AI Paper Atlas

Research map / 3D vision / Face and shape

Shapeglot: Learning Language for Shape Differentiation

Panos Achlioptas, Judy Fan, Robert Hawkins, Noah Goodman, Leonidas J. Guibas

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 72 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 image input to point-cloud inputbaseline listener · CiC object generalizationaccuracy: 66.4 -> 77.4Improved
use both images and point clouds instead of images onlybaseline listener · CiC object generalizationaccuracy: 77.4 -> 78.9Improved
add word attention (ablation)baseline listener with both modalities · CiC object generalizationaccuracy: 78.9 -> 79.6Improved
add word attention (ablation)baseline listener with point clouds only · CiC object generalizationaccuracy: 66.4 -> 65.6No clear effect
share weights across objects (Baseline) instead of Combined-Interpretation (ablation)listener · CiC object generalizationaccuracy: 75.9 -> 79.6Improved
add explicit context encoding (Early-Context) (ablation)Baseline listener · CiC object generalizationaccuracy: 79.6 -> 79.4No clear effect
ground LSTM with images and add point clouds late rather than the reverse (ablation)listener · CiCaccuracy: +4.8% on averageImproved
add dropout and L2 regularization (ablation)listener · CiCaccuracy: ~10%Improved
add label smoothing (ablation)listener · CiCaccuracy: ~2%Improved
lesion the mentioned part in the input (ablation)image-only listener · CiC part-lesion subset (image-only listener)accuracy: 77.4 -> 42.8Hurt
lesion a random part in the input (ablation)image-only listener · CiC part-lesion subset (image-only listener)accuracy: 77.4 -> 67.0Hurt
make the speaker pragmatic (rerank with internal listener)literal image speaker · CiC human listenersaccuracy: 68.3 -> 78.7Improved

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