Large deviation principle for reflected SPDE on infinite spatial domain

Kavli Affiliate: Ran Wang | First 5 Authors: Ran Wang, Beibei Zhang, , , | Summary: We study a large deviation principle for a reflected stochastic partial differential equation on infinite spatial domain. A new sufficient condition for the weak convergence criterion proposed by Matoussi, Sabbagh and Zhang ({it Appl. Math. Optim.} 83: 849-879, 2021) […]


Continue.. Large deviation principle for reflected SPDE on infinite spatial domain

An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

Kavli Affiliate: Huawei Zhang | First 5 Authors: Kunran Xu, Huawei Zhang, Yishi Li, Yuhao Zhang, Rui Lai | Summary: Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic. This brief firstly presents an extremely tiny backbone to construct high efficiency CNN models for […]


Continue.. An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

Kavli Affiliate: Huawei Zhang | First 5 Authors: Kunran Xu, Huawei Zhang, Yishi Li, Yuhao Zhang, Rui Lai | Summary: Tiny machine learning (TinyML), executing AI workloads on resource and power strictly restricted systems, is an important and challenging topic. This brief firstly presents an extremely tiny backbone to construct high efficiency CNN models for […]


Continue.. An Ultra-low Power TinyML System for Real-time Visual Processing at Edge

Positive-Negative Equal Contrastive Loss for Semantic Segmentation

Kavli Affiliate: Jing Wang | First 5 Authors: Jing Wang, Lingfei Xuan, Wenxuan Wang, Tianxiang Zhang, Jiangyun Li | Summary: The contextual information is critical for various computer vision tasks, previous works commonly design plug-and-play modules and structural losses to effectively extract and aggregate the global context. These methods utilize fine-label to optimize the model […]


Continue.. Positive-Negative Equal Contrastive Loss for Semantic Segmentation

The effect of obstacles near a silo outlet on the discharge of soft spheres

Kavli Affiliate: Jing Wang | First 5 Authors: Jing Wang, Kirsten Harth, Dmitry Puzyrev, Ralf Stannarius, | Summary: Soft smooth particles in silo discharge show peculiar characteristics, including, for example, non-permanent clogging and intermittent flow. This paper describes a study of soft, low-frictional hydro-gel spheres in a quasi-2D silo. We enforce a more competitive behavior […]


Continue.. The effect of obstacles near a silo outlet on the discharge of soft spheres

Monitoring AGNs with H$β$ Asymmetry. III. Long-term Reverberation Mapping Results of 15 Palomar-Green Quasars

Kavli Affiliate: Luis C. Ho | First 5 Authors: Dong-Wei Bao, Michael S. Brotherton, Pu Du, Jacob N. McLane, T. E. Zastrocky | Summary: In this third paper of the series reporting on the reverberation mapping (RM) campaign of active galactic nuclei with asymmetric H$beta$ emission-line profiles, we present results for 15 Palomar-Green (PG) quasars […]


Continue.. Monitoring AGNs with H$β$ Asymmetry. III. Long-term Reverberation Mapping Results of 15 Palomar-Green Quasars

Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition

Kavli Affiliate: Jing Wang | First 5 Authors: Mingkun Yang, Minghui Liao, Pu Lu, Jing Wang, Shenggao Zhu | Summary: Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data […]


Continue.. Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition

SASV Based on Pre-trained ASV System and Integrated Scoring Module

Kavli Affiliate: Zhuo Li | First 5 Authors: Yuxiang Zhang, Zhuo Li, Wenchao Wang, Pengyuan Zhang, | Summary: Based on the assumption that there is a correlation between anti-spoofing and speaker verification, a Total-Divide-Total integrated Spoofing-Aware Speaker Verification (SASV) system based on pre-trained automatic speaker verification (ASV) system and integrated scoring module is proposed and […]


Continue.. SASV Based on Pre-trained ASV System and Integrated Scoring Module