184 citations · 222 across the 7 of their papers we have counts for
7 papers
A Unified Study of Machine Learning Explanation Evaluation Metrics
Yipei Wang, Xiaoqian Wang
The growing need for trustworthy machine learning has led to the blossom of interpretability research. Numerous explanation methods have been developed to serve this purpose. Howev…
Self-Interpretable Model with TransformationEquivariant Interpretation
Yipei Wang, Xiaoqian Wang
In this paper, we propose a self-interpretable model SITE with transformation-equivariant interpretations. We focus on the robustness and self-consistency of the interpretations of…
End-to-End Subtitle Detection and Recognition for Videos in East Asian Languages via CNN Ensemble with Near-Human-Level Performance
Yan Xu, Siyuan Shan, Ziming Qiu +5
In this paper, we propose an innovative end-to-end subtitle detection and recognition system for videos in East Asian languages. Our end-to-end system consists of multiple stages.…
Learning Multi-level Features For Sensor-based Human Action Recognition
Yan Xu, Zhengyang Shen, Xin Zhang +5
This paper proposes a multi-level feature learning framework for human action recognition using a single body-worn inertial sensor. The framework consists of three phases, respecti…
Gland Instance Segmentation Using Deep Multichannel Neural Networks
Yan Xu, Yang Li, Yipei Wang +4
Objective: A new image instance segmentation method is proposed to segment individual glands (instances) in colon histology images. This process is challenging since the glands not…
Gland Instance Segmentation by Deep Multichannel Neural Networks
Yan Xu, Yang Li, Mingyuan Liu +4
In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images. This is a task called instance segmentatio…
Gland Instance Segmentation by Deep Multichannel Side Supervision
Yan Xu, Yang Li, Mingyuan Liu +3
In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images. This is a task called instance segmentatio…