xujinglin Goto Github PK

unsup_temp_embed

Official implementation of the paper: Unsupervised learning of action classes with continuous temporal embedding (CVPR'19)

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2020

uvc

Joint-task Self-supervised Learning for Temporal Correspondence (NeurIPS 2019)

vae

a simple vae and cvae from keras

vatic

An extension to original vatic tools for human action labeling. vatic is an online, interactive video annotation tool for computer vision research that crowdsources work to Amazon's Mechanical Turk. Our tool makes it easy to build massive, affordable video data sets. Written in Python + C + Javascript, vatic is free and open-source software.

vcca-studynotes

Canonical Correlation Analysis, Variational CCA

vcl

ECCV2020: Visual Compositional Learning for Human-Object Interaction Detection

vedatad

A single stage temporal action detection toolbox based on PyTorch

video-nonlocal-net

Non-local Neural Networks for Video Classification

video-person-reid

Video-based Person ReID Method Implementations on MARS

video-swin-transformer

This is an official implementation for "Video Swin Transformers".

video_repres_sts

Pytorch implementation of Self-supervised Video Representation Learning by Uncovering Motion and Appearance Statistics

videoalignment

Learning to align and match videos with kernelized temporal layers

videogpt

vie

Codes for "Unsupervised Learning from Video with Deep Neural Embeddings"

vision

Datasets, Transforms and Models specific to Computer Vision

vision_transformer

vistr

[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

voxelhashing

[Siggraph Asia 2013] Large-Scale, Real-Time 3D Reconstruction

wb_color_augmenter

Emulating white balance effects for color augmentation

weakalign

End-to-end weakly-supervised semantic alignment

wislar

code of Temporal Unet

wsad

Weakly Supervised Temporal Action Localization Using Deep Metric Learning

wtalc-pytorch

W-TALC: Weakly-supervised Temporal Activity Localization and Classification

xujinglin.github.io

you-get

:arrow_double_down: Dumb downloader that scrapes the web

yowo

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

ytse

YouTube subscribe extension