Research map / Detection and segmentation / CNN features
HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use HATS instead of HOTS | Event-based object classification · N-MNIST | accuracy: 0.808 -> 0.991 | Helped |
| Use HATS instead of HOTS | Event-based object classification · N-Caltech101 | accuracy: 0.210 -> 0.642 | Helped |
| Use HATS instead of HOTS | Event-based object classification · MNIST-DVS | accuracy: 0.803 -> 0.984 | Helped |
| Use HATS instead of HOTS | Event-based object classification · CIFAR10-DVS | accuracy: 0.271 -> 0.524 | Helped |
| Use HATS instead of Gabor-SNN | Event-based object classification · N-CARS | accuracy: 0.789 -> 0.902 | Helped |
| Use HATS instead of Gabor-SNN | Event-based object classification · N-CARS | AUC: 0.735 -> 0.945 | Helped |
| Use HATS instead of HOTS | Event-based feature extraction · N-CARS | average computation time per sample: 157.57 -> 7.28 | Helped |
| Use HATS instead of Gabor-SNN | Event-based feature extraction · N-CARS | average computation time per sample: 285.95 -> 7.28 | Helped |
| Add a local-memory time surface that accumulates a temporal window of past events instead of using only the last event (ablation) | HATS representation · Object classification | accuracy | Helped |
| Add block normalization (ablation) | HATS on N-CARS · N-CARS | accuracy | No clear effect |
| Use smaller cell size K (ablation) | HATS · Low-resolution inputs | accuracy | Helped |
Closest papers by meaning
- EventPillars: Pillar-based Efficient Representations for Event Data (AAAI 2025 · similarity 0.86)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.86)
- Flow-Event Autoencoder: Event Stream Object Recognition Dataset Generation with Arbitrary High Temporal Resolution (AAAI 2024 · similarity 0.86)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.86)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.85)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.