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 26–50 of 80 papers

TitleStatusHype
Improved object recognition using neural networks trained to mimic the brain's statistical propertiesCode0
Aligning Artificial Neural Networks to the Brain yields Shallow Recurrent Architectures—0
PCA-RECT: An Energy-efficient Object Detection Approach for Event Cameras—0
Humans can decipher adversarial images—0
Grassmannian Discriminant Maps (GDM) for Manifold Dimensionality Reduction with Application to Image Set Classification—0
Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection NetworkCode0
Best sources forward: domain generalization through source-specific nets—0
Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?—0
Data augmentation instead of explicit regularizationCode0
Recurrent Convolutional Fusion for RGB-D Object RecognitionCode0
Multiple Manifolds Metric Learning with Application to Image Set Classification—0
A Simple Riemannian Manifold Network for Image Set Classification—0
Visual Object Categorization Based on Hierarchical Shape Motifs Learned From Noisy Point Cloud Decompositions—0
VISER: Visual Self-Regularization—0
Convolutional Networks for Object Category and 3D Pose Estimation from 2D Images—0
Dual Skipping Networks—0
Enhanced Biologically Inspired Model for Image Recognition Based on a Novel Patch Selection Method with Moment—0
Are we done with object recognition? The iCub robot's perspectiveCode0
SimiNet: a Novel Method for Quantifying Brain Network Similarity—0
Cross-label Suppression: A Discriminative and Fast Dictionary Learning with Group Regularization—0
Weakly-Supervised Spatial Context Networks—0
Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networks—0
Object categorization in finer levels requires higher spatial frequencies, and therefore takes longer—0
Learning Deep Visual Object Models From Noisy Web Data: How to Make it WorkCode0
Emergence of Selective Invariance in Hierarchical Feed Forward Networks—0
Show:102550
← PrevPage 2 of 4Next →

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