AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Object Discovery in Videos as Foreground Motion Clustering

Christopher Xie, Yu Xiang, Zaid Harchaoui, Dieter Fox

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 62 citations (OpenAlex)

Check 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
Use learned pixel-trajectory clustering rather than clustering foreground pixels independently in each frame (ablation)Object Discovery in Videos as Foreground Motion Clustering · FBMSmulti-object F: 59.7 -> 67.3Improved
Use foreground masks to restrict trajectory clustering (ablation)Object Discovery in Videos as Foreground Motion Clustering · FBMSmulti-object F: 59.6 -> 67.3Improved
Add the spatial coordinate module to trajectory embeddings (ablation)Object Discovery in Videos as Foreground Motion Clustering · FBMSmulti-object F: 63.2 -> 67.3Improved
Pre-train on FT3D before FBMS and DAVIS-m training (ablation)Object Discovery in Videos as Foreground Motion Clustering · FBMSmulti-object F: 63.1 -> 67.3Improved
Add DAVIS-m to FBMS training (ablation)Object Discovery in Videos as Foreground Motion Clustering · FBMSmulti-object F: 62.1 -> 67.3Improved
Use mid-level RGB/optical-flow fusion rather than early fusion (ablation)Y-Net · FT3Dforeground IoU: 0.883 -> 0.905Improved
Use mid-level RGB/optical-flow fusion rather than late fusion (ablation)Y-Net · FT3Dforeground IoU: 0.897 -> 0.905Improved
Use conv PT-RNN instead of convGRU PT-RNN (ablation)Pixel Trajectory RNN · FBMSmulti-object F: 64.8 -> 67.3Improved
Use conv PT-RNN instead of standard PT-RNN (ablation)Pixel Trajectory RNN · FBMSmulti-object F: 66.0 -> 67.3Improved
Use the proposed method rather than CCGMulti-object motion segmentation · FBMSmulti-object F: 65.0 -> 67.3Improved
Use the proposed method rather than CCGMulti-object motion segmentation · ComplexBackgroundmulti-object F: 65.6 -> 58.3Hurt
Use the proposed method rather than CCGMulti-object motion segmentation · CamouflagedAnimalmulti-object F: 72.2 -> 75.3Improved

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