Sujuan Hou — accepted AI-conference papers

2024

Multi-Stage Progressive Refinement and RoI Context Enhancement Network for Small Logo Detection

ICASSP 2024accepted

Logo detection is a critical task in computer vision with a wide range of applications. In logo detection tasks, small logos occupy a limited number of pixels in the image due to their small size. Additionally, background clutter may have textures, colors, or shapes that are similar to small logos,…

Cited by 0 Source ↗Scholar ↗

2021

Exploiting Probabilistic Siamese Visual Tracking with a Conditional Variational Autoencoder

Wenhui Huang, Jason Gu, Peiyong Duan, Sujuan Hou, Yuanjie Zheng

ICRA 2021poster

Visual tracking is a fundamental capability for robots tasked with humans and environment interaction. However, state-of-the-art visual tracking methods are still prone to failures and are imprecise when applied to challenging stereos, and their results are generally confidence agonistic. These meth…

Cited by 9 Source ↗Scholar ↗