kugatsu-sudo

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

SincNet

SincNet is a neural architecture for efficiently processing raw audio samples.

free-spoken-digit-dataset

A free audio dataset of spoken digits. An audio version of MNIST.

light-reid

[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x

leaf-audio

LEAF is a learnable alternative to audio features such as mel-filterbanks, that can be initialized as an approximation of mel-filterbanks, and then be trained for the task at hand, while using a very small number of parameters.

TDN

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Relation-Aware-Global-Attention-Networks

We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.

end2end-asr-pytorch

End-to-End Automatic Speech Recognition on PyTorch

PySNN

Efficient Spiking Neural Network framework, built on top of PyTorch for GPU acceleration

AlignPS

Code for CVPR 2021 paper: Anchor-Free Person Search

tdfbanks

Pytorch implementation of time-domain filterbanks

leaf-audio-pytorch

Pytorch port of Google Research's LEAF Audio paper

hypergraph_reid

Code for CVPR 2020 paper Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification

Image_Filter

Commonly used image filters. :earth_americas: 包罗常见的图像滤波器。

GCL

Implementation for CVPR2021 paper "Joint Generative and Contrastive Learning for Unsupervised Person Re-identification"

IIR-filter

An IIR filter class implementation in Python

ares

Ares: A framework for quantifying the resilience of deep neural networks

PytorchSR

Pytorch based phoneme recognition (TIMIT phoneme classification)

dcase2018_task1

spykesim

Extended edit similarity measurement for high dimensional discrete-time series signal (e.g., multi-unit spike-train).

snn-for-asr

Pytorch-Kaldi implementation of SNN-based ASR systems

dct-snn

Code for DCT_SNN, an input encoding scheme for SNNs using DCT

spikes

Code for spike coding networks

snn_speechrec

Convolutional Spiking Neural Network to recognize speech utterances using Spike-Timing-Dependent Plasticity

TIDIGITS_task

BandpassGeffesAlgorithm

Python program for bandpass filter design

DT2118-Deep-Learning-Project

leaf

PyTorch implementation of LEAF

SpeechSpeakerRecognition

Repository for course in Speech and Speaker Recognition lab tasks

DigitsSpeech

Speech recognition model for digits from 0 to 9.