suki7

a-new-scale-aware-loss-

inspared by 《Scale-Aware Trident Networks for Object Detection》

simpledet

A Simple and Versatile Framework for Object Detection and Instance Recognition

BaSNet-pytorch

Official Pytorch Implementation of 'Background Suppression Network for Weakly-supervised Temporal Action Localization' (AAAI-20 Spotlight)

PAGE-Net

Salient Object Detection with Pyramid Attention and Salient Edges (CVPR19)

semseg

Semantic Segmentation in Pytorch

Grad-CAM

:rainbow: :camera: Gradient-weighted Class Activation Mapping (Grad-CAM) Demo

GCT

Gated Channel Transformation for Visual Recognition (CVPR 2020)

TIN

[AAAI 2020] Temporal Interlacing Network

AR-Net

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

ECANet

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

VSGNet

VSGNet:Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions.

Probabilistic3DCNN

Spatiotemporal Fusion in 3D CNNs: A Probabilistic View

Action_Recognition_Zoo

Codes for popular action recognition models, verified on the something-something data set.

awesome-action-recognition

A curated list of action recognition and related area resources

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

glore

Global Reasoning unit (GloRe)

OctaveConv.pytorch

A Pytorch Implementation for Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

octaveconv-pytorch

Implementation of Octave Convolution from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution in Pytorch (https://arxiv.org/abs/1904.05049)

pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

ECCV2024-Papers-with-Code

ECCV 2024 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2024论文和开源项目

SmallBigNet

SmallBigNet: Integrating Core and Contextual Views for Video Classification (CVPR2020)

SAN

Exploring Self-attention for Image Recognition, CVPR2020.

PARL

A high-performance distributed training framework for Reinforcement Learning

CVPR2019-Code

CVPR 2019 Paper with Code

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

SATA

SATA: Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network

decord

An efficient video loader for deep learning with smart shuffling that's super easy to digest

timeception

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

video-long-term-feature-banks

Long-Term Feature Banks for Detailed Video Understanding