Research map / Detection and segmentation / Tracking
DART: Distribution Aware Retinal Transform for Event-based Cameras
Bharath Ramesh, Hong Yang, Garrick Orchard, Ngoc Anh Le Thi, Shihao Zhang, Cheng Xiang
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 HATS with DART descriptors | bag-of-words classifier · N-Caltech101 | accuracy (%): 64.20 -> 66.42 | Improved |
| replace HATS with DART descriptors | bag-of-words classifier · N-MNIST | accuracy (%): 99.10 -> 97.95 | Hurt |
| replace HATS with DART | classifier · CIFAR10-DVS | accuracy (%): 52.40 -> 65.78 | Improved |
| replace HATS with DART | classifier · MNIST-DVS | accuracy (%): 98.40 -> 98.51 | No clear effect |
| restrict events to object outline annotations (ablation) | DART classifier · N-Caltech101 | accuracy (%): 66.42 -> 70.33 | Improved |
| use three-level SPM grid instead of two-level (ablation) | DART classifier · N-MNIST | accuracy | Improved |
| increase codebook size (ablation) | DART classifier · N-MNIST | accuracy | Improved |
| increase maximum radius of log-polar grid (ablation) | DART descriptor · N-Caltech101 | accuracy | Hurt |
| train on scale-4 and 8 and test on scale-16 with fixed grid | DART classifier · MNIST-DVS | accuracy (%): 98.51 -> 24.42 | Hurt |
Later papers that compared with this method
1 later accepted paper reports DART as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Event-based Asynchronous Sparse Convolutional Networks (ECCV 2020 · better on 1 of 1 shared result)
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.
- HATS — HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification (CVPR 2018) · better on 3 of 4 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
- Recurrent Vision Transformers for Object Detection With Event Cameras (CVPR 2023 · similarity 0.88)
- End-to-End Learning of Object Motion Estimation from Retinal Events for Event-Based Object Tracking (AAAI 2020 · similarity 0.87)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · similarity 0.87)
- TTAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events (CVPR 2026 · similarity 0.86)
- SODFormer: Streaming Object Detection With Transformer Using Events and Frames (TPAMI 2023 · similarity 0.86)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · 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.
