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 present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...
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...
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...
The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
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...
Advances in sensor technology are greatly expanding the range of quantities that can be measured while simultaneously reducing the cost. However, deployed sensors drift out of calibration and fail, so every sensor network requires quality control procedures to promptly detect these failures. To address these problems, we propose a two-level...
Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
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...