AI Paper Atlas

Research map / Video / Video segmentation and tracking

An End-to-End Edge Aggregation Network for Moving Object Segmentation

Prashant W. Patil, Kuldeep M. Biradar, Akshay Dudhane, Subrahmanyam Murala

CVPR 2020 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 63 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 the proposed end-to-end network without test-video fine-tuningMoving object segmentation · DAVIS-2016F-measure: 0.902 -> 0.915Improved
use the proposed end-to-end networkMoving object segmentation · SegTrack-v2F-measure: 0.899 -> 0.918Improved
use the proposed network with global training and no target-video fine-tuningMoving object segmentation · CDnet-2014F-measure: 0.964 -> 0.969Improved
use the proposed method for thermal-data segmentationMoving object segmentation · GTFD thermalF-measure: 0.73 -> 0.75Improved
combine optical flow with RGB input frames rather than using either input alone (ablation)Proposed network · DAVIS-2016F-measure: 0.8648; 0.8246 -> 0.9149Improved
use four streams, 3×3 and 7×7 filters, and concatenation in EEM rather than the other tested stream/filter/fusion combinations (ablation)Proposed network · DAVIS-2016F-measure: 0.8545; 0.8601; 0.8793; 0.8908; 0.8635; 0.8733; 0.8937 -> 0.9149Improved
add one DRB to the bridge network rather than using no DRB (ablation)Proposed network · DAVIS-2016F-measure: 0.8701 -> 0.8917Improved
add a second DRB to the bridge network (ablation)Proposed network · DAVIS-2016F-measure: 0.8917 -> 0.9149Improved
add a third DRB to the bridge network instead of using two DRBs (ablation)Proposed network · DAVIS-2016F-measure: 0.9149 -> 0.8667Hurt

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