Zobrazeno 1 - 10
of 13 844
pro vyhledávání: '"Cheng, Wen"'
Event-based cameras, inspired by the biological retina, have evolved into cutting-edge sensors distinguished by their minimal power requirements, negligible latency, superior temporal resolution, and expansive dynamic range. At present, cameras used
Externí odkaz:
http://arxiv.org/abs/2407.04277
Extremal elastic materials here refer to a specific class of elastic materials whose elastic matrices exhibit one or more zero eigenvalues, resulting in soft deformation modes that, in principle, cost no energy. They can be approximated through artif
Externí odkaz:
http://arxiv.org/abs/2406.07462
Autor:
Liu, Hou-I, Tseng, Yu-Wen, Chang, Kai-Cheng, Wang, Pin-Jyun, Shuai, Hong-Han, Cheng, Wen-Huang
Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data. This challe
Externí odkaz:
http://arxiv.org/abs/2406.05755
UAV tracking and pose estimation plays an imperative role in various UAV-related missions, such as formation control and anti-UAV measures. Accurately detecting and tracking UAVs in a 3D space remains a particularly challenging problem, as it require
Externí odkaz:
http://arxiv.org/abs/2405.16867
Autor:
Wu, Bo, Liu, Peiye, Cheng, Wen-Huang, Liu, Bei, Zeng, Zhaoyang, Wang, Jia, Huang, Qiushi, Luo, Jiebo
Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating so
Externí odkaz:
http://arxiv.org/abs/2405.10497
Autor:
Chao, Rong, Cheng, Wen-Huang, La Quatra, Moreno, Siniscalchi, Sabato Marco, Yang, Chao-Han Huck, Fu, Szu-Wei, Tsao, Yu
This work aims to study a scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. We exploit a Mamba-based regression model to characterize speech signals and build an SE system upon Mamba, termed SEMamba. We explore the proper
Externí odkaz:
http://arxiv.org/abs/2405.06573
Autor:
Xie, Hongxia, Peng, Chu-Jun, Tseng, Yu-Wen, Chen, Hung-Jen, Hsu, Chan-Feng, Shuai, Hong-Han, Cheng, Wen-Huang
Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but
Externí odkaz:
http://arxiv.org/abs/2404.16670
Autor:
Liu, Hou-I, Galindo, Marco, Xie, Hongxia, Wong, Lai-Kuan, Shuai, Hong-Han, Li, Yung-Hui, Cheng, Wen-Huang
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable improveme
Externí odkaz:
http://arxiv.org/abs/2404.07236
Autor:
Liu, Hou-I, Wu, Christine, Cheng, Jen-Hao, Chai, Wenhao, Wang, Shian-Yun, Liu, Gaowen, Hwang, Jenq-Neng, Shuai, Hong-Han, Cheng, Wen-Huang
Monocular 3D object detection (Mono3D) is an indispensable research topic in autonomous driving, thanks to the cost-effective monocular camera sensors and its wide range of applications. Since the image perspective has depth ambiguity, the challenges
Externí odkaz:
http://arxiv.org/abs/2404.04910
Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny objects,
Externí odkaz:
http://arxiv.org/abs/2404.03507