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

computer-vision-11

Sketch Recognition

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sketch-recognition-11

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find sketch-recognition-11 models and implementations

Datasets

Quick, Draw! Dataset

ShoeV2

AtyPict

Subtasks

No subtasks available.

Most implemented papers

Sketch-a-Net that Beats Humans

T. Xiang, Timothy M. Hospedales, Yongxin Yang, Yi-Zhe Song, Qian Yu•Thu Jan 29 2015

A multi-scale multi-channel deep neural network framework that yields sketch recognition performance surpassing that of humans, and not only delivers the best performance on the largest human sketch dataset to date, but also is small in size making efficient training possible using just CPUs.

241

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

From paper to machine: extracting strokes from images for use in sketch recognition

Pankaj Rajan, T. Hammond•Tue Jun 10 2008

A stroke-tracing algorithm that can be used to extract stroke data from the pixilated image of the sketch drawn on paper and handles overlapping strokes and also attempts to capture sequencing information, which is helpful in many sketch recognition techniques.

21 0

Paper Graph

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

T. Xiang, Timothy M. Hospedales, Yi-Zhe Song, Zhanyu Ma, Jun Guo, Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang•Sun Feb 18 2018

This work proposes a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset and shows that state-of-the-art hashing models specifically engineered for static images fail to perform well on temporal sketch data.

121 0

Paper Graph

Distribution-Aware Binarization of Neural Networks for Sketch Recognition

A. Namboodiri, Ameya Prabhu, Vishal Batchu, Sri Aurobindo Munagala, Rohit Gajawada•Sun Mar 11 2018

This work presents a highly generalized, distribution-aware approach to binarizing deep networks that allows us to retain the advantages of a binarized network, while reducing accuracy drops.

5 0

Paper Graph

Sketch-BERT: Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Learning of Sketch Gestalt

Yu-Gang Jiang, Yanwei Fu, X. Xue, Hangyu Lin•Mon May 18 2020

This work presents a model of learning Sketch Bidirectional Encoder Representation from Transformer (Sketch-BERT), and generalizes BERT to sketch domain, with the novel proposed components and pre-training algorithms, including the newly designed sketch embedding networks, and the self-supervised learning of sketch gestalt.

76 0

Paper Graph

Edge Augmentation for Large-Scale Sketch Recognition without Sketches

Giorgos Tolias, Ondřej Chum, Nikos Efthymiadis•Fri Feb 25 2022

This work addresses scaling up the sketch classification task into a large number of categories by overcoming the lack of training sketch data by exploiting labeled collections of natural images that are easier to obtain by introducing Randomization in the parameters of edge detection and edge selection.

7 0

Paper Graph

Abstracting Sketches through Simple Primitives

Zeynep Akata, Anjan Dutta, Massimiliano Mancini, Stephan Alaniz, D. Marcos•Tue Jul 26 2022

The Primitive-Matching Network (PMN), learns interpretable abstractions of a sketch in a self supervised manner and empirically achieves the highest performance on sketch recognition and sketch-based image retrieval given a communication budget, while at the same time being highly interpretable.

15 0

Paper Graph

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

Kushin Mukherjee, Holly Huey, Xuanchen Lu, Yael Vinker, Rio Aguina-Kang, Ariel Shamir, Judith E. Fan•Mon Dec 04 2023

SEVA is introduced, a new benchmark dataset containing approximately 90K human-generated sketches of 128 object concepts produced under different time constraints, and thus systematically varying in sparsity, to explore the potential of models that emulate human visual abstraction in generative tasks.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.

Sketch Recognition | State-of-the-Art