SOTAVerified

Object Recognition

Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.

( Image credit: Tensorflow Object Detection API )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1101–1150 of 2042 papers

TitleStatusHype
Quantum Doubly Stochastic Transformers—0
Query Adaptive Similarity Measure for RGB-D Object Recognition—0
Radar-based Materials Classification Using Deep Wavelet Scattering Transform: A Comparison of Centimeter vs. Millimeter Wave Units—0
RadarLCD: Learnable Radar-based Loop Closure Detection Pipeline—0
Randomized Kernel Multi-view Discriminant Analysis—0
Ranking to Learn: Feature Ranking and Selection via Eigenvector Centrality—0
RAPTOR: Refined Approach for Product Table Object Recognition—0
RAVEN: A Dataset for Relational and Analogical Visual rEasoNing—0
Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data—0
RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation—0
Reading Ancient Coin Legends: Object Recognition vs. OCR—0
Achieving More Human Brain-Like Vision via Human EEG Representational Alignment—0
Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement—0
Real-time Monocular Object SLAM—0
Real Time Surveillance for Low Resolution and Limited-Data Scenarios: An Image Set Classification Approach—0
Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?—0
Reason from Context with Self-supervised Learning—0
Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition—0
Recognizing Objects From Any View With Object and Viewer-Centered Representations—0
Recognizing Objects In-the-wild: Where Do We Stand?—0
Recognizing Open-Vocabulary Relations between Objects in Images—0
Recognizing RGB Images by Learning from RGB-D Data—0
Recurrent 3D Attentional Networks for End-to-End Active Object Recognition—0
Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders—0
Recurrent Connectivity Aids Recognition of Partly Occluded Objects—0
Recurrent Convolutional Neural Network for Object Recognition—0
Recurrent Feedback Improves Recognition of Partially Occluded Objects—0
Recursive Counterfactual Deconfounding for Object Recognition—0
Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction—0
Reducing Bias in Production Speech Models—0
Reducing Label Effort: Self-Supervised meets Active Learning—0
Reducing Overconfidence Predictions for Autonomous Driving Perception—0
Reducing the False Positive Rate Using Bayesian Inference in Autonomous Driving Perception—0
Refining Neural Activation Patterns for Layer-Level Concept Discovery in Neural Network-Based Receivers—0
Reflection Invariant and Symmetry Detection—0
Regional Active Contours based on Variational level sets and Machine Learning for Image Segmentation—0
Region-Manipulated Fusion Networks for Pancreatitis Recognition—0
Regularized Evolutionary Algorithm for Dynamic Neural Topology Search—0
Regularizing Max-Margin Exemplars by Reconstruction and Generative Models—0
Regulation of Mouse Learning and Mood by the Anti-Inflammatory Cytokine Interleukin-10—0
Relative Afferent Pupillary Defect Screening through Transfer Learning—0
Reliable Attribute-Based Object Recognition Using High Predictive Value Classifiers—0
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering—0
Representational constraints underlying similarity between task-optimized neural systems—0
Representation Learning on Unit Ball with 3D Roto-Translational Equivariance—0
Resampling and super-resolution of hexagonally sampled images using deep learning—0
ResearchDoom and CocoDoom: Learning Computer Vision with Games—0
Reshaping Visual Datasets for Domain Adaptation—0
Resume Information Extraction via Post-OCR Text Processing—0
Revealing Bias Formation in Deep Neural Networks Through the Geometric Mechanisms of Human Visual Decoupling—0
Show:102550
← PrevPage 23 of 41Next →
All datasetsshape biasCIFAR10-DVSN-Caltech 101ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 GestureMECCANON-CARS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Imagenshape bias98.7—Unverified
2Stable Diffusionshape bias92.7—Unverified
3Partishape bias91.7—Unverified
4ViT-22B-384shape bias86.4—Unverified
5ViT-22B-560shape bias83.8—Unverified
6CLIP (ViT-B)shape bias79.9—Unverified
7ViT-22B-224shape bias78—Unverified
8ResNet-50 (L2 eps 5.0 adv trained)shape bias69.5—Unverified
9ResNet-50 (with strong augmentations)shape bias62.2—Unverified
10SWSL (ResNeXt-101)shape bias49.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.55—Unverified
2SSNNAccuracy (% )78.57—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.62—Unverified
2SSNNAccuracy (% )79.25—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy18.75—Unverified
2yunTop 5 Accuracy14.75—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2DYTop 5 Accuracy0.08—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2AJ2021Top 5 Accuracy27.68—Unverified
#ModelMetricClaimedVerifiedStatus
1SSNNAccuracy (% )94.91—Unverified
#ModelMetricClaimedVerifiedStatus
1Faster-RCNNmAP30.39—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )96—Unverified