Zobrazeno 1 - 10
of 1 496
pro vyhledávání: '"Namboodiri P"'
Autor:
Namboodiri Pradeep, Wyrick Jonathan, Stan Gheorghe, Wang Xiqiao, Fei Fan, Kashid Ranjit Vilas, Schmucker Scott W., Kasica Richard, Barnes Bryan M., Stewart Jr Michael D., Silver Richard M.
Publikováno v:
Nanotechnology Reviews, Vol 13, Iss 1, Pp 242-6 (2024)
Externí odkaz:
https://doaj.org/article/33bc7056a2974d1c99dccca4d57f09f5
The spatio-temporal nature of live-cell microscopy data poses challenges in the analysis of cell states which is fundamental in bioimaging. Deep-learning based segmentation or tracking methods rely on large amount of high quality annotations to work
Externí odkaz:
http://arxiv.org/abs/2411.03924
Autor:
Singh, Utsav, Chakraborty, Souradip, Suttle, Wesley A., Sadler, Brian M., Sahu, Anit Kumar, Shah, Mubarak, Namboodiri, Vinay P., Bedi, Amrit Singh
This work introduces Hierarchical Preference Optimization (HPO), a novel approach to hierarchical reinforcement learning (HRL) that addresses non-stationarity and infeasible subgoal generation issues when solving complex robotic control tasks. HPO le
Externí odkaz:
http://arxiv.org/abs/2411.00361
Autor:
Namboodiri, M N N
Let $\mathcal{G}$ be a locally compact Hausdorff group in which every element is of finite order, and let $P(\mathcal{G})$ denote the class of all regular probability measures on $\mathcal{G}$. In this note, it is observed that a charecterisation of
Externí odkaz:
http://arxiv.org/abs/2410.10520
Indoor navigation is challenging due to the absence of satellite positioning. This challenge is manifold greater for Visually Impaired People (VIPs) who lack the ability to get information from wayfinding signage. Other sensor signals (e.g., Bluetoot
Externí odkaz:
http://arxiv.org/abs/2410.18109
Autor:
Kravets, Alexey, Namboodiri, Vinay
Numerous methods have been proposed to adapt a pre-trained foundational CLIP model for few-shot classification. As CLIP is trained on a large corpus, it generalises well through adaptation to few-shot classification. In this work, we analyse the intr
Externí odkaz:
http://arxiv.org/abs/2409.11338
Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is critical for applications in healthcare, safety, and industrial production. However, variations in activity patterns, device types, and sensor placements create distrib
Externí odkaz:
http://arxiv.org/abs/2410.00003
Portrait sketching involves capturing identity specific attributes of a real face with abstract lines and shades. Unlike photo-realistic images, a good portrait sketch generation method needs selective attention to detail, making the problem challeng
Externí odkaz:
http://arxiv.org/abs/2409.00345
Diffusion-based models demonstrate impressive generation capabilities. However, they also have a massive number of parameters, resulting in enormous model sizes, thus making them unsuitable for deployment on resource-constraint devices. Block-wise ge
Externí odkaz:
http://arxiv.org/abs/2408.17095
Autor:
Saunders, Jack, Namboodiri, Vinay
Speech-driven facial animation is important for many applications including TV, film, video games, telecommunication and AR/VR. Recently, transformers have been shown to be extremely effective for this task. However, we identify two issues with the e
Externí odkaz:
http://arxiv.org/abs/2408.13714