Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning

Ye-Chan Kim, Seunghee Choi, SeungJu Cha, Si-Woo Kim, Hwiseon Kim et al.|September 3, 2026arXiv

Key Takeaway

Using a VLM to detect actual visual transitions in videos produces better event localization and captions than pre-written transition descriptions inserted at fixed positions.

Summary

This paper tackles dense video captioning—describing multiple events in long videos—by using a vision-language model to intelligently detect transition moments between events rather than blindly inserting captions everywhere.

multimodal evaluation training

Key Terms

vision-language-model dense-video-captioning weakly-supervised-learning vision-language-alignment