On the Temporality for Sketch Representation Learning
Not on the map. Why?
Abstract (arXiv)
Sketches are simple human hand-drawn abstractions of complex scenes and real-world objects. Although the field of sketch representation learning has advanced significantly, there is still a gap in understanding the true relevance of the temporal aspect to the quality of these representations. This work investigates whether it is indeed justifiable to treat sketches as sequences, as well as which internal orders play a more relevant role. The results indicate that, although the use of traditional positional encodings is valid for modeling sketches as sequences, absolute coordinates consistently outperform relative ones. Furthermore, non-autoregressive decoders outperform their autoregressive counterparts. Finally, the importance of temporality was shown to depend on both the order considered and the task evaluated.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 3 Dec 2025.
Builds on
29 of 39 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2016Gaussian Error Linear Units (GELUs)cited by 3,431
- 2020Point Transformercited by 1,462
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
- 2018Self-Attention with Relative Position Representationscited by 1,112
- 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,085
17 more
- 2021E(n) Equivariant Graph Neural Networkscited by 951
- 2020On Layer Normalization in the Transformer Architecturecited by 906
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2015Sequence Level Training with Recurrent Neural Networkscited by 568
- 2017Non-Autoregressive Neural Machine Translationcited by 457
- 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
- 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
- 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
- 2017A Neural Representation of Sketch Drawingscited by 311
- 2023CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Notcited by 79
- 2020Sketchformer: Transformer-based Representation for Sketched Structurecited by 78
- 2020Group Equivariant Stand-Alone Self-Attention For Visioncited by 63
- 2020B'ezierSketch: A generative model for scalable vector sketchescited by 43
- 2021Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwritingcited by 38
- 2018Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Mattercited by 18
- 2021Cloud2Curve: Generation and Vectorization of Parametric Sketchescited by 16
- 2024SketchINR: A First Look into Sketches as Implicit Neural Representationscited by 13
Built on by
Citing papers per year: 2026: 1.
1 paper.