Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

OpenTLD is an open source library for real-time 2D tracking of a single object in video. This repository is no longer under development. For latest version see: http://www.tldvision.com/tld2.html

Class Activation Mapping

This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vi…

Tiny Face Detector, CVPR 2017

Piotr's Image & Video Matlab Toolbox

Low-Rank and Sparse Tools for Background Modeling and Subtraction in Videos

Original Caffe Version for LightCNN-9. Highly recommend to use PyTorch Version (https://github.com/AlfredXiangWu/LightCNN)

Arbitrary object tracking at 50-100 FPS with Fully Convolutional Siamese networks.

Various hashing methods for image retrieval and serves as the baselines

Single Image Super-Resolution from Transformed Self-Exemplars (CVPR 2015)

Object detection system using deformable part models (DPMs) and latent SVM (voc-release5). You may want to use the latest tarball on my website. The github code may include code changes that have n…

Code release for "Detect to Track and Track to Detect", ICCV 2017

NetVLAD: CNN architecture for weakly supervised place recognition

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution (CVPR 2017)

Learning to Track: Online Multi-Object Tracking by Decision Making

NormFace: L2 HyperSphere Embedding for Face Verification, 99.21% on LFW

SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Main repository for Deep Metric Learning via Lifted Structured Feature Embedding

Face alignment in 3000 FPS

MatConvNet implementation for incorporating a 3D Morphable Model (3DMM) into a Spatial Transformer Network (STN)

Semi-parametric Image Synthesis

Code and data for the research paper "A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement" (Submitted to IEEE Transactions on Cybernetics)

[CVPR'16] Staple: Complementary Learners for Real-Time Tracking"

Code and some data for 'Recurrent Scale Approximation for Object Detection in CNN' in ICCV 2017

Multi Person Pose Estimation

Code for Context-aware CNNs for person head detection

Hierarchical Convolutional Features for Visual Tracking (ICCV 2015)

Implement for ``Learning Deep Features via Congenerous Cosine Loss for Person Recognition''

Full version (training+testing) of implementation of Shizhan Zhu et al.'s CVPR-15 work Face Alignment by Coarse-to-Fine Shape Searching