Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning

14 Jun 2020  ·  Yuqing Song, Shi-Zhe Chen, Yida Zhao, Qin Jin ·

Detecting meaningful events in an untrimmed video is essential for dense video captioning. In this work, we propose a novel and simple model for event sequence generation and explore temporal relationships of the event sequence in the video. The proposed model omits inefficient two-stage proposal generation and directly generates event boundaries conditioned on bi-directional temporal dependency in one pass. Experimental results show that the proposed event sequence generation model can generate more accurate and diverse events within a small number of proposals. For the event captioning, we follow our previous work to employ the intra-event captioning models into our pipeline system. The overall system achieves state-of-the-art performance on the dense-captioning events in video task with 9.894 METEOR score on the challenge testing set.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Dense Video Captioning ActivityNet Captions Bi-directional+intra captioning METEOR 11.28 # 3

Methods


No methods listed for this paper. Add relevant methods here