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...
Deep learning and neural network has been widely used in research, deep learning has empowered many tasks such as point clouds segmentation and shape recognition. One of the main advantages of deep interaction point cloud segmentation is that it allows the feature extraction can be learned through neural network based...
The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
Remote sensing forest inventory gained increased attention in the last decade triggered by the decrease in the price of sensors and the explosion of data availability and formats. Evermore, the constant advances in the hardware processing the data emphasized the necessity to develop algorithms to extract forest relevant information from...
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...
Deep learning has recently revolutionized robot perception in many canonical robotic applications, such as autonomous driving. However, a similar transformation has yet to occur in more harsh environments including underwater and underground. This is due in part to the difficulty in deploying robots in these environments, which lack large real...
In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
Papers proposing novel machine learning algorithms tend to present the algorithm or technique in question in the best possible light. The standard practice is generally for authors to emphasize their proposed algorithms' performance in the precise setting where it is maximally impressive, often by only fully evaluating their best known...
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...