AI Paper Atlas

Research map / Video / Video segmentation and tracking

OV-VIS: Open-Vocabulary Video Instance Segmentation

Haochen Wang, Cilin Yan, Keyan Chen, Xiaolong Jiang, Xu Tang, Yao Guang Hu, Guoliang Kang, Weidi Xie, Efstratios Gavves

IJCV 2024 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 14 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 InstCLIP (ablation)MinVIS-CLIP · BURSTAP: 2.1 -> 3.3Improved
add InstCLIP (ablation)MinVIS-CLIP · UVOAP: 9.0 -> 13.2Improved
add InstCLIP (ablation)MinVIS-CLIP · YouTube-VISAP: 30.6 -> 48.6Improved
add contrastive instance margin loss L_SC (ablation)InstFormer · BURSTAP: 3.3 -> 3.5Improved
add InstCLIP token (ablation)InstFormer · BURSTAP: 3.5 -> 3.9Improved
add rollout tracker (ablation)InstFormer · BURSTAP: 3.9 -> 4.2Improved
add instance tokens without guidance to CLIP (ablation)N times CLIP · BURSTAP: 2.11 -> 1.09Hurt
add designed instance attention mask guidance (ablation)InstCLIP · BURSTAP: 1.70 -> 3.28Improved
add register token (ablation)InstCLIP · BURSTAP: 3.28 -> 3.87Improved
add instance token to rollout tracker (ablation)Rollout tracker · BURSTAP: 3.6 -> 4.2Improved
use RNN instead of linear layer in rollout tracker (ablation)Rollout tracker · BURSTAP: 3.7 -> 4.2Improved
use RNN instead of two-layer MLP in rollout tracker (ablation)Rollout tracker · BURSTAP: 3.4 -> 4.2Improved

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