and Pattern Recognition, in XJTU

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

Cartesian k-means for Approximate nearest neighbor search, codebook learning, etc.