Zobrazeno 1 - 10
of 72 978
pro vyhledávání: '"LI, Yu"'
Prior works on physical adversarial camouflage against vehicle detectors mainly focus on the effectiveness and robustness of the attack. The current most successful methods optimize 3D vehicle texture at a pixel level. However, this results in conspi
Externí odkaz:
http://arxiv.org/abs/2409.17963
For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e., a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is an intricate task for the development of deblurring models. Exis
Externí odkaz:
http://arxiv.org/abs/2409.17792
This paper presents an approach that employs log-linearization in Lie group theory and the Newton-Euler equations to derive exact linear error dynamics for a multi-rotor model, and applies this model with a novel log-linear dynamic inversion controll
Externí odkaz:
http://arxiv.org/abs/2409.10866
Audio-driven talking head synthesis strives to generate lifelike video portraits from provided audio. The diffusion model, recognized for its superior quality and robust generalization, has been explored for this task. However, establishing a robust
Externí odkaz:
http://arxiv.org/abs/2409.10281
Autor:
Huang, Hsiang-Wei, Sun, Jiacheng, Yang, Cheng-Yen, Jiang, Zhongyu, Huang, Li-Yu, Hwang, Jenq-Neng, Yeh, Yu-Ching
Assessing gross motor development in toddlers is crucial for understanding their physical development and identifying potential developmental delays or disorders. However, existing datasets for action recognition primarily focus on adults, lacking th
Externí odkaz:
http://arxiv.org/abs/2409.00349
Autor:
Jiang, Jiyue, Chen, Liheng, Chen, Pengan, Wang, Sheng, Bao, Qinghang, Kong, Lingpeng, Li, Yu, Wu, Chuan
The rapid evolution of large language models (LLMs) has transformed the competitive landscape in natural language processing (NLP), particularly for English and other data-rich languages. However, underrepresented languages like Cantonese, spoken by
Externí odkaz:
http://arxiv.org/abs/2408.16756
Vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot ability in image classification tasks by aligning text and images but suffer inferior performance compared with task-specific expert models. On the contrary, expert models
Externí odkaz:
http://arxiv.org/abs/2408.11449
To complete a complex task where a robot navigates to a goal object and fetches it, the robot needs to have a good understanding of the instructions and the surrounding environment. Large pre-trained models have shown capabilities to interpret tasks
Externí odkaz:
http://arxiv.org/abs/2408.10578
Autor:
Li, Yang, Cai, Wen-Qi, Ren, Ji-Gang, Wang, Chao-Ze, Yang, Meng, Zhang, Liang, Wu, Hui-Ying, Chang, Liang, Wu, Jin-Cai, Jin, Biao, Xue, Hua-Jian, Li, Xue-Jiao, Liu, Hui, Yu, Guang-Wen, Tao, Xue-Ying, Chen, Ting, Liu, Chong-Fei, Luo, Wen-Bin, Zhou, Jie, Yong, Hai-Lin, Li, Yu-Huai, Li, Feng-Zhi, Jiang, Cong, Chen, Hao-Ze, Wu, Chao, Tong, Xin-Hai, Xie, Si-Jiang, Zhou, Fei, Liu, Wei-Yue, Liu, Nai-Le, Li, Li, Xu, Feihu, Cao, Yuan, Yin, Juan, Shu, Rong, Wang, Xiang-Bin, Zhang, Qiang, Wang, Jian-Yu, Liao, Sheng-Kai, Peng, Cheng-Zhi, Pan, Jian-Wei
A quantum network provides an infrastructure connecting quantum devices with revolutionary computing, sensing, and communication capabilities. As the best-known application of a quantum network, quantum key distribution (QKD) shares secure keys guara
Externí odkaz:
http://arxiv.org/abs/2408.10994
Handwritten Mathematical Expression Recognition (HMER) has extensive applications in automated grading and office automation. However, existing sequence-based decoding methods, which directly predict $\LaTeX$ sequences, struggle to understand and mod
Externí odkaz:
http://arxiv.org/abs/2408.08578