SOTAVerified

Object Categorization

Object categorization identifies which label, from a given set, best corresponds to an image region defined by an input image and bounding box.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 80 papers

TitleStatusHype
Learning Deep Visual Object Models From Noisy Web Data: How to Make it WorkCode0
Recurrent Convolutional Fusion for RGB-D Object RecognitionCode0
Systematic evaluation of CNN advances on the ImageNetCode0
Improved object recognition using neural networks trained to mimic the brain's statistical propertiesCode0
Cost-Effective Active Learning for Deep Image ClassificationCode0
Deep Fisher Kernels - End to End Learning of the Fisher Kernel GMM Parameters—0
Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition—0
A New Manifold Distance Measure for Visual Object Categorization—0
Cross-label Suppression: A Discriminative and Fast Dictionary Learning with Group Regularization—0
Best sources forward: domain generalization through source-specific nets—0
Show:102550
← PrevPage 3 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Unified-IOXLCategorization (ablation)61.7—Unverified
2GPV-2Categorization (ablation)54.7—Unverified
3CLIPCategorization (ablation)48.1—Unverified
4OFA_LargeCategorization (ablation)22.6—Unverified