A S M Iftekhar's repositories
Awesome-Learning-with-Label-Noise
A curated list of resources for Learning with Noisy Labels
Awesome-Video-Datasets
Video datasets
Bongard-HOI
[CVPR 2022 (oral)] Bongard-HOI for benchmarking few-shot visual reasoning
DeepCEP_DAIS
Implementation of DeepCEP for DAIS paper
HAKE-Action-Torch
HAKE-Action in PyTorch
HOI-Learning-List
A list of the Human-Object Interaction Learning studies.
large_vocabulary_hoi_detection
Code for ICCV2021: Discovering Human Interactions with Large-Vocabulary Objects via Query and Multi-Scale Detection
MethaneMapper-Spectral-Absorption-aware-Hyperspectral-Transformer-for-Methane-Detection
MethaneMapper: Spectral Absorption aware Hyperspectral Transformer for Methane Detection
PlotNeuralNet
Latex code for making neural networks diagrams
polyloss-pytorch
Implementing PolyLoss in Pytorch
pytorch-estimate-flops
Estimate/count FLOPS for a given neural network using pytorch
spatio-attentive-graphs
Official PyTorch implementation for our paper "Spatio-attentive Graphs for Human-Object Interaction Detection"
Squeeze-and-Recursion-Temporal-Gates
Code for : [Pattern Recognit. Lett. 2020] "Learn to cycle: Time-consistent feature discovery for action recognition" and [arXiv] "Right on Time: Multi-Temporal Convolutions for Human Action Recognition in Videos".
StressNet-Detecting-stress-from-thermal-videos
StressNet: Detecting Stress in Thermal Videos
suncet
Code to reproduce the results in the FAIR research papers "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples" https://arxiv.org/abs/2104.13963 and "Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations" https://arxiv.org/abs/2006.10803
SupContrast
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
trackformer
Implementation of "TrackFormer: Multi-Object Tracking with Transformers”. [Conference on Computer Vision and Pattern Recognition (CVPR), 2022]
Video-Action-Transformer-Network-Pytorch-
Implementation of the paper Video Action Transformer Network
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch