# Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks

arXiv: https://arxiv.org/abs/2009.08427 · HTML: https://mlsanity.com/paper/2009.08427/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [Graph Neural Network for spatiotemporal data: methods and applications](https://mlsanity.com/paper/2306.00012/) (2023)
- [Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition](https://mlsanity.com/paper/2110.04954/) (2021)
- [G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding](https://mlsanity.com/paper/2608.20157/) (2026)

## Abstract (arXiv)

Graph Neural Networks are perfectly suited to capture latent interactions between various entities in the spatio-temporal domain (e.g. videos). However, when an explicit structure is not available, it is not obvious what atomic elements should be represented as nodes. Current works generally use pre-trained object detectors or fixed, predefined regions to extract graph nodes. Improving upon this, our proposed model learns nodes that dynamically attach to well-delimited salient regions, which are relevant for a higher-level task, without using any object-level supervision. Constructing these localized, adaptive nodes gives our model inductive bias towards object-centric representations and we show that it discovers regions that are well correlated with objects in the video. In extensive ablation studies and experiments on two challenging datasets, we show superior performance to previous graph neural networks models for video classification.