axon-research / c3d-keras
C3D for Keras + TensorFlow
☆176Updated 7 years ago
Related projects: ⓘ
- Video Classification using 2 stream CNN☆310Updated 5 years ago
- Segment-CNN: A Framework for Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs☆235Updated 5 years ago
- train C3D with keras for action recognition☆119Updated 5 years ago
- Dynamic Image Networks for Action Recognition☆181Updated 6 years ago
- some famous works and new content to be added☆147Updated 7 years ago
- Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"☆196Updated 6 years ago
- ActionVLAD for video action classification (CVPR 2017)☆216Updated 5 years ago
- Tools to participate in the ActivityNet Challenge 2016 (NIPSW 2016)☆195Updated 6 years ago
- TensorFlow code for finetuning I3D model on UCF101.☆144Updated 6 years ago
- Temporal Segments LSTM and Temporal-Inception for Activity Recognition☆439Updated 4 years ago
- Action Recognition Toolbox for CUHKÐZ&SIAT submission to ActivityNet 2016☆253Updated 5 years ago
- Classify UCF101 videos using one frame at a time with a CNN(InceptionV3)☆196Updated 3 years ago
- keras implementation of inflated 3d from Quo Vardis paper + weights☆136Updated 6 years ago
- Code/Model release for NIPS 2017 paper "Attentional Pooling for Action Recognition"☆258Updated 6 years ago
- Pseudo-3D Convolutional Residual Networks for Video Representation Learning☆352Updated 5 years ago
- Tools to extract dense optical flow from videos, based on OpenCV☆246Updated 3 years ago
- Code release for "Spatiotemporal Residual Networks for Video Action Recognition", NIPS16 & "Spatiotemporal Multiplier Networks for Video …☆179Updated 7 years ago
- code for R-C3D☆254Updated 4 years ago
- Action recognition using soft attention based deep recurrent neural networks☆350Updated 7 years ago
- Two-stream CNNs for video action recognition implemented in Keras☆121Updated 5 years ago
- temporal action detection with SSN☆641Updated 5 years ago
- Appearance-and-Relation Networks☆204Updated 5 years ago
- C3D is a modified version of BVLC tensorflow to support 3D ConvNets.☆587Updated 5 years ago
- Extract TVL1 optical flows in python (multi-process && multi-server)☆192Updated 6 years ago
- A one stop shop for all of your activity recognition needs.☆107Updated 5 years ago
- Codes for popular action recognition models, verified on the something-something data set.☆244Updated 5 years ago
- Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an exampl…☆175Updated 5 years ago
- ☆253Updated 5 years ago
- GPU based optical flow extraction in OpenCV☆430Updated 4 years ago
- 3D Convolutional Networks☆15Updated 6 years ago