AI Paper Atlas

Research map / Video / Video segmentation and tracking

ReferEverything: Towards Segmenting Everything We Can Speak of in Videos

Anurag Bagchi, Zhipeng Bao, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert

ICCV 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 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
supervise mask prediction in the VAE latent space instead of RGB pixels (256px) (ablation)REM (MS-1.4B) · Ref-VPSJ: 31.6 -> 35.8Improved
supervise in latent space instead of RGB with fine-tuned VAE (256px) (ablation)REM (MS-1.4B) · Ref-YTBJ&F: 60.4 -> 61.4Improved
keep the pre-trained frozen VAE decoder instead of a CNN mask decoder (ablation)REM (MS-1.4B) · Ref-VPSJ: 29.4 -> 40.0Improved
keep the pre-trained frozen VAE decoder instead of an MLP mask decoder (ablation)REM (MS-1.4B) · Ref-VPSJ: 33.1 -> 40.0Improved
add image-only first stage (two-stage training) (ablation)REM (MS-1.4B) · Ref-VPSJ: 46.33 -> 49.0Improved
add image data in second stage (ablation)REM (MS-1.4B) · Ref-VPSJ: 40.7 -> 49.0Improved
add image data in second stage (ablation)REM (MS-1.4B) · Ref-YTBJ&F: 68.7 -> 68.4No clear effect
double the image data (2:1 images to videos) (ablation)REM (MS-1.4B) · Ref-VPSJ: 49.0 -> 48.0Hurt
use noise timestep 0 instead of 50 (ablation)REM · Ref-YTBJ: 35.0 -> 40.5Improved
use noise timestep 0 instead of 200 (ablation)REM · Ref-YTBJ&F: 59.2 -> 62.9Improved
use ModelScope backbone instead of Stable Diffusion 2.1 image model (ablation)REM · Ref-VPSJ: 29.8 -> 40.0Improved
use VideoCrafter-2 with curated data instead of VideoCrafter-1 (ablation)REM · Ref-VPSJ: 28.0 -> 36.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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