Multi-Level Representation Learning with Semantic Alignment for Referring Video Object Segmentation

Referring video object segmentation (RVOS) is a challenging language-guided video grounding task, which requires comprehensively understanding the semantic information of both video content and language queries for object prediction. However, existing methods adopt multi-modal fusion at a frame-based spatial granularity. The limitation of visual representation is prone to causing vision-language mismatching and producing poor segmentation results. To address this, we propose a novel multi-level representation learning approach, which explores the inherent structure of the video content to provide a set of discriminative visual embedding, enabling more effective vision-language semantic alignment. Specifically, we embed different visual cues in terms of visual granularity, including multi-frame long-temporal information at video level, intra-frame spatial semantics at frame level, and enhanced object-aware feature prior at object level. With the powerful multi-level visual embedding and carefully-designed dynamic alignment, our model can generate a robust representation for accurate video object segmentation. Extensive experiments on Refer-DAVIS <inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">17</inf> and Refer-YouTube-VOS demonstrate that our model achieves superior performance both in segmentation accuracy and inference speed.