Description

ImageNet (Deng et al., Russakovsky et al.) is the canonical large-scale image classification benchmark and the de facto pre-training corpus for modern computer vision backbones. In the vault its role is exclusively as the pre-training source for VGG / GoogLeNet / ResNet / ViT backbones that are then re-trained or fine-tuned for crowd counting, group counting, and CSI-vision fusion tasks.

Modality / size

  • Modality: still RGB images with class labels.
  • Scale: ~1.28M training images across 1000 classes (ILSVRC 2012 split).

Used by (papers)

  • Backbone pretraining for crowd counting (CTRN, Wei et al. 2020) and group counting (Singh AOE, GoogLeNet/VGGNet pretrained on ImageNet).
  • Cited as a reference open dataset that CSI-based behaviour-recognition datasets are aspired to match in scale.

Notes

  • Standard public benchmark; download via the ILSVRC release.
  • This note exists only because thesis-relevant papers use it as a backbone-pretraining reference; not used directly for CSI sensing.

9 vault papers evaluate on this dataset

Titles and DOIs only — no abstracts, no analyses.

  • A Survey on Human Behavior Recognition Using Channel State Information 2019 DOI ↗
  • Cross-Domain WiFi Sensing with Channel State Information: A Survey 2023 DOI ↗
  • SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing 2023 DOI ↗
  • Group Counting Using Micro-Doppler Signatures From a 77GHz FMCW Radar 2023 DOI ↗
  • A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects 2026 DOI ↗
  • Exposing the CSI: A Systematic Investigation of CSI-based Wi-Fi Sensing Capabilities and Limitations 2023 DOI ↗
  • Recent trends in crowd analysis: A review 2021 DOI ↗
  • MetAegis: Defend Against Physical-layer Wireless Sensing Leakage via Metasurface Obfuscation 2026 DOI ↗
  • Constructing WiFi-Video-Fused Multi-Modal Synthetic Datasets for Crowd Counting 2025 DOI ↗