Video Object Segmentation with Language Referring Expressions

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 approach we augment the popular video object segmentation benchmarks, DAVIS16 and DAVIS17 with language descriptions of target objects. We show that our approach performs on par with the methods which have access to a pixel-level mask of the target object on DAVIS16 and is competitive to methods using scribbles on the challenging DAVIS17 dataset. Query: "A man in a red sweatshirt performing breakdance" Figure 1: Examples of the proposed approach. Classical semi-supervised video object segmentation relies on an expensive pixel-level mask annotation of a target object in the first frame of a video. We explore a more natural and more practical way of pointing out a target object by providing a language referring expression.