PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning
This work addresses dense video captioning for makeup videos, but it appears incremental as it builds on existing encoding-decoding methods with added semantic features.
The paper tackled dense video captioning by incorporating semantic information into an encoding-decoding framework, achieving significant improvements on the YouMakeup dataset under DVC evaluation metrics.
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of PIC 4th Challenge.