wanglimin / Tdd
Trajectory-pooled Deep-Convolutional Descriptors
Stars: ✭ 99
Programming Languages
matlab
3953 projects
Labels
Projects that are alternatives of or similar to Tdd
theWorldInSafety
Surveillance System Against Violence
Stars: ✭ 31 (-68.69%)
Mutual labels: caffe, action-recognition
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+80.81%)
Mutual labels: caffe, action-recognition
Video Caffe
Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
Stars: ✭ 172 (+73.74%)
Mutual labels: caffe, action-recognition
Training toolbox caffe
Training Toolbox for Caffe
Stars: ✭ 51 (-48.48%)
Mutual labels: caffe, action-recognition
Video classification pytorch
Video Classification based on PyTorch
Stars: ✭ 89 (-10.1%)
Mutual labels: action-recognition
Caffe Tools
Some tools and examples for pyCaffe including LMDB I/O, custom Python layers and monitoring training error and loss.
Stars: ✭ 78 (-21.21%)
Mutual labels: caffe
Mobilenet V2 Caffe
MobileNet-v2 experimental network description for caffe
Stars: ✭ 93 (-6.06%)
Mutual labels: caffe
Caffe Model
Caffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+1170.71%)
Mutual labels: caffe
Vidvrd Helper
To keep updates with VRU Grand Challenge, please use https://github.com/NExTplusplus/VidVRD-helper
Stars: ✭ 81 (-18.18%)
Mutual labels: action-recognition
Temporal Segment Networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
Stars: ✭ 1,287 (+1200%)
Mutual labels: action-recognition
Mobilenet Caffe
Caffe Implementation of Google's MobileNets (v1 and v2)
Stars: ✭ 1,217 (+1129.29%)
Mutual labels: caffe
Dispnet Flownet Docker
Dockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Stars: ✭ 78 (-21.21%)
Mutual labels: caffe
Mobilenet Ssd
MobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) Faster than YoloV2 + Explosion speed by RaspberryPi · Multiple moving object detection with high accuracy.
Stars: ✭ 84 (-15.15%)
Mutual labels: caffe
Video Dataset Loading Pytorch
Generic PyTorch Dataset Implementation for Loading, Preprocessing and Augmenting Video Datasets
Stars: ✭ 92 (-7.07%)
Mutual labels: action-recognition
Onnx Chainer
Add-on package for ONNX format support in Chainer
Stars: ✭ 83 (-16.16%)
Mutual labels: caffe
Trajectory-Pooled Deep-Convolutional Descriptors
Here we provide the code for the extraction of Trajectory-Pooled Deep-Convolutional Descriptors (TDD), from the following paper:
Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
Limin Wang, Yu Qiao, and Xiaou Tang, in CVPR, 2015
Updates
- Dec 24, 2015
- Release the second version of TDD (branch: cudnn2.0) compatible with latest caffe toolbox. Due to speedup brought by cudnn2.0 or above, TDD extraction is becoming more efficient.
- Jul 21, 2015
- Release the first version TDD (branch: master) compatible with an older version of caffe toolbox.
Two-stream CNN models trained on the UCF101 dataset
First, we provide our trained two-stream CNN models on the split1 of UCF101 dataset, which achieve the recognition accuracy of 84.7%
"Spatial net model (v1)" "Spatial net prototxt (v1)" "Temporal net model (v1)" "Temporal net prototxt (v1)"
TDD demo code
Here, a matlab demo code for TDD extraction is provided.
- Step 1: Improved Trajectory Extraction You need download our modified iDT feature code and compile it by yourself. Improved Trajectories
- Step 2: TVL1 Optical Flow Extraction You need download our dense flow code and compile it by yourself. Dense Flow
- Step 3: Matcaffe You need download the public caffe toolbox. Our TDD code is compatatible with the latest version of parallel caffe toolbox. Note that you need to download the models in the new proto format: "Spatial net model (v2)" "Temporal net model (v2)"
- Step 4: TDD Extraction Now you can run the matlab file "script_demo.m" to extract TDD features.
Questions
Contact
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].