arXiv Computer Vision
Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 22
Event-Frame Fusion for Inter-Frame Segmentation via Event-Guided Motion
arXiv:2609.22500v1 Announce Type: new Abstract: Autonomous navigation requires precise and efficient semantic segmentation, yet existing frame-based approaches remain limited by motion blur, glare, l...
arXiv Computation and Language
Oct 8
SpikingVLA: Asynchronous Spiking Vision-Language-Action Models
arXiv:2610.09710v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical route toward energy-efficient spiking Vision-Language-Action (VLA) models by bypassing the substantial cost of...
arXiv AI
Sep 18
REACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal Perception
REACT is a fully spiking state‑space model that processes raw event‑camera data one event at a time, avoiding temporal accumulation and its associated delay. It employs a complex‑valued spiking neuron (C‑SiLIF) whose dynamics are driven by the inter‑event interval, enabling continuous‑time state updates at microsecond resolution. Evaluated on gesture recognition and time‑to‑collision estimation, REACT achieves low latency (4.6 ms) and high accuracy, supports anytime prediction, zero‑shot transfer, and INT8 quantization, dramatically reducing energy consumption.
arXiv Computer Vision
Oct 9
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
SV-TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of dense reconstruction in token‑selection methods. By integrating this primitive into a temporal action detection framework, the approach cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, it surpasses prior state‑of‑the‑art performance at roughly half the computational cost and naturally supports auxiliary task tokens for improved fine‑grained assembly detection on ATTACH.
Hugging Face Trending Papers
Oct 8
SV-TAD: Native Sparse Convs for Efficient Temporal Action Detection
SV‑TAD introduces native sparse 2D convolutions to enable convolutional adapters to operate directly on dynamically pruned token sets, addressing the inefficiency of existing adapters that do not reduce inference‑time computation. By integrating this primitive, SV‑TAD cuts VideoMAEv2‑L computation by up to 64% and achieves 2.2× faster inference while preserving state‑of‑the‑art accuracy on THUMOS‑14 and ActivityNet‑1.3. When applied to InternVideoNext‑L, the approach surpasses prior state‑of‑the‑art performance at roughly half the computational cost and also supports auxiliary task tokens, improving fine‑grained assembly detection on ATTACH.
arXiv AI
Aug 28
ANTShapes Benchmarking Datasets for Event-Based Neuromorphic Object Classification
The paper introduces four new event‑based vision datasets created with the ANTShapes simulation tool, designed to support object classification research using spiking neural networks (SNNs). These datasets vary in difficulty and are benchmarked against established spiking datasets such as N‑MNIST, CIFAR10‑DVS, DVSGesture, and POKER‑DVS using a convolutional SNN. The work provides detailed, high‑quality datasets for future experiments and validates ANTShapes as a suitable tool for generating event‑based vision data.