CZHQuality

pytudes

Python programs, usually short, of considerable difficulty, to perfect particular skills.

vit-pytorch

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

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

ann-benchmarks

Benchmarks of approximate nearest neighbor libraries in Python

cnn-benchmarks

Benchmarks for popular CNN models

doing_the_PhD

Video-Swin-Transformer

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

dtw

DTW (Dynamic Time Warping) python module

DiskANN

Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search

Random-Erasing

Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST

nsg

Navigating Spreading-out Graph For Approximate Nearest Neighbor Search

Patch-NetVLAD

Code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition"

weixin-knife

weixin python framework

videosearch

Large-scale video retrieval using image queries.

VideoAudit

:video_camera: 一个短视频APP视频内容安全审核的思路调研及实现汇总

CenseoQoE

image and video quality assessment

VCSL

Video Copy Segment Localization (VCSL) dataset and benchmark [CVPR2022]

GCC

Graph Contrastive Clustering (ICCV2021)

search-video-demo

S2-BNN

S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

openBCT

Pytorch code for Towards Backward-Compatible Representation Learning [CVPR 2020 Oral]

pytorch_onnx_openvino

Validation of the PyTorch -> ONNX -> Intel OpenVino workflow using pretrained ResNet-50

HANet

PyTorch implementation of HANet: Hierarchical Alignment Networks for Video-Text Retrieval (ACM MM 2021).

Sal-CFS-GAN

TIP2019-GazeGAN Saliency Model

dtw

Simple speech recognition using dynamic time warping with examples

find-audio

Dynamic time warping for audio matching and alignment

NR-3DQA

Point cloud version for "No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh models".

FVV_QoE

Official Implementation of "Subjective and Objective Quality of Experiment of Free Viewpoint Videos"

ImageRetrieval_DF_CDVS

scoregraph

These python scripts analyze music score metadata in XML format into a semantically enriched knowledge graph.