Event and Entity Extraction from Generated Video Captions
This addresses the challenge of costly human annotation for multimedia data by automating metadata extraction, though it is incremental as it builds on existing captioning models.
The paper tackled the problem of extracting semantic metadata from automatically generated video captions, showing that entities, properties, relations, and video categories can be extracted, with quality influenced by event localization and caption generation performance.
Annotation of multimedia data by humans is time-consuming and costly, while reliable automatic generation of semantic metadata is a major challenge. We propose a framework to extract semantic metadata from automatically generated video captions. As metadata, we consider entities, the entities' properties, relations between entities, and the video category. We employ two state-of-the-art dense video captioning models with masked transformer (MT) and parallel decoding (PVDC) to generate captions for videos of the ActivityNet Captions dataset. Our experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions. We observe that the quality of the extracted information is mainly influenced by the quality of the event localization in the video as well as the performance of the event caption generation.