The pretrained models trained on Moments in Time Dataset
Switch branches/tags
Nothing to show
Clone or download
Bolei demo updated
Latest commit 2b8b943 Mar 10, 2018

Pretrained models for Moments in Time Dataset

We release the pre-trained models trained on Moments in Time.

Download the Models

  • Clone the code from Github:
    git clone
    cd moments_models


  • RGB model in PyTorch (ResNet50 pretrained on ImageNet). Run the following script to download and run the test sample. The model is tested sucessfully in PyTorch0.3 + python36.

To test the model on your own video, supply the path of an mp4 file to this script like so:

    python --video_file path/to/video.mp4
  • Dynamic Image model in Caffe: use the testing script.

  • TRN models is at this repo. To use the TRN model trained on Moments:

Clone the TRN repo and Download the pretrained TRN model

git clone --recursive
cd TRN-pytorch/pretrain
cd ../sample_data

Test the pretrained model on the sample video (Bolei is juggling ;-]!)


python --arch InceptionV3 --dataset moments \
    --weight pretrain/TRN_moments_RGB_InceptionV3_TRNmultiscale_segment8_best.pth.tar \
    --frame_folder sample_data/bolei_juggling

RESULT ON sample_data/bolei_juggling
0.982 -> juggling
0.003 -> flipping
0.003 -> spinning


Mathew Monfort, Bolei Zhou, Sarah Adel Bargal, Alex Andonian, Tom Yan, Kandan Ramakrishnan, Lisa Brown, Quanfu Fan, Dan Gutfreund, Carl Vondrick, Aude Oliva. 'Moments in Time Dataset: one million videos for event understanding'. arXiv:1801.03150. pdf, bib


The project is supported by MIT-IBM Watson AI Lab and IBM Research.