AI Paper Atlas

Research map / Detection and segmentation / CNN features

Flow Guided Recurrent Neural Encoder for Video Salient Object Detection

Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin

CVPR 2018 · Detection and segmentation › CNN features · approach: RGB salient object detection · 197 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 flow-guided feature warping and recurrent temporal encoding to DSSDSS · DAVISmaxF: 0.775 -> 0.798Improved
Add flow-guided feature warping and recurrent temporal encoding to DSSDSS · DAVISMAE: 0.047 -> 0.032Improved
Add flow-guided feature warping and recurrent temporal encoding to DSSDSS · FBMSmaxF: 0.760 -> 0.783Improved
Add flow-guided feature warping and recurrent temporal encoding to DSSDSS · FBMSMAE: 0.077 -> 0.063Improved
Replace temporal modeling with naive weighted feature aggregation (ablation)DSS video model · DAVISmaxF: 0.775 -> 0.768Hurt
Add flow-guided feature warping to LSTM temporal encoding (ablation)DSS video model · DAVISmaxF: 0.777 -> 0.793Improved
Add reverse-LSTM optical-flow refinement to warping plus LSTM (ablation)DSS video model · DAVISmaxF: 0.793 -> 0.798Improved
Add reverse-LSTM optical-flow refinement to warping plus LSTM (ablation)DSS video model · DAVISMAE: 0.035 -> 0.032Improved
Use LSTM encoding without optical flow or warping (ablation)DSS video model · DAVISmaxF: 0.775 -> 0.777Improved
Use LSTM encoding without optical flow or warping (ablation)DSS video model · DAVISMAE: 0.047 -> 0.036Improved
Use flow-guided warping in place of unaligned weighted feature aggregation (ablation)DSS video model · DAVISmaxF: 0.768 -> 0.780Improved
Use flow-guided warping in place of unaligned weighted feature aggregation (ablation)DSS video model · DAVISMAE: 0.052 -> 0.036Improved

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