相关论文: Low-latency Event-based Object Detection with Spat…

Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory…

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat…

Sparse attention as a efficient method can significantly decrease the computation cost, but current sparse attention tend to rely on window self attention which block the global information flow. For this problem, we present Shifted Cross…

Event-based data are commonly encountered in edge computing environments where efficiency and low latency are critical. To interface with such data and leverage their rich temporal features, we propose a causal spatiotemporal convolutional…

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing…

The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize…

With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical…

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera…

Automotive embedded algorithms have very high constraints in terms of latency, accuracy and power consumption. In this work, we propose to train spiking neural networks (SNNs) directly on data coming from event cameras to design fast and…

Dynamic Vision Sensors (DVSs) asynchronously stream events in correspondence of pixels subject to brightness changes. Differently from classic vision devices, they produce a sparse representation of the scene. Therefore, to apply standard…

Self-supervised learning (SSL) on 3D point clouds has the potential to learn feature representations that can transfer to diverse sensors and multiple downstream perception tasks. However, recent SSL approaches fail to define pretext tasks…

Dense self-supervised learning (SSL) methods showed its effectiveness in enhancing the fine-grained semantic understandings of vision models. However, existing approaches often rely on parametric assumptions or complex post-processing…

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in…

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are…

Event-based object detection has recently garnered attention in the computer vision community due to the exceptional properties of event cameras, such as high dynamic range and no motion blur. However, feature asynchronism and sparsity…

Object detection has recently seen an interesting trend in terms of the most innovative research work, this task being of particular importance in the field of remote sensing, given the consistency of these images in terms of geographical…

Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection…

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…