AI Paper Atlas

Research map / Video / Video segmentation and tracking

STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling

Yang He, Wei-Chen Chiu, Margret Keuper, Mario Fritz

CVPR 2017 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 134 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
Add superpixels to the single-frame FCN (ablation)FCN · NYUDv2 40-classMean IoU: 34.0 -> 36.0Improved
Train with additional unlabeled frames (ablation)STD2P superpixel · NYUDv2 40-classMean IoU: 36.0 -> 38.1Improved
Use multiple views at test time (ablation)STD2P superpixel+ · NYUDv2 40-classMean IoU: 38.1 -> 40.1Improved
Replace average temporal pooling with max pooling (ablation)STD2P full model · NYUDv2 40-classMean IoU: 40.1 -> 38.0Hurt
Replace average spatial pooling with max pooling (ablation)STD2P full model · NYUDv2 40-classMean IoU: 40.1 -> 33.8Hurt
Replace both average pooling operations with max pooling (ablation)STD2P full model · NYUDv2 40-classMean IoU: 40.1 -> 32.1Hurt
Use region correspondences rather than pixel correspondences (ablation)Multi-view FCN segmentation · NYUDv2 40-classMean IoU: 34.6 -> 40.1Improved
Use wider and future views (ablation)STD2P multi-view prediction · NYUDv2 40-classMean IoUImproved
Add multi-view test-time information (ablation)STD2P superpixel+ · SUN3D 33-classMean IoU: +3.5ppImproved
Use superpixel-based partial-label training (ablation)FCN · SUN3D 33-classMean IoU: +3.3ppImproved
Use STD2P multi-view pooling (ablation)STD2P full model · NYUDv2 4-classPixel Acc.: 82.7 -> 83.6Improved
Use STD2P multi-view pooling (ablation)STD2P superpixel+ · NYUDv2 13-classMean Acc.: 67.0 -> 68.4Improved

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