Tanyjiang

EOCO

We develop a unified object counting framework as the first attempt to implement a class-incremental object counting task. Additionally, we introduce a new dataset, EoCo, that includes multiple object classes.

awesome-radar-perception

A curated list of radar datasets, detection, tracking and fusion

3D-ResNets-PyTorch

3D ResNets for Action Recognition (CVPR 2018)

action-detection

temporal action detection with SSN

Artistic-Video-Partial-Conv-Depth-Loss

This is pytorch implementation of paper Stable Video Style Transfer Based on Partial Convolution with Depth-Aware Supervision.

arxiv-sanity-preserver

Web interface for browsing, search and filtering recent arxiv submissions

Awesome-Incremental-Learning

Awesome Incremental Learning

CamStyle

Camera Style Adaptation for Person Re-identification CVPR 2018

CCNet

CCNet: Criss-Cross Attention for Semantic Segmentation

CF-former

DeepSOCIAL

Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic and Beyond

Graph_Convolutional_LSTM

Traffic Graph Convolutional Recurrent Neural Network

kinetics_i3d_pytorch

Inflated i3d network with inception backbone, weights transfered from tensorflow

ExdNet

models

Models and examples built with TensorFlow

Multi-Camera-Live-Object-Tracking

Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.

pytorch-i3d

Research

Aerospace engineering research in Matlab

simple-distance-measure-by-camera

基于地面假设的单目测距，核心代码文件

StInNet

STTN

paper : <Spatial-Temporal Transformer Networks for Traffic Flow Forecasting>

two-stream-pytorch

PyTorch implementation of two-stream networks for video action recognition

video_CIL

WeSamBE

Yolov5_Tensorrt_Win10

A simple implementation of tensorrt yolov5 python/c++🔥

Zero_shot_action_reco_STGCN

Zero shot action recognition using spatial temporal graph convolutional networks

ZeroShotVideoClassification

Zero-shot video classification by end-to-end training of 3D convolutional neural networks