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
Salient Explanation for Fine-grained Classification—0
V1Net: A computational model of cortical horizontal connections—0
PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION—0
Temporal-Coded Deep Spiking Neural Network with Easy Training and Robust PerformanceCode0
Towards Interpreting Recurrent Neural Networks through Probabilistic AbstractionCode0
Simultaneous Segmentation and Recognition: Towards more accurate Ego Gesture Recognition—0
Task-Aware Monocular Depth Estimation for 3D Object DetectionCode0
Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition—0
Performance Evaluation of Learned 3D Features—0
A Dual-hierarchy Semantic Graph for Robust Object Recognition—0
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNsCode0
FoodTracker: A Real-time Food Detection Mobile Application by Deep Convolutional Neural NetworksCode0
Recurrent Connectivity Aids Recognition of Partly Occluded Objects—0
Foveated Downsampling Techniques—0
The Natural Tendency of Feed Forward Neural Networks to Favor Invariant Units—0
Significance of feedforward architectural differences between the ventral visual stream and DenseNet—0
How well do deep neural networks trained on object recognition characterize the mouse visual system?—0
Dual-attention Focused Module for Weakly Supervised Object Localization—0
DaTscan SPECT Image Classification for Parkinson's Disease—0
TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion—0
New Graph-based Features For Shape Recognition—0
Exploring Temporal Differences in 3D Convolutional Neural Networks—0
Detecting Deep Neural Network Defects with Data Flow Analysis—0
Iterative Clustering with Game-Theoretic Matching for Robust Multi-consistency Correspondence—0
Topologically-Guided Color Image Enhancement—0
Performance comparison of 3D correspondence grouping algorithm for 3D plant point clouds—0
Story-oriented Image Selection and Placement—0
EBPC: Extended Bit-Plane Compression for Deep Neural Network Inference and Training AcceleratorsCode0
Multi-stage Deep Classifier Cascades for Open World RecognitionCode0
BIM-assisted object recognition for the on-site autonomous robotic assembly of discrete structures—0
Instance Scale Normalization for image understanding—0
Demonstration of 3D ISAR Security Imaging at 24GHz with a Sparse MIMO Array—0
Detecting semantic anomaliesCode0
Relative Afferent Pupillary Defect Screening through Transfer Learning—0
Image Captioning with Unseen Objects—0
Look Further to Recognize Better: Learning Shared Topics and Category-Specific Dictionaries for Open-Ended 3D Object Recognition—0
SceneGraphNet: Neural Message Passing for 3D Indoor Scene AugmentationCode2
Filter Bank Regularization of Convolutional Neural Networks—0
Self-supervised Domain Adaptation for Computer Vision TasksCode0
Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?—0
Real-Time Correlation Tracking via Joint Model Compression and TransferCode0
Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images—0
ImageNet-trained deep neural network exhibits illusion-like response to the Scintillating Grid—0
Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders—0
Discriminative Embedding Autoencoder with a Regressor Feedback for Zero-Shot Learning—0
Human Pose Estimation for Real-World Crowded ScenariosCode0
Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects—0
Rehearsal-Free Continual Learning over Small Non-I.I.D. BatchesCode1
A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching—0
Region-Manipulated Fusion Networks for Pancreatitis Recognition—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