AI Paper Atlas

Research map / Video / Video segmentation and tracking

Unsupervised Open-Vocabulary Object Localization in Videos

Ke Fan, Zechen Bai, Tianjun Xiao, Dominik Zietlow, Max Horn, Zixu Zhao, Carl-Johann Simon-Gabriel, Mike Zheng Shou, Francesco Locatello, Bernt Schiele, Thomas Brox, Zheng Zhang and 2 more

ICCV 2023 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 8 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 name-assisted joint optimization (merge same-label neighboring slots, drop background) (ablation)Ours with patch-based CLIP · ImageNet-VIDmAP50: 5.20 -> 29.23Improved
add name-assisted joint optimization (ablation)Ours with patch-based CLIP · YouTube-VISmAP50: 5.96 -> 35.19Improved
use patch-based CLIP instead of vanilla CLIP under joint optimization (ablation)Ours · ImageNet-VIDmAP50: 3.04 -> 29.23Improved
use vanilla CLIP with joint optimization (ablation)Ours · ImageNet-VIDCorLoc: 42.99 -> 15.65Hurt
use video backbone (VideoMAE) with spatio-temporal video slots instead of per-frame slots (ablation)Ours · ImageNet-VIDmAP50: 25.77 -> 29.23Improved
use spatio-temporal video slots with DINO image backbone (ablation)Ours · ImageNet-VIDmAP50: 28.75 -> 28.40No clear effect
replace pixel-reconstruction slot methods with feature reconstruction (DINOSAUR)Slot-Attention/SAVi · ImageNet-VIDCorLoc: 16.23 (SAVi) -> 48.04 (DINOSAUR)Improved
add joint optimization to raise single-object slot share (ablation)Ours · ImageNet-VIDSingle-object slot share: 8.87% -> 49.33%Improved
add synonyms to the text vocabulary (ablation)Ours · ImageNet-VID/YouTube-VISlocalization and labelingNo clear effect

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