Multi-level visual representation with semantic-reinforced learning for video captioning

C Dong, X Chen, A Chen, F Hu, Z Wang… - Proceedings of the 29th …, 2021 - dl.acm.org
C Dong, X Chen, A Chen, F Hu, Z Wang, X Li
Proceedings of the 29th ACM international conference on multimedia, 2021dl.acm.org
This paper describes our bronze-medal solution for the video captioning task of the
ACMMM2021 Pre-Training for Video Understanding Challenge. We depart from the Bottom-
Up-Top-Down model, with technical improvements on both video content encoding and
caption decoding. For encoding, we propose to extract multi-level video features that
describe holistic scenes and fine-grained key objects, respectively. The scene-level and
object-level features are enhanced separately by multi-head self-attention mechanisms …
This paper describes our bronze-medal solution for the video captioning task of the ACMMM2021 Pre-Training for Video Understanding Challenge. We depart from the Bottom-Up-Top-Down model, with technical improvements on both video content encoding and caption decoding. For encoding, we propose to extract multi-level video features that describe holistic scenes and fine-grained key objects, respectively. The scene-level and object-level features are enhanced separately by multi-head self-attention mechanisms before feeding them into the decoding module. Towards generating content-relevant and human-like captions, we train our network end-to-end by semantic-reinforced learning. Finally, in order to select the best caption from captions produced by distinct models, we perform caption reranking by cross-modal matching between a given video and each candidate caption. Both internal experiments on the MSR-VTT test set and external evaluations by the challenge organizers justify the viability of the proposed solution.
ACM Digital Library
以上显示的是最相近的搜索结果。 查看全部搜索结果