In computer vision, significant advances have been made on object detection with the rapid
development of deep convolutional neural networks (CNN). This paper provides a …

Edge detection is one of the most important and fundamental problems in the field of
computer vision and image processing. Edge contours extracted from images are widely …

The class activation maps are generated from the final convolutional layer of CNN. They can
highlight discriminative object regions for the class of interest. These discovered object …

Humans naturally decompose their environment into entities at the appropriate level of
abstraction to act in the world. Allowing machine learning algorithms to derive this …

We present a high-performance method that can achieve mask-level instance segmentation
with only bounding-box annotations for training. While this setting has been studied in the …

Scene text detection and recognition has received increasing research attention. Existing
methods can be roughly categorized into two groups: character-based and segmentation …

We address the problem of real-time 3D object detection from point clouds in the context of
autonomous driving. Speed is critical as detection is a necessary component for safety …

Weakly supervised segmentation methods using bounding box annotations focus on
obtaining a pixel-level mask from each box containing an object. Existing methods typically …

Despite remarkable progress, weakly supervised segmentation methods are still inferior to
their fully supervised counterparts. We obverse that the performance gap mainly comes from …

Object detection, including objectness detection (OD), salient object detection (SOD), and
category-specific object detection (COD), is one of the most fundamental yet challenging …