Zobrazeno 1 - 10
of 411
pro vyhledávání: '"Zhu, Hongyi"'
Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy, and truthfulness. Although human evaluation provides valuable insig
Externí odkaz:
http://arxiv.org/abs/2411.05706
Web attacks are one of the major and most persistent forms of cyber threats, which bring huge costs and losses to web application-based businesses. Various detection methods, such as signature-based, machine learning-based, and deep learning-based, h
Externí odkaz:
http://arxiv.org/abs/2410.07725
In the era of large language models, parameter-efficient fine-tuning (PEFT) has been extensively studied. However, these approaches usually rely on the space domain, which encounters storage challenges especially when handling extensive adaptations o
Externí odkaz:
http://arxiv.org/abs/2410.09103
Autor:
Huang, Jia-Hong, Zhu, Hongyi, Shen, Yixian, Rudinac, Stevan, Pacces, Alessio M., Kanoulas, Evangelos
Evaluating the quality of automatically generated image descriptions is challenging, requiring metrics that capture various aspects such as grammaticality, coverage, correctness, and truthfulness. While human evaluation offers valuable insights, its
Externí odkaz:
http://arxiv.org/abs/2408.01723
A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning
Federated Learning (FL) has garnered widespread adoption across various domains such as finance, healthcare, and cybersecurity. Nonetheless, FL remains under significant threat from backdoor attacks, wherein malicious actors insert triggers into trai
Externí odkaz:
http://arxiv.org/abs/2407.00719
Image search stands as a pivotal task in multimedia and computer vision, finding applications across diverse domains, ranging from internet search to medical diagnostics. Conventional image search systems operate by accepting textual or visual querie
Externí odkaz:
http://arxiv.org/abs/2404.18746
Dog owners are typically capable of recognizing behavioral cues that reveal subjective states of their dogs, such as pain. But automatic recognition of the pain state is very challenging. This paper proposes a novel video-based, two-stream deep neura
Externí odkaz:
http://arxiv.org/abs/2209.13296
Autor:
Wang, Yihao, Guo, Youjie, Zhao, Dechao, Zhu, Hongyi, Zhang, Huawei, Wang, Mingliang, Huang, Jie, Chen, Zhe, Wang, Haowei
Publikováno v:
In Journal of Alloys and Compounds 15 October 2024 1002
Publikováno v:
In Journal of Manufacturing Processes 15 September 2024 125:512-522
Autor:
Dong, Shaohua, Zhang, Cilei, Yang, Chun, Wu, Shenghui, Sun, Haoliang, Zhang, Yonghao, Qin, Yifeng, Song, Xianglian, Xue, Kun, Zhang, Shuhan, Li, Feipeng, Feng, Jiqiang, Zhong, Qin, Yang, Chuanchuan, Zhu, Hongyi, Li, Yi, Li, Hongbin
Publikováno v:
In Optics and Laser Technology September 2024 176