AI Paper Atlas

Research map / Architectures and efficiency / CNN design

LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling

Zhen Li, Yukang Gan, Xiaodan Liang, Yizhou Yu, Hui Cheng, Liang Lin

ECCV 2016 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs · 181 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 the cross-layer connection of RGB conv features to the fused contexts (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 15.2 -> 48.1Improved
add the RGB path (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 15.8 -> 48.1Improved
add multi-scale RGB feature concatenation (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 42.1 -> 48.1Improved
add the depth path (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 43.7 -> 48.1Improved
add the memorized fusion layer (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 44.7 -> 48.1Improved
add the memorized context layers (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 45.7 -> 48.1Improved
add memorized layers (both context and fusion) versus none (ablation)LSTM-CF · SUNRGBDmean accuracy (%): 45.0 -> 48.1Improved
use separate memorized context layers per path instead of a single shared one before fusion (ablation)LSTM-CF · SUNRGBDmean accuracyImproved
LSTM-CF versus previous state of the artRGB-D scene labeling · SUNRGBD (37 classes)average Jaccard index (%): 45.9 -> 48.1Improved
LSTM-CF versus previous state of the artRGB-D scene labeling · NYUDv2 (37 classes)average Jaccard index (%): 43.9 -> 49.4Improved
LSTM-CF versus previous state of the artRGB-D scene labeling · SUN3D (12 classes)average Jaccard index (%): 45.7 -> 58.5Improved
LSTM-CF versus previous method on test speedRGB-D scene labeling · SUNRGBDseconds per image: 1.5 -> 0.15Improved

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