In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
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...
We investigate a number of techniques for increasing throughput and quality of media applications over wireless networks. A typical media communication application such as video streaming imposes strict requirements on the delay and throughout of its packets, which unfortunately, cannot be guaranteed by the underlying wireless network due inherently to...
Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
This dissertation addresses the problem of recognizing human activities in videos. Our focus is on activities with stochastic structure, where the activities are characterized by variable space-time arrangements of actions, and conducted by a variable number of actors. These activities occur frequently in sports and surveillance videos. They may appear...
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...
This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
Robotic Bipedal locomotion holds the potential for efficient, robust traversal of difficult terrain. The difficulty lies in the dynamics of locomotion which complicate control and motion planning. Bipedal locomotion dynamics are dimensionally large problems, extremely nonlinear, and operate on the limits of actuator capabilities, which limit the performance of generic...
This dissertation addresses few-shot object segmentation in images. The goal of segmentation is to label every image pixel with a class of the object occupying that pixel, where the class may represent a semantic object category or instance. In few-shot segmentation, training and test datasets have different classes. Every new...