Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
Data can be represented in multiple views. Traditional multi-view learning methods (i.e., co-training, multi-task learning) focus on improving learning performance using information from the auxiliary view, although information from the target view is sufficient for learning task. However, this work addresses a semi-supervised case of multi-view learning, the surrogate supervision...
Automatic painterly rendering systems have been proposed but they opted for selecting a single style to generate paintings from images, which lacks the ability of creatively using multiple styles to focus important objects and deemphasize unimportant part of the scenes. We provide a multi-style painting framework to
address this issue...
Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
As one of the most popular data types, the point cloud is widely used in various appli- cations, including computer vision, computer graphics and robotics. The capability to directly measure 3D point clouds is invaluable in those applications as depth information could remove a lot of the segmentation ambiguities in...
Hand detection is a fundamental step for many hand-related computer vision tasks, such as gesture recognition, hand pose estimation, hand sign language translation, and so on. However, robustly detecting hands is a challenging task because of drastic changes in appearance based on finger articulation and changes in lighting conditions, camera...
In pursuit of global sustainability, forestry has witnessed significant shifts in practices and the development of new technologies and ideas. Primary and secondary processing industries have made substantial efforts to increase wood utilization rates, improve occupational safety and the working environment for humans, and have exhibited interest in procuring raw...
In supervised learning, label information can be provided at different levels of granularity. For small datasets, it is possible to acquire a label for each data instance. However, in the big-data regime, this fine granularity approach is prohibitively costly. For example, in semi-supervised learning, only a limited number of samples...
Wood composites are an important renewable structural material which can be a net carbon sink when used in combination with sustainable forest management practices and high rates of log utilization. Adhesive bondlines are an essential part of composites, and for wood composites, they determine the moisture durability and mechanical performance...