All Projects → vra → Action Recognition Using 3d Resnet

vra / Action Recognition Using 3d Resnet

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Action Recognition Using 3d Resnet

I3d finetune
TensorFlow code for finetuning I3D model on UCF101.
Stars: ✭ 128 (+300%)
Mutual labels:  cnn, action-recognition
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+459.38%)
Mutual labels:  cnn, action-recognition
Video Classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+1596.88%)
Mutual labels:  cnn, action-recognition
Squeezenet v1.2
Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.
Stars: ✭ 23 (-28.12%)
Mutual labels:  cnn
Fast Shadow Detection
Fast Shadow Detection from a Single Image Using a Patched CNN
Stars: ✭ 24 (-25%)
Mutual labels:  cnn
Servenet
Service Classification based on Service Description
Stars: ✭ 21 (-34.37%)
Mutual labels:  cnn
Smsop
Code for Statistically-motivated Second-order Pooling, ECCV2018
Stars: ✭ 32 (+0%)
Mutual labels:  cnn
Cnn Fusion
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
Stars: ✭ 22 (-31.25%)
Mutual labels:  cnn
Kaggle Web Traffic Time Series Forecasting
Solution to Kaggle - Web Traffic Time Series Forecasting
Stars: ✭ 29 (-9.37%)
Mutual labels:  cnn
Neural Image Captioning
Implementation of Neural Image Captioning model using Keras with Theano backend
Stars: ✭ 12 (-62.5%)
Mutual labels:  cnn
Dcnv2
Deformable Convolutional Networks v2 with Pytorch
Stars: ✭ 868 (+2612.5%)
Mutual labels:  cnn
Cnnimageretrieval Pytorch
CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch
Stars: ✭ 931 (+2809.38%)
Mutual labels:  cnn
Mxnet Ir
Image Retrieval Experiment Using Triplet Loss
Stars: ✭ 27 (-15.62%)
Mutual labels:  cnn
Deepfakes video classification
Deepfakes Video classification via CNN, LSTM, C3D and triplets
Stars: ✭ 24 (-25%)
Mutual labels:  cnn
Qa Rankit
QA - Answer Selection (Rank candidate answers for a given question)
Stars: ✭ 30 (-6.25%)
Mutual labels:  cnn
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-28.12%)
Mutual labels:  cnn
Cnn Question Classification Keras
Chinese Question Classifier (Keras Implementation) on BQuLD
Stars: ✭ 28 (-12.5%)
Mutual labels:  cnn
Attention Ocr
A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.
Stars: ✭ 844 (+2537.5%)
Mutual labels:  cnn
Flownet2
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 938 (+2831.25%)
Mutual labels:  cnn
Video Classification 3d Cnn Pytorch
Video classification tools using 3D ResNet
Stars: ✭ 874 (+2631.25%)
Mutual labels:  action-recognition

action-recognition-using-3d-resnet

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

how to use

  1. Clone this repo:
   git clone https://github.com/vra/action-recognition-using-3d-resnet.git
  1. Download 3D ResNet

  2. Download its pretrained models, put these models to this repo's data/models/

  3. run the script under scripts under to extract 3D resnet features of UCF101 and HMDB51:

   bash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch ucf101 /path/to/ucf101/videos 
   bash scripts/extract_resnet_3d_features.sh /path/to/video-classification/3d-cnn-pytorch hmdb51 /path/to/hmdb51/videos 

Also, you can download my extracted features of ucf101 and hmdb51 at here and here. Remember to put the first one to data/jsons/ucf101 before you download the second one, otherwise the first one will be convered.

  1. Run main.py to classify extracted 3D resnet features:
   python main.py -dataset hmdb51

Results:

strategy dataset accuracy
mean ucf101 0.8487
max ucf101 0.8667
mean hmdb51 0.5425
max hmdb51 0.5399
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].