R2D2oid

Multimodal-Action-Recognition

Multimodal action recognition using autoencoders

OOD-Sentence-Detection

Detects out-of-domain (OOD) sentences

Video-Text-Retrieval_OOD

wslogs_topicmodeling

network anomaly detection using topic models

noisy_ssl

Studying the behaviour of SSL objectives in presence of noise

ssl_benchmarks

Tempuckey-Dataset

text2feat

extracts feature embeddings for text input

VideoFeatExtractor

Video feature extraction for video analysis tasks

Adhoc-Visualizations

A collection of adhoc scripts mainly in python and latex for visualization of various concepts.

deepsbd

This is a package to do shot boundary detection on videos.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

github-do-not-ban-us

GitHub do not ban us from open source world :iran:

howto100m

Code for the HowTo100M paper

IFT6135H19_Assignments

IFT6135H19 Assigments

lightly

A python library for self-supervised learning on images.

MIL-NCE_HowTo100M

PyTorch GPU distributed training code for MIL-NCE HowTo100M

noisy_barlowtwins

PyTorch implementation of Barlow Twins.

noisy_moco

r2d2oid.github.io

RNN-Climate-Time-series

S3D_HowTo100M

S3D Text-Video model trained on HowTo100M using MIL-NCE

scikit-learn

scikit-learn: machine learning in Python

slowfast_feature_extractor

Feature Extractor module for videos using the PySlowFast framework

video2frame

Yet another easy-to-use tool to extract frames from videos, for deep learning and computer vision.

video2frames

video_feature_extractor

Easy to use video deep features extractor