Object Referring in Videos with Language and Human Gaze

Arun Balajee Vasudevan
Dengxin Dai
Luc Van Gool

ETH Zurich


We investigate the problem of object referring (OR) i.e. to localize a target object in a visual scene coming with a language description. Humans perceive the world more as continued video snippets than as static images, and describe objects not only by their appearance, but also by their spatio-temporal context and motion features. Humans also gaze at the object when they issue a referring expression. Existing works for OR mostly focus on static images only, which fall short in providing many such cues. This paper addresses OR in videos with language and human gaze. To that end, we present a new video dataset for OR, with 30, 000 objects over 5, 000 stereo video sequences annotated for their descriptions and gaze. We further propose a novel network model for OR in videos, by integrating appearance, motion, gaze, and spatio-temporal context into one network. Experimental results show that our method effectively utilizes motion cues, human gaze, and spatio-temporal context. Our method outperforms previousOR methods.


Object Referring in Videos with Language and Human Gaze
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
CVPR 2018
pdf / bibtex


Code and Data

Gaze Interface: [code]
Dataset: [data]


This work was supported by Toyota TRACE-Zurich.
This webpage template uses the work of Zhang et al.