liviust Goto Github PK

trecvid_code

trn-pytorch

Temporal Relation Networks

tsfresh

Automatic extraction of relevant features from time series:

twostreamfusion

Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.

udastrongbaseline

Open-source stronger baseline for unsupervised or domain adaptive object re-ID.

unit

unitrack

[NeurIPS'21] Unified tracking framework with a single appearance model. It supports Single Object Tracking (SOT), Video Object Segmentation (VOS), Multi-Object Tracking (MOT), Multi-Object Tracking and Segmentation (MOTS), Pose Tracking, Video Instance Segmentation (VIS), and class-agnostic MOT (e.g. TAO dataset).

universe

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

unsupervised-image-retrieval

Unsupervised image retrieval on MNIST dataset using a convolutional autoencoder

vector-quantize-pytorch

Vector Quantization, in Pytorch

vehicle-detection

Detect vehicles in a video

vggfacematching

vggfeatextract

Python wrapper to extract CNN embeddings with Oxford VGG models using caffe.

vid2speech

Code for "Vid2speech: Speech Reconstruction from Silent Video" ICASSP '17

video-caffe

Video-friendly caffe -- comes with a recent version of Caffe (Dec 2016), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data

video-caption.pytorch

pytorch implementation of video captioning

videoavatars

This repository contains code corresponding to the paper Video based reconstruction of 3D people models.

videosearch

Large-scale video retrieval using image queries.

vilt

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

virtual-fully-connected-layer

visdom

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

visible-thermal-person-re-identification

Demo code for visible thermal (cross-modality) person re-identification

visionio

Boilerplate template for a web-based computer vision demo / application with image uploader, various visualization tools, etc.

vistasoft

VISTASOFT is the main software repository of the VISTA lab at Stanford University.

visual-feature-attribution-using-wasserstein-gans-pytorch

Implementation of Visual Feature Attribution using Wasserstein GANs (https://arxiv.org/abs/1711.08998) in PyTorch

vitaa

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

vqa-winner-cvprw-2017

Pytorch Implementation of winner from VQA Chllange Workshop in CVPR'17

warp-ctc

Fast parallel CTC.

wassersteingan-pytorch

This is a new alogorithm named WGAN, an alternative to traditional GAN training!

web-dictaphone

A sample MDN app that uses getUserMedia and MediaRecorder API for recording audio snippets, and The Web Audio API for visualizations.