视频描述生成提速：并行解码不丢精度
给视频写详细文字描述（比如“第3秒一个人走进房间，第10秒拿起杯子”）通常要一个字一个字地生成，速度很慢。这篇论文发现：不同时间段的事件之间关联很弱，可以同时生成，而每个事件内部的词才需要按顺序写。他们设计了一个“全局规划”机制，先自动识别出视频里有哪些事件，然后让这些事件对应的描述并行生成，同时保证每个事件内部的语义连贯。在多个测试集上，速度提升明显，且描述质量不降反升。它不是你明天能用上的，但指明了多模态大模型在视频理解上提速的一个可行方向。
📄 原文摘要(英文)
Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation. In this domain, autoregressive video large language models have emerged as a prevalent paradigm due to their strong generative and cross-modal modeling capacity. However, generating dense captions under the token-by-token paradigm severely limits inference efficiency and hinders scalability as video length and event density increase. In this work, we propose a parallelized autoregressive framework that not only improves generation efficiency but also enhances temporally grounded captioning performance. Our key insight is to exploit the weak local dependencies across temporally distinct events to restructure the causal dependency graph, thereby enabling lossless parallel generation. Specifically, tokens with weak cross-event dependencies can be decoded in parallel, while tightly coupled tokens within each event retain sequential decoding to preserve local semantic coherence. To realize this insight, we introduce two key components for lossless parallel decoding: (1) a latent global planning mechanism that automatically learns the event-level structure and produces compact tokens encoding global inter-event causality while adaptively aggregating event-level audio-visual semantics, guiding subsequent dependency restructuring and parallel decoding; and (2) an event-factorized parallel decoding mechanism that effectively balances local focus with global inter-event awareness. Experiments on various benchmarks demonstrate the clear advantage of our approach in both efficiency and performance in omni-modal event grounding and captioning. Project website: https://github.com/showlab/PadCaptioner.