515 Open source projects that are alternatives of or similar to Action Recognition Using 3d Resnet

TensorFlow code for finetuning I3D model on UCF101.

Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

in progress

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

Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.

Implementation of Neural Image Captioning model using Keras with Theano backend

a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

Cache design for CNN on mobile

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)

Fast Shadow Detection from a Single Image Using a Patched CNN

TensorFlow and Deep Learning Tutorials

Service Classification based on Service Description

Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别

采用CNN将高分辨率灰度图像和低分辨率彩色图像合成为高分辨率彩色图像的图像融合算法

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Solution to Kaggle - Web Traffic Time Series Forecasting

Implementation of papers for text classification task on DBpedia

Temporal Segment Networks (TSN) in PyTorch

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

temporal action detection with SSN

Some interesting TensorFlow tutorials for beginners.

Keras implementation of yolo v3 object detection.

Visualization toolkit for neural networks in PyTorch! Demo -->

Implementation of Quickdraw - an online game developed by Google

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

CNN visualization tool in TensorFlow

Image Retrieval Experiment Using Triplet Loss

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

Deepfakes Video classification via CNN, LSTM, C3D and triplets

A deep neural network based self-driving car, that combines Lego Mindstorms NXT with the computational power of a Raspberry Pi 3.

QA - Answer Selection (Rank candidate answers for a given question)

Hide screen when boss is approaching.

🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis

Code for Tensorflow Machine Learning Cookbook

Video classification tools using 3D ResNet

Medical image preprocessing and augmentation toolkit for deep learning

Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Network复现

Network estimating 3D Handpose from single color images

Code for Statistically-motivated Second-order Pooling, ECCV2018

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Data augmentation for NLP, presented at EMNLP 2019

Implementation of Prototypical Networks for Few Shot Learning (https://arxiv.org/abs/1703.05175) in Pytorch

Deformable Convolutional Networks v2 with Pytorch

Exercise notebooks for CVND.

Hierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)

🌅The code of post "Image retrieval using MatconvNet and pre-trained imageNet"

Chinese Question Classifier (Keras Implementation) on BQuLD

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

A high performance anime upscaler

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]

Discriminative Unsupervised Feature Learning with Convolutional Neural Networks

Code for the AAAI 2018 publication "SEE: Towards Semi-Supervised End-to-End Scene Text Recognition"

A top-down, practical guide to learn AI, Deep learning and Machine Learning.

Action recognition.基于C3D的视频动作识别

OpenCV 3 & Keras implementation of face recognition for specific people.

使用Theano实现的一些RNN代码，包括最基本的RNN，LSTM，以及部分Attention模型，如论文MLSTM等