Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for
developing colorectal cancer. However, polyp segmentation is a challenging task due to the …

The task of converting a natural language question into an executable SQL query, known as
text-to-SQL, is an important branch of semantic parsing. The state-of-the-art graph-based …

The paper proposes a semantic clustering based deduction learning by mimicking the
learning and thinking process of human brains. Human beings can make judgments based …

In the majority of object detection frameworks, the confidence of instance classification is
used as the quality criterion of predicted bounding boxes, like the confidence-based ranking …

Multi-label zero-shot learning is a branch of the classification problem more in line with
practical applications, because a real image does not usually contain only one category …

Layer-wise learning, as an alternative to global backpropagation, is memory efficient and
easy to interpret, analyze. Recent studies demonstrate that layer-wise learning can achieve …

To preferably make use of the complementary information of infrared and visible images, we
propose a novel method of network structure with convolution kernel orthogonalization and …

In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network
training, based on adaptive estimates of feasible region via branch-and-bound. The method …

There is a growing need for the development of computational methods and tools for
automated, objective, and quantitative analysis of biomedical signal and image data to …

Object re-identification is a common task in computer vision, a certain object's (person,
wildlife, vehicle, etc.) image of interest is used to match against a large gallery of images to …