Papers with video-language multimodal models
QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing video-to-text summarization evaluation methods depend heavily on human-written reference summaries. |
| Approach: | They propose a reference-free metric evaluating candidate summaries directly against source videos through multimodal question answering. |
| Outcome: | The proposed metric assesses candidate summaries directly against source videos through multimodal question answering. |