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 1–10 of 2042 papers

TitleStatusHype
GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing—0
Out-of-distribution detection in 3D applications: a review—0
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point CloudsCode0
Continual Hyperbolic Learning of Instances and Classes—0
DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects—0
Aligning Text, Images, and 3D Structure Token-by-Token—0
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous DrivingCode1
Feature-Based Lie Group Transformer for Real-World Applications—0
EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects—0
Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness—0
Show:102550
← PrevPage 1 of 205Next →
All datasetsshape biasCIFAR10-DVSN-Caltech 101ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 GestureMECCANON-CARS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2DYTop 5 Accuracy0.08—Unverified