Research map / Architectures and efficiency / Spiking networks
Time-Ordered Recent Event (TORE) Volumes for Event Cameras
R. Wes Baldwin, Ruixu Liu, Mohammed Almatrafi, Vijayan K. Asari, Keigo Hirakawa
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace EDnCNN representation with a 9x9x14 TORE volume | denoising CNN · DVSNOISE20 | RPMD: 50.0 -> 43.6 | Improved |
| use TORE denoiser instead of raw noisy events | event denoising · DVSNOISE20 | RPMD: 222.0 -> 43.6 | Improved |
| TORE vs EDnCNN on LabFast scene | denoising CNN · DVSNOISE20 LabFast | RPMD: 61 -> 67 | Hurt |
| TORE-based U-Net instead of E2VID | image reconstruction · ECD | MSE: 0.06 -> 0.05 | Improved |
| TORE-based U-Net instead of E2VID | image reconstruction · ECD | SSIM: 0.56 -> 0.55 | No clear effect |
| use TORE volumes with GoogLeNet instead of IETS | classification · N-CARS | accuracy: 0.976 -> 0.977 | Improved |
| use TORE volumes instead of SLAYER SNN | classification · SL-ANIMALS-DVS | accuracy: 0.780 -> 0.851 | Improved |
| use TORE volumes instead of RG-CNN | classification · ASL-DVS | accuracy: 0.901 -> 0.996 | Improved |
| use TORE volumes instead of Event Clouds | classification · DVS128 Gesture | accuracy: 0.953 -> 0.962 | Improved |
| percentage split instead of 15 samples per class test | TORE classifier · N-Caltech101 | accuracy: 79.8% -> 83.4% | Improved |
| replace DHP19 representation with TORE volumes (camera 2) | 2D pose CNN · DHP19 | MPJPE (pixels): 7.18 -> 5.07 | Improved |
| replace DHP19 representation with TORE volumes (camera 3) | 2D pose CNN · DHP19 | MPJPE (pixels): 6.87 -> 5.77 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SLAYER — SLAYER: Spike Layer Error Reassignment in Time (NeurIPS 2018) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Events-To-Video: Bringing Modern Computer Vision to Event Cameras (CVPR 2019 · similarity 0.87)
- High Speed and High Dynamic Range Video with an Event Camera (TPAMI 2019 · similarity 0.87)
- EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · similarity 0.86)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.85)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.85)
- State Space Models for Event Cameras (CVPR 2024 · similarity 0.84)
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.
