AI Paper Atlas

Research map / Video / Video segmentation and tracking

Learning to Explore Intrinsic Saliency for Stereoscopic Video

Qiudan Zhang, Xu Wang, Shiqi Wang, Shikai Li, Sam Kwong, Jianmin Jiang

CVPR 2019 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 7 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 spatio-temporal, intrinsic-depth, and Conv-LSTM fusion model instead of OMCNNstereoscopic video saliency prediction · SVSAUC Jud: 0.9066 -> 0.9201Improved
use the proposed spatio-temporal, intrinsic-depth, and Conv-LSTM fusion model instead of OMCNNstereoscopic video saliency prediction · SVSAUC Borji: 0.8244 -> 0.8390Improved
use the proposed spatio-temporal, intrinsic-depth, and Conv-LSTM fusion model instead of OMCNNstereoscopic video saliency prediction · SVSCC: 0.5184 -> 0.6339Improved
use the proposed spatio-temporal, intrinsic-depth, and Conv-LSTM fusion model instead of OMCNNstereoscopic video saliency prediction · SVSSIM: 0.4068 -> 0.5171Improved
use the proposed spatio-temporal, intrinsic-depth, and Conv-LSTM fusion model instead of OMCNNstereoscopic video saliency prediction · SVSNSS: 2.6336 -> 3.2320Improved
add intrinsic-depth saliency estimation and fusion to spatio-temporal saliency (ablation)Proposed-ST · SVSAUC Jud: 0.8836 -> 0.9201Improved
add intrinsic-depth saliency estimation and fusion to spatio-temporal saliency (ablation)Proposed-ST · SVSAUC Borji: 0.8088 -> 0.8390Improved
add intrinsic-depth saliency estimation and fusion to spatio-temporal saliency (ablation)Proposed-ST · SVSCC: 0.6096 -> 0.6339Improved
add intrinsic-depth saliency estimation and fusion to spatio-temporal saliency (ablation)Proposed-ST · SVSSIM: 0.4922 -> 0.5171Improved
add intrinsic-depth saliency estimation and fusion to spatio-temporal saliency (ablation)Proposed-ST · SVSNSS: 3.2075 -> 3.2320Improved
add spatio-temporal saliency and fusion to depth-only saliency (ablation)Proposed-Depth · SVSAUC Jud: 0.8444 -> 0.9201Improved
add spatio-temporal saliency and fusion to depth-only saliency (ablation)Proposed-Depth · SVSAUC Borji: 0.7903 -> 0.8390Improved

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