LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

TL;DR

LongVideoBench is a comprehensive benchmark designed to evaluate large multimodal models on long-duration, complex video-language understanding tasks, emphasizing detailed reasoning over extended video contexts.

Contribution

The paper introduces LongVideoBench, a novel long-form video question-answering benchmark with a new referring reasoning task and extensive human-annotated questions, filling a critical gap in multimodal evaluation.

Findings

State-of-the-art models struggle with the benchmark's complexity.

Performance improves with increased frame processing.

Open-source models lag behind proprietary ones.

Abstract

Large multimodal models (LMMs) are processing increasingly longer and richer inputs. Albeit the progress, few public benchmark is available to measure such development. To mitigate this gap, we introduce LongVideoBench, a question-answering benchmark that features video-language interleaved inputs up to an hour long. Our benchmark includes 3,763 varying-length web-collected videos with their subtitles across diverse themes, designed to comprehensively evaluate LMMs on long-term multimodal understanding. To achieve this, we interpret the primary challenge as to accurately retrieve and reason over detailed multimodal information from long inputs. As such, we formulate a novel video question-answering task termed referring reasoning. Specifically, as part of the question, it contains a referring query that references related video contexts, called referred context. The model is then required to reason over relevant video details from the referred context. Following the paradigm of referring reasoning, we curate 6,678 human-annotated multiple-choice questions in 17 fine-grained categories, establishing one of the most comprehensive benchmarks for long-form video understanding. Evaluations suggest that the LongVideoBench presents significant challenges even for the most advanced proprietary models (e.g. GPT-4o, Gemini-1.5-Pro, GPT-4-Turbo), while their open-source counterparts show an even larger performance gap. In addition, our results indicate that model performance on the benchmark improves only when they are capable of processing more frames, positioning LongVideoBench as a valuable benchmark for evaluating future-generation long-context LMMs.