AI Paper Atlas

Research map / Video / Video generation

CI-VID: A Coherent Interleaved Text-Video Dataset

Yiming Ju, Jijin Hu, Zhengxiong Luo, Haoge Deng, hanyu Zhao, Li Du, Wenbo Xiao, Chengwei Wu, Donglin Hao, Xinlong Wang, Tengfei Pan

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 4 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
fine-tune on CI-VIDNOVA-0.6B video model · Human evaluation (consistency)win rate: 90.0% win, 6.5% tie, 3.6% lossImproved
fine-tune on CI-VIDNOVA-0.6B video model · Human evaluation (narrativity)win rate: 80.9% win, 15.0% tie, 4.1% lossImproved
fine-tune on CI-VIDNOVA-0.6B video model · Human evaluation (correctness)win rate: 78.3% win, 9.8% tie, 11.9% lossImproved
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Stylistic Consistency)VLM score: 2.93 -> 3.83Improved
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Entity Consistency)VLM score: 2.84 -> 3.73Improved
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Background Consistency)VLM score: 2.80 -> 3.75Improved
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Perspective Transition)VLM score: 3.02 -> 3.81Improved
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Text Prompt Alignment)VLM score: 3.99 -> 4.07No clear effect
fine-tune on CI-VIDNOVA-0.6B video model · VLM evaluation (Visual Plausibility)VLM score: 3.25 -> 3.62Improved
fine-tune on CI-VIDNOVA-0.6B video model · Similarity evaluation (Whole)CLIP: 0.512 -> 0.670Improved
fine-tune on CI-VIDNOVA-0.6B video model · Similarity evaluation (Whole)SSIM: 0.199 -> 0.272Improved
fine-tune on CI-VIDNOVA-0.6B video model · Similarity evaluation (Object)CLIP: 0.601 -> 0.702Improved

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