NeMo: Needle in a Montage for Video-Language Understanding
This work addresses the problem of assessing critical reasoning in video-language understanding for researchers and developers, though it is incremental as it builds on existing needle-in-a-haystack tests for LLMs.
The authors tackled the need for evaluating complex temporal reasoning in video-language models by introducing the Needle in a Montage (NeMo) task and NeMoBench benchmark, which includes 31,378 automatically generated question-answer pairs from 13,486 videos, and they evaluated 20 state-of-the-art models to provide insights into their capabilities.
Recent advances in video large language models (VideoLLMs) call for new evaluation protocols and benchmarks for complex temporal reasoning in video-language understanding. Inspired by the needle in a haystack test widely used by LLMs, we introduce a novel task of Needle in a Montage (NeMo), designed to assess VideoLLMs' critical reasoning capabilities, including long-context recall and temporal grounding. To generate video question answering data for our task, we develop a scalable automated data generation pipeline that facilitates high-quality data synthesis. Built upon the proposed pipeline, we present NeMoBench, a video-language benchmark centered on our task. Specifically, our full set of NeMoBench features 31,378 automatically generated question-answer (QA) pairs from 13,486 videos with various durations ranging from seconds to hours. Experiments demonstrate that our pipeline can reliably and automatically generate high-quality evaluation data, enabling NeMoBench to be continuously updated with the latest videos. We evaluate 20 state-of-the-art models on our benchmark, providing extensive results and key insights into their capabilities and limitations. Our project page is available at: https://lavi-lab.github.io/NeMoBench.