output
20212025
most citedBounding Box Tightness Prior for Weakly Supervised Image Segmentation

40 citations

5 papers

physics.optics2025★ 16 cited

Integrated photonics incorporating 2D materials for practical applications

David J. Moss

On-chip integration of 2D materials with exceptional optical properties provides an attractive solution for next-generation photonic integrated circuits to address the limitations…

physics.flu-dyn2023★ 2 cited

Rayleigh-Taylor Unstable Flames: the Effect of Two-Mode Coupling

Mingxuan Liu, Elizabeth P. Hicks

In the classical Rayleigh-Taylor (RT) instability, initial conditions are forgotten and the growth of the mixing layer becomes self-similar when short wavelength modes couple to ge…

cs.HC2021★ 3 cited

Human Activity Recognition (HAR) in Smart Homes

Damien Bouchabou, Christophe Lohr, Ioannis Kanellos +1

Generally, Human Activity Recognition (HAR) consists of monitoring and analyzing the behavior of one or more persons in order to deduce their activity. In a smart home context, the…

cs.CV2021★ 40 cited

Bounding Box Tightness Prior for Weakly Supervised Image Segmentation

Juan Wang, Bin Xia

This paper presents a weakly supervised image segmentation method that adopts tight bounding box annotations. It proposes generalized multiple instance learning (MIL) and smooth ma…

cs.CV2021★ 3 cited

CDRNet: Accurate Cup-to-Disc Ratio Measurement with Tight Bounding Box Supervision in Fundus Photography Using Deep Learning

Juan Wang, Bin Xia

The cup-to-disc ratio (CDR) is one of the most significant indicator for glaucoma diagnosis. Different from the use of costly fully supervised learning formulation with pixel-wise…