RUC+CMU: System Report for Dense Captioning Events in Videos
This is an incremental improvement for video understanding tasks, specifically targeting the ActivityNet Dense Captioning benchmark.
The authors tackled the dense video captioning problem by developing a system with proposal ranking and context-enhanced caption generation, achieving state-of-the-art performance with an 8.529 METEOR score on the ActivityNet challenge testing set.
This notebook paper presents our system in the ActivityNet Dense Captioning in Video task (task 3). Temporal proposal generation and caption generation are both important to the dense captioning task. Therefore, we propose a proposal ranking model to employ a set of effective feature representations for proposal generation, and ensemble a series of caption models enhanced with context information to generate captions robustly on predicted proposals. Our approach achieves the state-of-the-art performance on the dense video captioning task with 8.529 METEOR score on the challenge testing set.