Temporal Gaussian Mixture Layer for Videos

This repository contains the code for our ICML 2019 paper:

AJ Piergiovanni and Michael S. Ryoo
"Temporal Gaussian Mixture Layer for Videos"
in ICML 2019

If you find the code useful for your research, please cite our paper:

    @inproceedings{piergiovanni2018super,
          title={Temporal Gaussian Mixture Layer for Videos},
          booktitle={International Conference on Machine Learning (ICML)},
          author={AJ Piergiovanni and Michael S. Ryoo},
          year={2019}
    }

Temporal Gaussian Mixture Layer

The core of our approach, the Temporal Gaussian Mixture (TGM) Layer can be found in tgm.py.

Multiple (M) temporal Gaussian distributions are learned, and they are combined with the learned soft attention weights to form the C temporal convolution filters. L is the temporal length of the filter.

The kernels are applied to each input channel, C_in, and a 1x1 convolution is applied to combine the C_in input channels for each output channel, C_out.

Activity Detection Experiments

To run our pre-trained models:

python train_model.py -mode joint -dataset multithumos -train False -rgb_model_file models/multithumos/rgb_baseline -flow_model_file models/multithumos/flow_baseline

We tested our models on the MultiTHUMOS, Charades, and MLB-YouTube datasets. We provide our trained models in the models directory.

Results

Charades

MultiTHUMOS

MLB-YouTube

THUMOS

Example Results

The temporal regions classified as various basketball activities from a basketball game video in MultiTHUMOS. Our TMG layers greatly improve performance.

Requirements

Our code has been tested on Ubuntu 14.04 and 16.04 using python 2.7, PyTorch version 0.3.1 with a Titan X GPU.

Setup

1. Download the code git clone https://github.com/piergiaj/tgm-icml19.git

2. Extract features from your dataset. See Pytorch-I3D for our code to extract I3D features.

3. train_model.py contains the code to train and evaluate models.

Refrences

[1] G. A. Sigurdsson, S. Divvala, A. Farhadi, and A. Gupta. Asynchronous temporal fields for action recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

[2] J. Carreira and A. Zisserman. Quo vadis, action recognition? A new model and the kinetics dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.

[3] S. Yeung, O. Russakovsky, N. Jin, M. Andriluka, G. Mori, and L. Fei-Fei. Every moment counts: Dense detailed labeling of actions in complex videos. International Journal of Computer Vision (IJCV), pages 1–15, 2015

[4] A. Piergiovanni and M. S. Ryoo. Learning latent super-events to detect multiple activities in videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 arxiv code