Exploiting Egocentric Object Prior for 3D Saliency Detection

TL;DR

This paper introduces an EgoObject Representation that encodes shape, size, depth, and location features from egocentric RGBD images, improving 3D saliency detection, future saliency prediction, and interaction classification.

Contribution

It develops a novel egocentric object prior representation and demonstrates its effectiveness across multiple tasks on a new RGBD dataset.

Findings

30% improvement in 3D saliency detection accuracy

Effective prediction of future salient objects

Successful classification of human-object interactions

Abstract

On a minute-to-minute basis people undergo numerous fluid interactions with objects that barely register on a conscious level. Recent neuroscientific research demonstrates that humans have a fixed size prior for salient objects. This suggests that a salient object in 3D undergoes a consistent transformation such that people's visual system perceives it with an approximately fixed size. This finding indicates that there exists a consistent egocentric object prior that can be characterized by shape, size, depth, and location in the first person view. In this paper, we develop an EgoObject Representation, which encodes these characteristics by incorporating shape, location, size and depth features from an egocentric RGBD image. We empirically show that this representation can accurately characterize the egocentric object prior by testing it on an egocentric RGBD dataset for three tasks: the 3D saliency detection, future saliency prediction, and interaction classification. This representation is evaluated on our new Egocentric RGBD Saliency dataset that includes various activities such as cooking, dining, and shopping. By using our EgoObject representation, we outperform previously proposed models for saliency detection (relative 30% improvement for 3D saliency detection task) on our dataset. Additionally, we demonstrate that this representation allows us to predict future salient objects based on the gaze cue and classify people's interactions with objects.