mlsanityData to 13 Oct 2026

HaSPeR: An Image Repository for Hand Shadow Puppet Recognition

arXiv 2408.10360 ↗First posted 19 Aug 2024cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Hand shadow puppetry, also known as shadowgraphy or ombromanie, is a form of theatrical art and storytelling where hand shadows are projected onto flat surfaces to create illusions of living creatures. The skilled performers create these silhouettes by hand positioning, finger movements, and dexterous gestures to resemble shadows of animals and objects. Due to the lack of practitioners and a seismic shift in people's entertainment standards, this art form is on the verge of extinction. To facilitate its preservation and proliferate it to a wider audience, we introduce rm Hsmall ASPsmall ER, a novel dataset consisting of 15,000 images of hand shadow puppets across 15 classes extracted from both professional and amateur hand shadow puppeteer clips. We provide a detailed statistical analysis of the dataset and employ a range of pretrained image classification models to establish baselines. Our findings show a substantial performance superiority of skip-connected convolutional models over attention-based transformer architectures. We also find that lightweight models, such as MobileNetV2, suited for mobile applications and embedded devices, perform comparatively well. We surmise that such low-latency architectures can be useful in developing ombromanie teaching tools, and we create a prototype application to explore this surmission. Keeping the best-performing model ResNet34 under the limelight, we conduct comprehensive feature-spatial, explainability, and error analyses to gain insights into its decision-making process and explore architectural improvements. To the best of our knowledge, this is the first documented dataset and research endeavor to preserve this dying art for future generations, with computer vision approaches. Our code and data are publicly available at https://github.com/Starscream-11813/HaSPeR.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 32 of its 79 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

32 of 79 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  5. 2017Mask R-CNNcited by 7,266
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  7. 2016Densely Connected Convolutional Networkscited by 6,707
  8. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,426
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  10. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,055
  11. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,786
  12. 2014Going Deeper with Convolutionscited by 4,239
20 more
  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,836
  2. 2022A ConvNet for the 2020scited by 3,563
  3. 2016Wide Residual Networkscited by 3,063
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,544
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,360
  6. 2019Searching for MobileNetV3cited by 1,990
  7. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,219
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,134
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,130
  10. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,058
  11. 2020Designing Network Design Spacescited by 956
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 941
  13. 2024KAN: Kolmogorov-Arnold Networkscited by 641
  14. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  15. 2014One weird trick for parallelizing convolutional neural networkscited by 264
  16. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 79
  17. 2024Convolutional Kolmogorov-Arnold Networkscited by 76
  18. 2021A Deep Learning-based Multimodal Depth-Aware Dynamic Hand Gesture Recognition Systemcited by 5
  19. 2023From paintbrush to pixel: A review of deep neural networks in AI-generated artcited by 5
  20. 2023Image Classification using Combination of Topological Features and Neural Networkscited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditionscited by 9
  2. 2025DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Datacited by 4
  3. 2026SpectroFusion-ViT: A Lightweight Transformer for Speech Emotion Recognition Using Harmonic Mel-Chroma Fusioncited by 0
  4. 2026Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractorscited by 0
  5. 2026Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memescited by 0