AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation

Xuelu Feng, Dongdong Chen, Junsong Yuan, Chunming Qiao, Gang Hua, Zixin Zhu

ECCV 2024 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 27 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 referring text tokens as condition instead of image tokens only (ablation)VD-IT · Ref-YouTube-VOSJ&F: 59.7 -> 61.9Improved
combine image and text tokens as condition (ablation)VD-IT · Ref-YouTube-VOSJ&F: 61.9 -> 63.8Improved
predict video-specific noise instead of Gaussian noise (ablation)VD-IT · Ref-YouTube-VOSJ&F: 63.8 -> 64.8Improved
fuse text and image tokens by attention instead of concatenation (ablation)VD-IT · Ref-YouTube-VOSJ&F: 62.4 -> 64.8Improved
increase noise step added to video latent from 1 to 100 (ablation)VD-IT · Ref-YouTube-VOSJ&F: 64.8 -> 62.7Hurt
use fixed generative T2V diffusion backbone instead of Video SwinR-VOS · Ref-YouTube-VOSIoU diff between frames: 7.24 -> 5.19Improved
add text tokens to image-token conditioning (ablation)VD-IT · Ref-YouTube-VOSratio of IoU>0.9 to IoU>0.5 masks: 47.26% -> 46.71%Mixed
apply VD-IT unchanged to referring image segmentationVD-IT · RefCOCO/+/gOverall IoU: 76.3 -> 76.7 (RefCOCO)No clear effect
use T2V diffusion backbone instead of Video Swin at inferenceR-VOS · Ref-YouTube-VOSFPS: 65 -> 21Hurt

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