AI Paper Atlas

Research map / Video / Video-language understanding

SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning

Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Minju Jeon, Hyungee Kim, Dong-Jin Kim

CVPR 2026 · Video › Video-language understanding · approach: Dense video captioning · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add similarity-aware mask guide (Lsim) (ablation)SAIL / ILCACM · ActivityNet Captions valCIDEr: 33.42 -> 35.18Improved
add LLM synthetic captions with inter-masks (ablation)SAIL / ILCACM · ActivityNet Captions valCIDEr: 33.42 -> 34.92Improved
combine similarity mask and synthetic captions (ablation)SAIL · ActivityNet Captions valCIDEr: 35.18 -> 35.38Improved
use synthetic captions as hard negatives in Lsim rather than as auxiliary inter-mask signal (ablation)SAIL · ActivityNet Captions valCIDEr: 35.38 -> 33.84Hurt
increase synthetic caption ratio from 25% to 100% (ablation)SAIL · ActivityNet Captions valCIDEr: 33.76 -> 35.38Improved
use Gaussian masks instead of Cauchy masks (ablation)SAIL · ActivityNet Captions valCIDEr: 33.85 -> 35.38Improved
use Gaussian masks instead of hard binary masks (ablation)SAIL · ActivityNet Captions valCIDEr: 17.54 -> 35.38Improved
apply SAIL on top of ILCACM with Hard Binary mask (ablation)ILCACM · ActivityNet Captions val (Hard Binary mask)CIDEr: 16.96 -> 17.54Improved
vary inter-mask width w_inter (ablation)SAIL · ActivityNet Captions valCIDEr, F1No clear effect
use SAIL instead of ILCACM on computationSAIL · ActivityNet Captions valtraining time: 1H 38M 27S -> 1H 41M 59SNo clear effect
train SAIL instead of ILCACM on YouCook2SAIL · YouCook2 valCIDEr: 13.49 -> 14.61Improved
reduce ground-truth caption density to 25% (baseline)ILCACM · ActivityNet Captions valCIDEr, SODA_cHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy