A Multimodal Framework for Video Ads Understanding

International Multimedia Conference(2021)

引用 1|浏览49
暂无评分
摘要
ABSTRACTThere is a growing trend in placing video advertisements on social platforms for online marketing, which demands automatic approaches to understand the contents of advertisements effectively. Taking the 2021 TAAC competition as an opportunity, we developed a multimodal system to improve the ability of structured analysis of advertising video content. In our framework, we break down the video structuring analysis problem into two tasks, i.e., scene segmentation and multi-modal tagging. In scene segmentation, we build upon a temporal convolution module for temporal modeling to predict whether adjacent frames belong to the same scene. In multi-modal tagging, we first compute clip-level visual features by aggregating frame-level features with NeXt-SoftDBoF. The visual features are further complemented with textual features that are derived using a global-local attention mechanism to extract useful information from OCR (Optical Character Recognition) and ASR (Audio Speech Recognition) outputs. Our solution achieved a score of 0.2470 measured in consideration of localization and prediction accuracy, ranking fourth in the 2021 TAAC final leaderboard.
更多
查看译文
关键词
video ads,multimodal framework
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要