CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models

  • 类型:arxiv
  • 标识:2608.04302
  • 链接:https://arxiv.org/abs/2608.04302
  • 主分类:multimodal
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:CLIP-CC-Bench provides a practical evaluation framework for long-form video description, filling a gap left by existing short-clip and QA-only benchmarks and quantifying the protocol's internal reliability through inter-judge agreement and bootstrap ranking stability.
  • 副分类:evaluation
  • 待LLM分类:否
  • 标题中文:CLIP-CC-Bench:评估视频-语言模型中的段落级视频描述
  • TLDR中文:CLIP-CC-Bench 为长视频描述提供了一个实用的评估框架,填补了现有短片段和仅 QA 基准的空白,并通过评分者间一致性(inter-judge agreement)与 bootstrap 排序稳定性量化该协议的内可靠性。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-11-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-08-11-agent-rag-longcontext-candidates.json
  • [S2 enrich]