JunweiLiang

Junwei Liang's repositories

awesome_lists

Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

Language:PythonMIT1476 33 1

Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20

Language:PythonMIT494 19 48

Multiverse

Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction". And for the ECCV'20 SimAug paper.

Language:PythonApache-2.0253 10 45

social-distancing-prediction

Out-of-the-box code and models for social distancing early forecasting.

Language:PythonApache-2.042 5 19

FVTA_MemexQA

Real-world photo sequence question answering system (MemexQA). CVPR'18 and TPAMI'19

Language:PythonMIT33 3 2

VERA_Shooter_Localization

Code and model for the Video Event Reconstruction and Analysis (VERA) system. ACM Multimedia.

Language:PHPApache-2.031 80

aicity_action

Code and model for the AI City Challenge (CVPR 2022) Track 3 Action Detection (Naturalistic Driving Action Recognition)

Language:Python28 3 4

DualAttentionNetwork

This repository contains the tensorflow implementation and models for DAN - CVPR 2017 paper

Language:Python22 2 2

MultiTrain

Code and model for "Multi-dataset Training of Transformers for Robust Action Recognition", NeurIPS 2022 Spotlight

Language:PythonMIT19 6 3

junweiliang.github.io

My academic personal page. Written in plain html with bootstrap.css

Language:HTML17 20

next-prediction

Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

Language:PythonApache-2.017 40

VERA_3D_Reconstruction

Code and model for the Video Event Reconstruction and Analysis (VERA) system. This repo is for the 3D event reconstruction part.

Language:JavaScriptApache-2.012 40

ForkingPaths

Dataset from the paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction"

9 40

about

My academic personal page. Written in plain html with jQuery.js and bootstrap.css

Language:HTML7 20

Lecture_Attendance_Management

A simple, efficient, mobile-usable web application for lecture attendance management.

Language:PHPApache-2.06 30

Semantic_Features

Given a list of videos, output the semantic features for each video.

Language:Python3 10

Awesome-Trajectory-Prediction

2 20

awesome-visual-question-answering

A curated list of Visual Question Answering(VQA)(Image/Video Question Answering),Visual Question Generation ,Visual Dialog ,Visual Commonsense Reasoning and related area.

2 20