In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features. Differentiating multiple potential instances within a single PoI feature is challen…
Text is a new way to guide human image manipulation. Albeit natural and flexible, text usually suffers from inaccuracy in spatial description, ambiguity in the description of appearance, and incomp…
Generative adversarial networks have achieved great success in unpaired image-to-image translation. Cycle consistency, a key component for this task, allows modeling the relationship between two di…
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed …
In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on top of two-stream C…
We theoretically investigate and optimize the performance of four-wave mixing (FWM) in microring resonators (MRRs) integrated with two-dimensional (2D) layered graphene oxide (GO) films. Owing to t…
We theoretically investigate and optimize four-wave mixing (FWM) in silicon nitride (SiN) waveguides integrated with 2D layered graphene oxide (GO) films. Based on extensive previous measurements o…