What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation
英文标题：What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation
arXiv:2607.12304v1 Announce Type: new Abstract: A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1. The task question: is the question even temporal, does it need several frames and their order? and
打开原文相关 1.6 · 机会 0
中文
arXiv:2607.12304v1 Announce Type: new Abstract: A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1. The task question: is the question even temporal, does it need several frames and their order? and
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
arXiv:2607.12304v1 Announce Type: new Abstract: A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1. The task question: is the question even temporal, does it need several frames and their order? and