VideoLLM Benchmarks and Evaluation: A Survey

TL;DR

This survey reviews current benchmarks and evaluation methods for Video Large Language Models, analyzing their strengths, limitations, and future directions to improve video understanding assessments.

Contribution

It provides a comprehensive analysis of existing VideoLLM benchmarks, evaluation protocols, and highlights key challenges and future research directions in the field.

Findings

Performance trends of state-of-the-art VideoLLMs across benchmarks

Identification of limitations in current evaluation protocols

Proposals for more diverse and interpretability-focused benchmarks

Abstract

The rapid development of Large Language Models (LLMs) has catalyzed significant advancements in video understanding technologies. This survey provides a comprehensive analysis of benchmarks and evaluation methodologies specifically designed or used for Video Large Language Models (VideoLLMs). We examine the current landscape of video understanding benchmarks, discussing their characteristics, evaluation protocols, and limitations. The paper analyzes various evaluation methodologies, including closed-set, open-set, and specialized evaluations for temporal and spatiotemporal understanding tasks. We highlight the performance trends of state-of-the-art VideoLLMs across these benchmarks and identify key challenges in current evaluation frameworks. Additionally, we propose future research directions to enhance benchmark design, evaluation metrics, and protocols, including the need for more diverse, multimodal, and interpretability-focused benchmarks. This survey aims to equip researchers with a structured understanding of how to effectively evaluate VideoLLMs and identify promising avenues for advancing the field of video understanding with large language models.