bhaktipriya / Dense-Optical-Flow-Prediction
Deep learning mechanism to predict the dense optical flow of every pixel given a static image. This approach considers non-semantic form of action prediction that makes it domain independent and makes no assumptions of the underlying scene.
☆14Updated 8 years ago
Alternatives and similar repositories for Dense-Optical-Flow-Prediction:
Users that are interested in Dense-Optical-Flow-Prediction are comparing it to the libraries listed below
- Actionness Estimation Using Hybrid Fully Convolutional Networks☆30Updated 8 years ago
- ☆22Updated 8 years ago
- Code and models of paper " Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection"…☆27Updated 6 years ago
- This repository is intended to host tools and demos for ActivityNet☆21Updated 8 years ago
- Code for "Predictive-Corrective Networks for Action Detection"☆16Updated 7 years ago
- TensorFlow implementation for "Guided Optical Flow Learning"☆25Updated 7 years ago
- Temporal action proposals☆47Updated 5 years ago
- P-CNN: Pose-based CNN Features for Action Recognition☆52Updated 7 years ago
- experiments on classifying actions using poses☆26Updated 6 years ago
- Im2Flow: Motion Hallucination from Static Images for Action Recognition (CVPR 2018)☆54Updated 6 years ago
- Disentangling Motion, Foreground and Background Features in Videos☆26Updated 7 years ago
- ☆20Updated 7 years ago
- Action localization Proposals from dense Trajectories☆21Updated 9 years ago
- Torch implementation of Fischer et al. FlowNet training code☆31Updated 8 years ago
- ☆22Updated 8 years ago
- A two-stream convolutional neural network for learning abitrary similarity functions over two sets of training data☆24Updated 7 years ago
- Real-time smart webcam in TensorFlow trained on the Charades dataset☆15Updated 7 years ago
- This is a script which tests the speed of multiple optical flow extraction methods. support both single-thread and multi-thread☆23Updated 6 years ago
- Multi-object tracker using structured graphs, as proposed in the CVIU paper☆10Updated 6 years ago
- Code for CVPR 2016 paper "First Person Action Recognition Using Deep Learned Descriptors"☆26Updated 10 months ago
- The source code for our CVPR 2016 work "Slicing Convolutional Neural Network for Crowd Video Understanding".☆47Updated 8 years ago
- Caffe implementation for Hu et al. Segmentation for Natural Language Expressions in arXiv:1603.06180, 2016 http://ronghanghu.com/text_obj…☆9Updated 8 years ago
- Optical flow extraction tool using OpenCV☆16Updated 8 years ago
- This is a reimplementation of 3D CNN (http://vlg.cs.dartmouth.edu/c3d/). It is compatitable with Caffe 2016. The Caffe is forked from Caf…☆9Updated 8 years ago
- Interpolate and extrapolate video frames using cGAN☆37Updated 8 years ago
- Pre-trained models for our CVPR 2016 paper: "Learning Local Image Descriptors With Deep Siamese and Triplet Convolutional Networks by Min…☆34Updated 8 years ago
- Pytorch code for "Foreground Segmentation for Anomaly Detection in Surveillance Videos Using Deep Residual Networks" (SBRT 2017)☆32Updated 6 years ago
- code for Two-Stream SR-CNNs for Action Recognition in Videos 2016☆34Updated 6 years ago
- ☆20Updated 6 years ago
- This is my attempt at the ActivityNet Challenge 2017. Thanks to the organizers for providing the boilerplate code and annotated datasets.…☆10Updated 7 years ago