AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

SDTrack: A Baseline for Event-based Tracking via Spiking Neural Networks

Yimeng Shan, Zhenbang Ren, Haodi Wu, Wenjie Wei, Rui-Jie Zhu, Shuai Wang, Dehao Zhang, Yichen Xiao, Jieyuan Zhang, Kexin Shi, Jingzhinan Wang, Jason K. Eshraghian and 2 more

CVPR 2026 · Architectures and efficiency › Spiking networks · approach: Event-camera spiking networks · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Intrinsic Position Learning (IPL) (ablation)SDTrack-Tiny · FE108PR (%): 89.66 -> 91.30Improved
add extra positional encoding on top of IPL (ablation)SDTrack-Tiny · FE108AUC (%): 59.00 -> 58.79 (learnable), 58.57 (sinusoidal)Hurt
enlarge template-search intersection to 128 (ablation)SDTrack-Tiny · FE108AUC (%): 59.00 -> 43.91Hurt
use center head instead of corner head (ablation)SDTrack-Tiny · FE108AUC (%): 58.81 -> 59.00Improved
add ImageNet-1K pretraining (ablation)SDTrack-Tiny · FE108AUC (%): 47.80 -> 59.00Improved
use SDTrack backbone instead of Spike-driven Transformer V1 (ablation)SDTrack-Tiny · FE108AUC (%): 52.4 -> 59.0Improved
use SDTrack backbone instead of Spike-driven Transformer V3 (ablation)SDTrack-Tiny · FE108AUC (%): 58.9 -> 59.0No clear effect
add spike neuron before conv in decision layer (ablation)SDTrack-Tiny · FE108PR (%): 91.3 -> 90.4Hurt
scale from SDTrack-Tiny to SDTrack-BaseSDTrack · VisEventAUC (%): 35.6 -> 37.4Improved
use T=2x2 LIF/I-LIF neurons instead of 1x4 I-LIFSDTrack-Tiny · FELTAUC (%): 39.3 -> 35.7Hurt
use GTP event aggregation instead of other aggregation methodsfive trackers · FE108AUCImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy