Simple, fast, and fair evaluation of remote physiological sensing models

Task 1 Research and Development Project : Development of a new rPPG method (3DCNN) to be integrated into the pyVHR framework

State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.

Pytorch implementation of anomaly prediction.

Compositional Video Prediction (ICCV19)

Papers for Video Anomaly Detection, released codes collection, Performance Comparision.

Pytorch Re-implement of ano_pre_cvpr2018, flownet2 / lite-flownet used.

Anomaly detection in the surveillance videos under varying visibility (day-night and sunny-rainy)

unofficial implementation of paper Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder (MemAE) for Unsupervised Anomaly Detection

MemAE for anomaly detection. -- Gong, Dong, et al. "Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection". ICCV 2019.

An official implementation of "Learning Memory-guided Normality for Anomaly Detection" (CVPR 2020) in PyTorch.

Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events. Oral paper in ACM Multimedia 2020.

Code for estimating social distances from RGB cameras.

Structured learning for social group detection in crowds

Comparing Different Clustering Methods and Similarity Metrics on Trajectory Datasets

This application written in Python is capable of fully automatic clustering of 2D trajectory data.

Joint Detection and Embedding for fast multi-object tracking

Main use to store some object trackiing code

Kanade–Lucas–Tomasi (KLT) feature tracker (MATLAB)

The official PyTorch implementation of CVPR 2020 paper "Improving Convolutional Networks with Self-Calibrated Convolutions"

CVPR 2019 Paper - Learning Actor Relation Graphs for Group Activity Recognition

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking

OpenCV问答群不再维护。有问题，自己去搜索。Google能找到大部分答案。

RGBD crowd counting

Reproduce AlignedReID: Surpassing Human-Level Performance in Person Re-Identification, using Pytorch.

Single Shot Tracker

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020

code of Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations (CVPR2020 oral)