Video Object Segmentation with Language Referring Expressions

TL;DR

This paper introduces a novel video object segmentation method that uses language referring expressions instead of pixel masks, making the process more practical, robust, and less costly while maintaining competitive performance.

Contribution

It extends language grounding models to video data for object segmentation, enabling language-based identification and tracking of objects in videos.

Findings

Performs on par with mask-based methods on DAVIS'16.

Competitive with scribble-based methods on DAVIS'17.

Augments benchmarks with language descriptions for evaluation.

Abstract

Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and time-consuming. In this work we explore an alternative way of identifying a target object, namely by employing language referring expressions. Besides being a more practical and natural way of pointing out a target object, using language specifications can help to avoid drift as well as make the system more robust to complex dynamics and appearance variations. Leveraging recent advances of language grounding models designed for images, we propose an approach to extend them to video data, ensuring temporally coherent predictions. To evaluate our method we augment the popular video object segmentation benchmarks, DAVIS'16 and DAVIS'17 with language descriptions of target objects. We show that our language-supervised approach performs on par with the methods which have access to a pixel-level mask of the target object on DAVIS'16 and is competitive to methods using scribbles on the challenging DAVIS'17 dataset.