Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
It improves video analysis for AI assistants, but is incremental as it builds on existing MLLMs with tool augmentation.
The paper tackles the challenge of enhancing Multimodal Large Language Models (MLLMs) for Video Question Answering (VideoQA) by addressing difficulties in modeling spatial relationships and temporal dynamics, achieving gains of 8.2% on VideoMME and 4.6% on LongVideoBench.
Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios. However, existing Multimodal Large Language Models (MLLMs) struggle with simultaneously modeling spatial relationships within video frames and understanding the causal dynamics of temporal evolution on complex and reasoning-intensive VideoQA task. In this work, we equip MLLM with a comprehensive and extensible Video Toolkit, to enhance MLLM's spatiotemporal reasoning capabilities and ensure the harmony between the quantity and diversity of tools. To better control the tool invocation sequence and avoid toolchain shortcut issues, we propose a Spatiotemporal Reasoning Framework (STAR) that strategically schedules temporal and spatial tools, thereby progressively localizing the key area in the video. Our STAR framework enhances GPT-4o using lightweight tools, achieving an 8.2% gain on VideoMME and 4.6% on LongVideoBench. We believe that our proposed Video Toolkit and STAR framework make an important step towards building autonomous and intelligent video analysis assistants. The code is publicly available at https://github.com/fansunqi/VideoTool.