Self-Selective Context for Interaction Recognition

TL;DR

This paper introduces Self-Selective Context (SSC), a novel method that improves human-object interaction recognition by focusing on the most relevant contextual information, reducing model size and noise.

Contribution

The paper proposes SSC, a new approach that models local human-object interactions and selectively incorporates context, enhancing accuracy and efficiency over existing methods.

Findings

SSC improves interaction recognition accuracy.

SSC uses fewer parameters than traditional models.

SSC effectively filters relevant contextual information.

Abstract

Human-object interaction recognition aims for identifying the relationship between a human subject and an object. Researchers incorporate global scene context into the early layers of deep Convolutional Neural Networks as a solution. They report a significant increase in the performance since generally interactions are correlated with the scene (\ie riding bicycle on the city street). However, this approach leads to the following problems. It increases the network size in the early layers, therefore not efficient. It leads to noisy filter responses when the scene is irrelevant, therefore not accurate. It only leverages scene context whereas human-object interactions offer a multitude of contexts, therefore incomplete. To circumvent these issues, in this work, we propose Self-Selective Context (SSC). SSC operates on the joint appearance of human-objects and context to bring the most discriminative context(s) into play for recognition. We devise novel contextual features that model the locality of human-object interactions and show that SSC can seamlessly integrate with the State-of-the-art interaction recognition models. Our experiments show that SSC leads to an important increase in interaction recognition performance, while using much fewer parameters.