Sentence-level Segmentation for Long Sign Language Videos with Captions

摘要

In existing Sign Language (SL) research, most datasets and backbone models focus on sentence-level samples. However, the annotated sentence-level SL datasets are rather limited, and it is in great need to expand sentence-level SL datasets. When considering the large-scale long SL videos with captions, we propose a new task, i.e., Sentence-level Sign Language Segmentation (SSLS), which splits the long videos into consecutive sentence-level videos. SSLS is an important and meaningful task, which can greatly reduce the labor costs in data annotation for sentence-level SL datasets. However, SSLS is a very challenging task, since it is rather difficult to accurately find the boundary of each sentence in a long video. To address this issue, we formalize, learn, and optimize the boundaries of sentences step by step. First, to distinguish the boundary and the inside of a sentence, we formalize SSLS as a frame-level classification task and design a boundary annotation scheme. Second, to learn the boundary of each sentence from the long video, we design a multimodal framework, SignBD, which correlates the local features and global features through dual dilated attention, while aligning visual and textual (i.e., sentences) modalities through gated cross-attention. Third, to alleviate the widely existed over-segmentation and under-segmentation problems in segmentation tasks, we propose a boundary optimization strategy, which utilizes the number of sentences provided by captions to optimize (i.e., insert or delete) boundaries based on information uncertainty. Extensive experimental results demonstrate the superiority of our solution.