Sketch Input Method Editor: A Comprehensive Dataset and Methodology for Systematic Input Recognition
Not on the map. Why?
Abstract (arXiv)
With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction. While previous research has focused on tasks such as recognition, retrieval, and generation of familiar everyday objects, this study aims to create a Sketch Input Method Editor (SketchIME) specifically designed for a professional C4I system. Within this system, sketches are utilized as low-fidelity prototypes for recommending standardized symbols in the creation of comprehensive situation maps. This paper also presents a systematic dataset comprising 374 specialized sketch types, and proposes a simultaneous recognition and segmentation architecture with multilevel supervision between recognition and segmentation to improve performance and enhance interpretability. By incorporating few-shot domain adaptation and class-incremental learning, the network's ability to adapt to new users and extend to new task-specific classes is significantly enhanced. Results from experiments conducted on both the proposed dataset and the SPG dataset illustrate the superior performance of the proposed architecture. Our dataset and code are publicly available at https://github.com/GuangmingZhu/SketchIME.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 48 references that are in the map. First posted on arXiv 30 Nov 2023.
Builds on
28 of 48 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2014Conditional Generative Adversarial Netscited by 2,162
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
- 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
- 2017A Neural Representation of Sketch Drawingscited by 313
- 2020Few-Shot Class-Incremental Learningcited by 251
- 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
- 2016Correlation Alignment for Unsupervised Domain Adaptationcited by 147
- 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 96
16 more
- 2022Constrained Few-shot Class-incremental Learningcited by 94
- 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
- 2020Deep Learning for Free-Hand Sketch: A Surveycited by 59
- 2015Sketch-based 3D Shape Retrieval using Convolutional Neural Networkscited by 41
- 2020Domain-Adaptive Few-Shot Learningcited by 40
- 2018SketchMate: Deep Hashing for Million-Scale Human Sketch Retrievalcited by 35
- 2019Multi-Graph Transformer for Free-Hand Sketch Recognitioncited by 35
- 2021Cloud2Curve: Generation and Vectorization of Parametric Sketchescited by 16
- 2018Universal Perceptual Groupingcited by 14
- 2018Fast Sketch Segmentation and Labeling with Deep Learningcited by 9
- 2016Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognitioncited by 3
- 2017SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networkscited by 3
- 2017Object category understanding via eye fixations on freehand sketchescited by 2
- 2017Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognitioncited by 2
- 2018Distribution-Aware Binarization of Neural Networks for Sketch Recognitioncited by 1
- 2021Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognitioncited by 1
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.