Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study
This work addresses the need for improved OCR capabilities in video LLMs, which is crucial for applications involving video content analysis, but it is incremental as it primarily provides a benchmarking tool rather than a new method.
The paper tackles the problem of evaluating optical character recognition (OCR) abilities in video-based multimodal large language models by introducing a novel benchmark with 1,028 videos and 2,961 question-answer pairs across six subtasks, resulting in a resource to advance research in this area.
With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability. This paper introduces a novel benchmark designed to evaluate the video OCR performance of multi-modal models in videos. Comprising 1,028 videos and 2,961 question-answer pairs, this benchmark proposes several key challenges through 6 distinct subtasks: (1) Recognition of text content itself and its basic visual attributes, (2)Semantic and Spatial Comprehension of OCR objects in videos (3) Dynamic Motion detection and Temporal Localization. We developed this benchmark using a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement, balancing efficiency, cost, and data quality. Our resource aims to help advance research in video LLMs and underscores the need for improving OCR ability for video LLMs. The benchmark will be released on https://github.com/YuHuiGao/FG-Bench.git.