Weakly Supervised Action Recognition and Detection
Matlab Shell M
Switch branches/tags
Nothing to show
Clone or download
Latest commit 09cd15c Sep 28, 2017
Permalink
Failed to load latest commit information.
data add thumos shot files Sep 28, 2017
matlab add detection code Aug 24, 2017
models add temporal stream Sep 14, 2017
scripts add reference model Sep 19, 2017
thumos_proto add thumos deploy proto Sep 27, 2017
README.md Update README.md Sep 19, 2017

README.md

UntrimmedNet for Action Recognition and Detection

We provide the code and models for our CVPR paper (Arxiv Preprint):

  UntrimmedNets for Weakly Supervised Action Recognition and Detection
  Limin Wang, Yuanjun Xiong, Dahua Lin, and Luc Van Gool
  in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Updates

  • September 19th, 2017
    • Release the learned models on the THUMOS14 and ActivityNet1.2 datasets.
  • August 20th, 2017
    • Release the model protos.

Guide

The training of UntrimmedNet is composed of three steps:

  • Step 1: extract action proposals (or shot boundaries) for each untrimmed video. We provide a sample of detected shot boudary on the ActivityNet (v1.2) under the folders of data/anet1.2/anet_1.2_train_window_shot/ and data/anet1.2/anet1.2/anet_1.2_val_window_shot/.
  • Step 2: construct file lists for training and validation. There are two filelists: one containing file path, number of frames, and label; the other one containing the shot file path and number of frames (Examples are in the folder data/anet1.2/).
  • Step 3: train UntrimmedNets using our modified caffe: https://github.com/yjxiong/caffe/tree/untrimmednet

The testing of UntrimmedNet for action recognition is based on temporal sliding window and top-k pooling

The testing of UntrimmedNet for action detection is based on a simple baseline (see code in matlab/

Downloads

You could download our trained models on the THUMOS14 and ActivityNet datasets by using the scripts of scripts/get_reference_model_thumos.sh and scripts/get_reference_model_anet.sh.