Výsledky vyhledávání - "Tasaka, Kazuyuki"

Report

Residual Squeeze-and-Excitation Network for Fast Image Deraining

Autor: Fu, Jun, Xu, Jianfeng, Tasaka, Kazuyuki, Chen, Zhibo

Image deraining is an important image processing task as rain streaks not only severely degrade the visual quality of images but also significantly affect the performance of high-level vision tasks. Traditional methods progressively remove rain strea

Externí odkaz: http://arxiv.org/abs/2006.00757

Zobrazit plný text záznamu

Report

Prior-enlightened and Motion-robust Video Deblurring

Autor: Zhou, Ya, Xu, Jianfeng, Tasaka, Kazuyuki, Chen, Zhibo, Li, Weiping

Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalizati

Externí odkaz: http://arxiv.org/abs/2003.11209

Zobrazit plný text záznamu

Report

SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration

Autor: Shi, Jun, Xu, Jianfeng, Tasaka, Kazuyuki, Chen, Zhibo

Accelerating the inference speed of CNNs is critical to their deployment in real-world applications. Among all the pruning approaches, those implementing a sparsity learning framework have shown to be effective as they learn and prune the models in a

Externí odkaz: http://arxiv.org/abs/2003.05891

Zobrazit plný text záznamu

Report

Multiple Human Tracking using Multi-Cues including Primitive Action Features

Autor: Nishimura, Hitoshi, Tasaka, Kazuyuki, Kawanishi, Yasutomo, Murase, Hiroshi

In this paper, we propose a Multiple Human Tracking method using multi-cues including Primitive Action Features (MHT-PAF). MHT-PAF can perform the accurate human tracking in dynamic aerial videos captured by a drone. PAF employs a global context, ric

Externí odkaz: http://arxiv.org/abs/1909.08171

Zobrazit plný text záznamu