Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Object Recognition

3260 papers • 126 benchmarks • 313 datasets

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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in object-recognition

Trend

Dataset

Best Model

Actions

MECCANO

MECCANO

ObjectNet (ImageNet classes, trained on ImageNet)

ObjectNet (ImageNet classes, trained on ImageNet)

Libraries

i

Use these libraries to find object-recognition models and implementations

peymanbateni/simple-cnaps

3 papers 110

Datasets

CIFAR-10

ImageNet

CORe50

N-CARS

SUN Attribute

OCID

Subtasks

3D Object Recognition Continuous Object Recognition Depiction Invariant Object Recognition

Most implemented papers

Densely Connected Convolutional Networks

Kilian Q. Weinberger, Zhuang Liu, Gao Huang•Wed Aug 24 2016

The Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion, and has several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.

41544

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

ObjectNet (ImageNet classes)

ObjectNet (ImageNet classes)

ObjectNet (All classes)

ObjectNet (All classes)

plai-group/simple-cnaps

3 papers 49

open-mmlab/mmdetection

2 papers 27,643

2 papers 15,375

PaddlePaddle/PaddleDetection

2 papers 12,008

open-mmlab/mmpose

2 papers 4,946

Deci-AI/super-gradients

2 papers 4,314

ContinualAI/avalanche

2 papers 1,654

KaiyangZhou/Dassl.pytorch

2 papers 1,072

ppengtang/pcl.pytorch

2 papers 245

dicarlolab/vonenet

2 papers 107

EV-IMO

EV-IMO

Washington RGB-D

Washington RGB-D

MECCANO

N-ImageNet

0

Going deeper with convolutions

Christian Szegedy, D. Erhan, Vincent Vanhoucke, Yangqing Jia, P. Sermanet, Andrew Rabinovich, Scott E. Reed, Dragomir Anguelov, Wei Liu•Mon Sep 15 2014

A deep convolutional neural network architecture codenamed Inception is proposed that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).

46416 0

Residual Attention Network for Image Classification

Xiaogang Wang, Xiaoou Tang, Fei Wang, Shuo Yang, C. Qian, Cheng Li, Honggang Zhang, Mengqing Jiang•Sat Apr 22 2017

The proposed Residual Attention Network is a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion and can be easily scaled up to hundreds of layers.

3563 0

Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

William Lotter, David D. Cox, Gabriel Kreiman•Tue May 24 2016

The results suggest that prediction represents a powerful framework for unsupervised learning, allowing for implicit learning of object and scene structure.

968 0

Finding Tiny Faces

Deva Ramanan, Peiyun Hu•Mon Dec 12 2016

The role of scale in pre-trained deep networks is explored, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges and demonstrating state-of-the-art results on massively-benchmarked face datasets.

771 0

Describing Textures in the Wild

A. Vedaldi, Iasonas Kokkinos, Subhransu Maji, Mircea Cimpoi, S. Mohamed•Wed Nov 13 2013

This work identifies a vocabulary of forty-seven texture terms and uses them to describe a large dataset of patterns collected "in the wild", and shows that they both outperform specialized texture descriptors not only on this problem, but also in established material recognition datasets.

3253 0

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Kaiming He, X. Zhang, Shaoqing Ren•Tue Jun 17 2014

This work equips the networks with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale.

12301 0

Microsoft COCO: Common Objects in Context

C. L. Zitnick, P. Perona, Serge J. Belongie, Piotr Dollár, M. Maire, James Hays, Tsung-Yi Lin, Deva Ramanan•Wed Apr 30 2014

A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.

50075 0

Texture Synthesis Using Convolutional Neural Networks

M. Bethge, Alexander S. Ecker, Leon A. Gatys•Tue May 26 2015

A new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition is introduced, showing that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit.

1419 0

Striving for Simplicity: The All Convolutional Net

Martin A. Riedmiller, T. Brox, Alexey Dosovitskiy, Jost Tobias Springenberg•Sat Dec 20 2014

It is found that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks.

4926 0

Adding a benchmark result helps the community track progress.

Object Recognition | State-of-the-Art