Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.16538 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917419049549824 |
|---|---|
| author | Dipta, Shubhashis Roy Wu, Tz-Ying Tripathi, Subarna |
| author_facet | Dipta, Shubhashis Roy Wu, Tz-Ying Tripathi, Subarna |
| contents | We propose VC-Inspector, a lightweight, open-source large multimodal model (LMM) for reference-free evaluation of video captions, with a focus on factual accuracy. Unlike existing metrics that suffer from limited context handling, weak factuality assessment, or reliance on proprietary services, VC-Inspector offers a reproducible and fact-aware alternative that aligns closely with human judgments. To enable robust training and interpretable evaluation, we introduce a systematic framework for generating captions with controllable factual errors, paired with graded quality scores and explanatory annotations. Experiments demonstrate that VC-Inspector achieves state-of-the-art correlation with human judgments, generalizing across diverse domains (e.g., VATEX-Eval, Flickr8K-Expert, and Flickr8K-CF benchmarks) and revealing the potential for caption improvement. Project page is available at https://dipta007.github.io/VC-Inspector |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16538 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis Dipta, Shubhashis Roy Wu, Tz-Ying Tripathi, Subarna Computer Vision and Pattern Recognition Computation and Language We propose VC-Inspector, a lightweight, open-source large multimodal model (LMM) for reference-free evaluation of video captions, with a focus on factual accuracy. Unlike existing metrics that suffer from limited context handling, weak factuality assessment, or reliance on proprietary services, VC-Inspector offers a reproducible and fact-aware alternative that aligns closely with human judgments. To enable robust training and interpretable evaluation, we introduce a systematic framework for generating captions with controllable factual errors, paired with graded quality scores and explanatory annotations. Experiments demonstrate that VC-Inspector achieves state-of-the-art correlation with human judgments, generalizing across diverse domains (e.g., VATEX-Eval, Flickr8K-Expert, and Flickr8K-CF benchmarks) and revealing the potential for caption improvement. Project page is available at https://dipta007.github.io/VC-Inspector |
| title | VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2509.16538 |