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

Showing 17511800 of 2042 papers

TitleStatusHype
Convolutional Models for Joint Object Categorization and Pose Estimation0
Multimodal Skip-gram Using Convolutional Pseudowords0
Basic Level Categorization Facilitates Visual Object Recognition0
Hand-Object Interaction and Precise Localization in Transitive Action Recognition0
Visual7W: Grounded Question Answering in Images0
Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer0
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images0
Pixel-wise Segmentation of Street with Neural Networks0
Fast Neuromimetic Object Recognition using FPGA Outperforms GPU Implementations0
Regional Active Contours based on Variational level sets and Machine Learning for Image Segmentation0
Generic decoding of seen and imagined objects using hierarchical visual features0
PERCH: Perception via Search for Multi-Object Recognition and Localization0
Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization0
Better Exploiting OS-CNNs for Better Event Recognition in Images0
DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer0
Online Vision- and Action-Based Object Classification Using Both Symbolic and Subsymbolic Knowledge Representations0
Compression of Deep Neural Networks on the Fly0
Deep Trans-layer Unsupervised Networks for Representation Learning0
Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing0
Amodal Completion and Size Constancy in Natural Scenes0
Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection0
Analyzing structural characteristics of object category representations from their semantic-part distributions0
On Binary Classification with Single-Layer Convolutional Neural Networks0
DeepSat - A Learning framework for Satellite ImageryCode0
Hierarchical Deep Learning Architecture For 10K Objects Classification0
Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces0
Object Recognition from Short Videos for Robotic Perception0
Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions0
Generating Image Descriptions with Gold Standard Visual Inputs: Motivation, Evaluation and Baselines0
From the Virtual to the RealWorld: Referring to Objects in Real-World Spatial Scenes0
Domain Generalization for Object Recognition with Multi-task AutoencodersCode1
Partitioning Large Scale Deep Belief Networks Using Dropout0
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition0
Sublinear Partition EstimationCode0
Places205-VGGNet Models for Scene RecognitionCode0
HFirst: A Temporal Approach to Object Recognition0
Deep supervised learning for hyperspectral data classification through convolutional neural networksCode0
Thinning Algorithm Using Hypergraph Based Morphological Operators0
Multimodal Deep Learning for Robust RGB-D Object RecognitionCode0
Fourier descriptors based on the structure of the human primary visual cortex with applications to object recognition0
Multiscale Adaptive Representation of Signals: I. The Basic Framework0
Deep Learning and Music Adversaries0
Robot In a Room: Toward Perfect Object Recognition in Closed Environments0
Linking Entities Across Images and Text0
Describing Images using Inferred Visual Dependency Representations0
Occlusion Coherence: Detecting and Localizing Occluded FacesCode0
Natural Scene Recognition Based on Superpixels and Deep Boltzmann Machines0
A Novel Feature Extraction Method for Scene Recognition Based on Centered Convolutional Restricted Boltzmann Machines0
A Discriminative Representation of Convolutional Features for Indoor Scene Recognition0
Multi-path Convolutional Neural Networks for Complex Image ClassificationCode0
Show:102550
← PrevPage 36 of 41Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Imagenshape bias98.7Unverified
2Stable Diffusionshape bias92.7Unverified
3Partishape bias91.7Unverified
4ViT-22B-384shape bias86.4Unverified
5ViT-22B-560shape bias83.8Unverified
6CLIP (ViT-B)shape bias79.9Unverified
7ViT-22B-224shape bias78Unverified
8ResNet-50 (L2 eps 5.0 adv trained)shape bias69.5Unverified
9ResNet-50 (with strong augmentations)shape bias62.2Unverified
10SWSL (ResNeXt-101)shape bias49.8Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.55Unverified
2SSNNAccuracy (% )78.57Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.62Unverified
2SSNNAccuracy (% )79.25Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy18.75Unverified
2yunTop 5 Accuracy14.75Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24Unverified
2DYTop 5 Accuracy0.08Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24Unverified
2AJ2021Top 5 Accuracy27.68Unverified
#ModelMetricClaimedVerifiedStatus
1SSNNAccuracy (% )94.91Unverified
#ModelMetricClaimedVerifiedStatus
1Faster-RCNNmAP30.39Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )96Unverified