Title | ||
---|---|---|
Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos. |
Abstract | ||
---|---|---|
The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically. we propose a reinforcement learning based framework improved by multi-task learning and it shows steady performance gains by considering additional supervised boundary information during training. Our proposed framework achieves state-of-the-art performance on ActivityNet'18 DenseCaption dataset (Krishna et al. 2017) and Charades-STA dataset (Sigurdsson et al. 2016; Gao et al. 2017) while observing only 10 or less clips per video. |
Year | Venue | Field |
---|---|---|
2019 | THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Sliding window protocol,Ranking,Computer science,Natural language,Ground,Artificial intelligence,Machine learning,Reinforcement learning,CLIPS |
DocType | Volume | Citations |
Journal | abs/1901.06829 | 1 |
PageRank | References | Authors |
0.35 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
He, D. | 1 | 33 | 13.67 |
Xiang Zhao | 2 | 1 | 4.40 |
Jizhou Huang | 3 | 58 | 7.65 |
Fu Li | 4 | 25 | 8.88 |
Xiao Liu | 5 | 284 | 41.90 |
Shilei Wen | 6 | 79 | 13.59 |