AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly-Supervised Deep Nonnegative Low-Rank Model for Social Image Tag Refinement and Assignment

AAAI 2017 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 12 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
link visual features to tags with a deep architecture jointly with a nonnegative low-rank model (WDNL)WDNL vs best baseline · MIRFlickr tag refinementMicroAUC: 0.644 -> 0.685Helped
link visual features to tags with a deep architecture jointly with a nonnegative low-rank model (WDNL)WDNL vs best baseline · NUS-WIDE tag refinementMicroAUC: 0.770 -> 0.789Helped
link visual features to tags with a deep architecture jointly with a nonnegative low-rank model (WDNL)WDNL vs best baseline · NUS-WIDE tag assignmentMacroAUC: 0.643 -> 0.671Helped
link visual features to tags with a deep architecture jointly with a nonnegative low-rank model (WDNL)WDNL vs best baseline · MIRFlickr tag assignmentMicroAUC: 0.642 -> 0.665Helped
use deep CNN-based representations instead of CCA on shallow features (CCA to CCA-CNN)CCA · MIRFlickr tag refinementMicroAUC: 0.583 -> 0.644Helped

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