Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

RefCaptioner: Multi-Reference Image-Grounded Video Captioning

First seen · 7/31/2026, 12:00 PMLatest activity · 7/31/2026, 12:00 PM

The paper introduces multi-reference image-grounded video captioning, requiring factual video descriptions with phrase-level grounding to multiple reference images. RefCaptioner uses a two-stage post-training pipeline combining mixed-data supervised fine-tuning with Hierarchical Coverage-Discounted GRPO. The authors construct a corpus of 20,000 videos and 171,354 reference images, and release MRVBench for evaluating factuality and multi-reference grounding across real-world and AI-generated videos. According to the abstract, RefCaptioner performs best overall among open-source models while remaining competitive on standard video-captioning benchmarks. Human evaluations also report preferred captions and more source-faithful video reconstruction.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/31, 12:00 PMnot independentRepresentative
    RefCaptioner: Multi-Reference Image-Grounded Video Captioning