Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning
This work addresses a specific bottleneck in dense video captioning for video understanding applications, representing an incremental improvement over existing query-based frameworks.
The paper tackled the problem of multi-task interference and temporal redundancy in dense video captioning by proposing role-specific queries with overlap suppression loss, achieving state-of-the-art results on YouCook2 and ActivityNet Captions benchmarks.
Dense Video Captioning (DVC) is a challenging multimodal task that involves temporally localizing multiple events within a video and describing them with natural language. While query-based frameworks enable the simultaneous, end-to-end processing of localization and captioning, their reliance on shared queries often leads to significant multi-task interference between the two tasks, as well as temporal redundancy in localization. In this paper, we propose utilizing role-specific queries that separate localization and captioning into independent components, allowing each to exclusively learn its role. We then employ contrastive alignment to enforce semantic consistency between the corresponding outputs, ensuring coherent behavior across the separated queries. Furthermore, we design a novel suppression mechanism in which mutual temporal overlaps across queries are penalized to tackle temporal redundancy, supervising the model to learn distinct, non-overlapping event regions for more precise localization. Additionally, we introduce a lightweight module that captures core event concepts to further enhance semantic richness in captions through concept-level representations. We demonstrate the effectiveness of our method through extensive experiments on major DVC benchmarks YouCook2 and ActivityNet Captions.