Skip to content
Go to file


Failed to load latest commit information.
Latest commit message
Commit time

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


  • October 16th, 2018
    • Release the learned models trained only on the train set of ActivityNet1.2 datasets. Note that our previously released ActivityNet models are trained on the train+val set.
  • September 19th, 2017
    • Release the learned models on the THUMOS14 and ActivityNet1.2 datasets.
  • August 20th, 2017
    • Release the model protos.


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:

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/


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


Weakly Supervised Action Recognition and Detection




No releases published


No packages published
You can’t perform that action at this time.