← Back to all news
arXiv Computer Vision By Pengzhi Zhong, Jiwei Mo, Haolun Li, Ge Zheng, Jingqi Wang, Xinyi Bo, Shuiwang Li

SBMVTrack: Spike-Budgeted Multi-View Learning for Energy-Efficient UAV Tracking

Read the original on arXiv Computer Vision →

SBMVTrack is a fully spiking neural network framework designed for energy-efficient UAV visual tracking. It introduces Energy-Weighted Spike Budgeting (EWSB) to constrain spike activity based on computational cost, and Masked Multi-View Target Modeling (MVTM) to enhance target representation by leveraging correlated temporal views. Experiments on multiple benchmarks show that SBMVTrack reduces spike firing rates and theoretical energy consumption while maintaining competitive tracking accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 27

STATrack: A Target-Aware Fully Spiking Neural Network for Efficient UAV Tracking

STATrack is a fully spiking neural network designed for UAV visual tracking using only RGB inputs, eliminating the need for costly event cameras. It introduces Adaptive Mutual Information Maximization (AMIM) to preserve fine-grained target information in deep spiking representations and a sample-difficulty-aware dynamic weighting strategy to adjust the mutual‑information constraint during training. Experiments on four UAV tracking benchmarks show that STATrack achieves state‑of‑the‑art performance while maintaining low theoretical energy consumption.

By Pengzhi Zhong, Jiwei Mo, Dan Zeng, Feixiang He, Shuiwang Li
benchmarks
More like this →
arXiv Computer Vision
Sep 17

Mask IPL: Noise-Free Intrinsic Position Learning via Computation Graph Clipping for Event-Based Spike-Driven Tracking

Mask IPL introduces a Computation Graph Clipping technique that removes noise from Intrinsic Position Learning (IPL) in spiking neural networks for event-based tracking. By applying a validity mask to each layer, the method aligns forward and backward propagation with ideal gradients without adding parameters. Experiments show that Mask IPL consistently improves tracking performance on Tiny‑scale and Base‑scale benchmarks such as FE108, FELT, and VisEvent.

By Yimeng Shan, Malu Zhang
More like this →
arXiv AI
Jul 15

Burst Spiking Neural Networks

arXiv:2607. 11914v1 Announce Type: cross Abstract: A central goal of current Spiking Neural Network (SNN) research is to improve their accuracy toward becoming low-power alternatives to Artificial Neural Networks (ANNs).

By Jiahong Zhang, Sijun Shen, Man Yao, Han Xu, Mingqiang Huang, Yonghong Tian, Bo Xu, Guoqi Li
efficiencybenchmarks
More like this →
Hugging Face Trending Papers
Jun 1

Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization

Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learnable prompts at the input level. However, existing VP methods typically employ dense pixel-level prompts, which often suffer from redundant perturbations, limited generalization and energy inefficiency.

llmsbenchmarks
More like this →
arXiv Computation and Language
3d ago

Spike-driven Vision-Language-Action Model

arXiv:2609.39514v1 Announce Type: new Abstract: Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. How...

By Shuai Wang, Malu Zhang, Mingquan Liu, Weihui Dai, Dehao Zhang, Jieyuan Zhang, Yimeng Shan, Zijian Zhou, Yang Yang
llmsragroboticsmultimodal
More like this →