2 citations · 5 across the 9 of their papers we have counts for
7 papers · 1 filter
Optimal Brain Apoptosis
Mingyuan Sun, Zheng Fang, Jiaxu Wang +5
The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pr…
EV-MGDispNet: Motion-Guided Event-Based Stereo Disparity Estimation Network with Left-Right Consistency
Junjie Jiang, Hao Zhuang, Xinjie Huang +2
Event cameras have the potential to revolutionize the field of robot vision, particularly in areas like stereo disparity estimation, owing to their high temporal resolution and hig…
Motion and Structure from Event-based Normal Flow
Zhongyang Ren, Bangyan Liao, Delei Kong +5
Recovering the camera motion and scene geometry from visual data is a fundamental problem in the field of computer vision. Its success in standard vision is attributed to the matur…
Spike-EVPR: Deep Spiking Residual Networks with SNN-Tailored Representations for Event-Based Visual Place Recognition
Zuntao Liu, Yaohui Li, Chenming Hu +3
Event cameras are ideal for visual place recognition (VPR) in challenging environments due to their high temporal resolution and high dynamic range. However, existing methods conve…
EV-MGRFlowNet: Motion-Guided Recurrent Network for Unsupervised Event-based Optical Flow with Hybrid Motion-Compensation Loss
Hao Zhuang, Xinjie Huang, Kuanxu Hou +3
Event cameras offer promising properties, such as high temporal resolution and high dynamic range. These benefits have been utilized into many machine vision tasks, especially opti…
FE-Fusion-VPR: Attention-based Multi-Scale Network Architecture for Visual Place Recognition by Fusing Frames and Events
Kuanxu Hou, Delei Kong, Junjie Jiang +3
Traditional visual place recognition (VPR), usually using standard cameras, is easy to fail due to glare or high-speed motion. By contrast, event cameras have the advantages of low…
Event-VPR: End-to-End Weakly Supervised Network Architecture for Event-based Visual Place Recognition
Delei Kong, Zheng Fang, Haojia Li +3
Traditional visual place recognition (VPR) methods generally use frame-based cameras, which is easy to fail due to dramatic illumination changes or fast motions. In this paper, we…