shuangli59 / gated-spatio-temporal-energy-graph

[CVPR'19] Pytorch implementation for learning an observation-Gated Spatio-Temporal Energy Graph for Video Relationship Reasoning on Charades dataset

Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph

Pytorch implementation for learning an observation-Gated Spatio-Temporal Energy Graph for Video Relationship Reasoning on Charades dataset.

Contact: Yao-Hung Hubert Tsai ([email protected])

Paper

Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
Yao-Hung Hubert Tsai, Santosh Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov and Ali Farhadi
Computer Vision and Pattern Recognition (CVPR), 2019.

Please cite our paper if you find the code, dataset, or the experimental setting useful for your research.

@inproceedings{tsai2019GSTEG,
  title={Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph},
  author={Tsai, Yao-Hung Hubert and Divvala, Santosh and Morency, Louis-Philippe and Salakhutdinov, Ruslan and Farhadi, Ali},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}

Overview

Relationship Reasoning in Videos

Visual relationship reasoning in images (top) vs. videos (bottom): Given a single image, it is ambiguous whether the monkey is creeping up or down the car. Using a video not only helps to unambiguously recognize a richer set of relations, but also model temporal correlations across them (e.g., creep down and jump left).

Gated Spatio-Temporal Energy Graph

An overview of our Proposed Gated Spatio-Temporal Energy Graph. Given an input instance (a video clip), we predict the output relationships (e.g., {monkey, creep down, car}, etc.,) by reasoning over a fully-connected spatio-temporal graph with nodes S (Subject),P (Predicate) and O (Object). Instead of assuming a non-gated (i.e., predefined or globally-learned) pairwise energy function, we explore the use of gated energy functions (i.e., conditioned on the specific visual observation).

Usage

Prerequisites

• Python 3.6
• Pytorch and torchvision

Datasets

• Charades dataset
• Charades' Training and Validation Annotations

Pretrained Model

• Download the pretrained (with Kinetics Dataset) I3D model here.

Run the Code

1. Modify exp/GSTEG.py
   • Create the cache directory
   • Specify the location of the data, training/validation split, and pretrained model.
2. Command as follows

python3 exp/GSTEG.py

Acknowledgement

A large portion of the code comes from the Temporal Fields, VidVRD, and ImageNet repo.