Zobrazeno 1 - 10
of 851
pro vyhledávání: '"Wang, Z. Jane"'
Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most effective defen
Externí odkaz:
http://arxiv.org/abs/2411.02871
Autor:
Tashakori, Arvin, Jiang, Zenan, Servati, Amir, Soltanian, Saeid, Narayana, Harishkumar, Le, Katherine, Nakayama, Caroline, Yang, Chieh-ling, Wang, Z. Jane, Eng, Janice J., Servati, Peyman
Publikováno v:
Nature Machine Intelligence 6 (2024) 106-118
Accurate real-time tracking of dexterous hand movements and interactions has numerous applications in human-computer interaction, metaverse, robotics, and tele-health. Capturing realistic hand movements is challenging because of the large number of a
Externí odkaz:
http://arxiv.org/abs/2410.02221
The increasing demand for medical imaging has surpassed the capacity of available radiologists, leading to diagnostic delays and potential misdiagnoses. Artificial intelligence (AI) techniques, particularly in automatic medical report generation (AMR
Externí odkaz:
http://arxiv.org/abs/2408.13988
The 7-point checklist (7PCL) is widely used in dermoscopy to identify malignant melanoma lesions needing urgent medical attention. It assigns point values to seven attributes: major attributes are worth two points each, and minor ones are worth one p
Externí odkaz:
http://arxiv.org/abs/2407.16822
Despite recent advances in human pose estimation (HPE), poor generalization to out-of-distribution (OOD) data remains a difficult problem. While previous works have proposed Test-Time Adaptation (TTA) to bridge the train-test domain gap by refining n
Externí odkaz:
http://arxiv.org/abs/2407.14605
Continuous Conditional Generative Modeling (CCGM) aims to estimate the distribution of high-dimensional data, typically images, conditioned on scalar continuous variables known as regression labels. While Continuous conditional Generative Adversarial
Externí odkaz:
http://arxiv.org/abs/2405.03546
Knowledge distillation from LLMs is essential for the efficient deployment of language models. Prior works have proposed data generation using LLMs for preparing distilled models. We argue that generating data with LLMs is prone to sampling mainly fr
Externí odkaz:
http://arxiv.org/abs/2403.19754
This paper proposes an end-to-end framework for generating 3D human pose datasets using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in terms of human poses and camera viewpoints, largely due to the resource-intensi
Externí odkaz:
http://arxiv.org/abs/2312.14915
In this paper, we propose a novel time of arrival (TOA) estimator for multiple-input-multiple-output (MIMO) backscatter channels in closed form. The proposed estimator refines the estimation precision from the topological structure of the MIMO backsc
Externí odkaz:
http://arxiv.org/abs/2311.13196
Millimeter wave (mmWave)-based unmanned aerial vehicle (UAV) communication is a promising candidate for future communications due to its flexibility and sufficient bandwidth. However, random fluctuations in the position of hovering UAVs will lead to
Externí odkaz:
http://arxiv.org/abs/2306.06405