Multimodal semantic comprehension has attracted increasing research interests in recent years, such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension which requires to capture semantic details of multimodal contents has not been well investigated. In this work, we introduce "YouMakeup", a large-scale multimodal instructional video dataset to support finegrained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which require fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models' ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering tasks from different aspects. We also establish a baseline of step caption generation for future comparison.
展开▼