LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos

TL;DR

LIGHTEN introduces a hierarchical, graph-based neural network that captures multi-granularity spatio-temporal cues in videos for human-object interaction detection without relying on depth or 3D pose data, achieving state-of-the-art results.

Contribution

The paper proposes LIGHTEN, a novel hierarchical approach that learns visual features for HOI detection using only RGB data, avoiding reliance on ground truth depth or pose information.

Findings

Achieves 88.9% and 92.6% accuracy on HOI detection tasks

Outperforms existing methods on CAD-120 and V-COCO datasets

Sets a new benchmark for visual feature-based HOI detection

Abstract

Analyzing the interactions between humans and objects from a video includes identification of the relationships between humans and the objects present in the video. It can be thought of as a specialized version of Visual Relationship Detection, wherein one of the objects must be a human. While traditional methods formulate the problem as inference on a sequence of video segments, we present a hierarchical approach, LIGHTEN, to learn visual features to effectively capture spatio-temporal cues at multiple granularities in a video. Unlike current approaches, LIGHTEN avoids using ground truth data like depth maps or 3D human pose, thus increasing generalization across non-RGBD datasets as well. Furthermore, we achieve the same using only the visual features, instead of the commonly used hand-crafted spatial features. We achieve state-of-the-art results in human-object interaction detection (88.9% and 92.6%) and anticipation tasks of CAD-120 and competitive results on image based HOI detection in V-COCO dataset, setting a new benchmark for visual features based approaches. Code for LIGHTEN is available at https://github.com/praneeth11009/LIGHTEN-Learning-Interactions-with-Graphs-and-Hierarchical-TEmporal-Networks-for-HOI