AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data

Yin Zheng, Yu‐Jin Zhang, Hugo Larochelle

TPAMI 2016 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 61 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 class-label supervision to DocNADE (SupDocNADE)DocNADE · LabelMeaccuracy (%): 81.97 -> 83.43Improved
add class-label supervision to DocNADE (SupDocNADE)DocNADE · UIUC-Sportsaccuracy (%): 74.23 -> 77.29Improved
add class-label supervision to DocNADE (SupDocNADE)DocNADE · LabelMeannotation F-measure (%): 43.32 -> 43.87No clear effect
add class-label supervision to DocNADE (SupDocNADE)DocNADE · UIUC-Sportsannotation F-measure (%): 46.38 -> 46.95No clear effect
SupDocNADE instead of sLDA for annotationsLDA · LabelMeannotation F-measure (%): 38.7 -> 43.87Improved
SupDocNADE instead of sLDA for annotationsLDA · UIUC-Sportsannotation F-measure (%): 35.0 -> 46.95Improved
use SupDocNADE instead of MMLDA for annotation on LabelMeMMLDA · LabelMeannotation F-measure (%): 46.64 -> 43.87Hurt
add spatial 2x2 grid and tuned generative weight lambda (ablation)SupDocNADE · LabelMe and UIUC-SportsaccuracyMixed
add more hidden layers (2 instead of 1), 625 epochs pretraining (ablation)SupDeepDocNADE · MIR FlickrMAP: 0.654 -> 0.671Improved
add third hidden layer, 625 epochs pretraining (ablation)SupDeepDocNADE · MIR FlickrMAP: 0.671 -> 0.670No clear effect
add third hidden layer, 4125 epochs pretraining (ablation)SupDeepDocNADE · MIR FlickrMAP: 0.684 -> 0.691Improved
increase unsupervised pretraining from 625 to 4125 epochs (3 layers) (ablation)SupDeepDocNADE · MIR FlickrMAP: 0.670 -> 0.691Improved

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