Related papers: Spatio-Temporal State Space Model For Efficient Ev…

Inaccurate optical flow estimates in and near occluded regions, and out-of-boundary regions are two of the current significant limitations of optical flow estimation algorithms. Recent state-of-the-art optical flow estimation algorithms are…

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with…

Event-based cameras are raising interest within the computer vision community. These sensors operate with asynchronous pixels, emitting events, or "spikes", when the luminance change at a given pixel since the last event surpasses a certain…

Event-based camera has emerged as a promising paradigm for robot perception, offering advantages with high temporal resolution, high dynamic range, and robustness to motion blur. However, existing deep learning-based event processing…

Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To…

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…

State space models (SSMs) have recently emerged as a powerful framework for long sequence processing, outperforming traditional methods on diverse benchmarks. Fundamentally, SSMs can generalize both recurrent and convolutional networks and…

Event cameras are neuromorphic sensors that capture asynchronous and sparse event stream when per-pixel brightness changes. The state-of-the-art processing methods for event signals typically aggregate events into a frame or a grid.…

This study introduces a novel approach to enhance the spatial-temporal resolution of time-event pixels based on luminance changes captured by event cameras. These cameras present unique challenges due to their low resolution and the sparse,…

Traffic flow forecasting is a crucial task in urban computing. The challenge arises as traffic flows often exhibit intrinsic and latent spatio-temporal correlations that cannot be identified by extracting the spatial and temporal patterns…

Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and low latency,…

Neuromorphic vision sensors (event cameras) simulate biological visual perception systems and have the advantages of high temporal resolution, less data redundancy, low power consumption, and large dynamic range. Since both events and…

Event cameras are bio-inspired sensors that capture intensity changes asynchronously with distinct advantages, such as high temporal resolution. Existing methods for event-based object/action recognition predominantly sample and convert…

Time-series forecasting in domains like traffic management and industrial monitoring often requires real-time, energy-efficient processing on edge devices with limited resources. Spiking neural networks (SNNs) offer event-driven computation…

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred…

Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time. Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging…

Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological…

The integration of event cameras and spiking neural networks (SNNs) promises energy-efficient visual intelligence, yet scarce event data and the sparsity of DVS outputs hinder effective training. Prior knowledge transfers from RGB to DVS…

Recent event-based image reconstruction methods predominantly rely on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to process complementary event information. However, these architectures face fundamental limitations:…

Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration. While ViTs generally outperform CNNs by effectively capturing long-range dependencies and input-specific…