AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Visual Recognition in RGB Images and Videos by Learning from RGB-D Data

Wen Li, Lin Chen, Dong Xu, Luc Van Gool

TPAMI 2017 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 44 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 depth features in the source domain plus MMD domain adaptation (DAM2S_A)SVM_A · RGB-D Object to Caltech-256 object recognitionaccuracy (%): 27.52 -> 53.17Improved
add privileged depth information via SVM2K without domain adaptationSVM_A · RGB-D Object to Caltech-256 object recognitionaccuracy (%): 27.52 -> 34.21Improved
add depth features and domain adaptation instead of best DA baseline DIPDIP · RGB-D Object to Caltech-256 object recognitionaccuracy (%): 45.13 -> 56.89Improved
use domain adaptation DAM2S_C on cross-dataset action recognitionSVM_A · Hollywood 3D to Hollywood2 cross-dataset action recognitionaccuracy (%): 19.17 -> 39.17Improved
use multi-source domain adaptation DAM instead of SVM_ASVM_A · Hollywood 3D to Hollywood2 cross-dataset action recognitionaccuracy (%): 19.17 -> 19.32No clear effect
use DAM2S_A on cross-view action recognitionSVM_A · ACT42 cross-view action recognitionaccuracy (%): 62.33 -> 68.86Improved
use SA-based regularizer (DAM2S_C) instead of MMD regularizer (DAM2S_A) under cross-view (ablation)DAM2S · ACT42 cross-view action recognitionaccuracy (%): 68.86 -> 65.56Hurt
use SA-based regularizer (DAM2S_C) instead of MMD regularizer (DAM2S_A) cross-dataset (ablation)DAM2S · Hollywood 3D to Hollywood2 cross-dataset action recognitionaccuracy (%): 30.64 -> 39.17Improved
use SVM2K subproblem (DAM2S_B) instead of SVM subproblem (DAM2S_A) (ablation)DAM2S · Hollywood 3D to Hollywood2 cross-dataset action recognitiontraining time (s): 20.7 -> 168.4Hurt
replace DAM2S_A with DAM2S_C (ablation)DAM2S · Hollywood 3D to Hollywood2 cross-dataset action recognitiontraining time (s): 20.7 -> 398.2Hurt
use SVM2K (exploit depth with two classifiers) instead of KCCAmulti-view baselines · RGB-D Object to Caltech-256 object recognitionaccuracy (%): 31.52 -> 34.21Improved

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