Browsing by Author "Wang, Jun"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item DEEP LEARNING FOR SCENE PERCEPTION AND UNDERSTANDING(2023) Wang, Jun; Davis, Larry; JaJa, Joseph; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The ability to accurately perceive objects and capture motion information from the environment is crucial in many real-world applications, including autonomous driving, augmented reality and robotics. This dissertation focuses on some fundamental challenges, regarding scene perception, scene understanding, and learning- based autonomous system. We first address the problem of developing a good representation of 3D sensor data for solving scene perception tasks. We start by focusing on learning how to explore the environment of a 3D perception system, including accurately perceiving objects and understanding the motion of dynamic objects. For example, it is critical for robotic agents to be able to develop a good understanding of objects in their environment. We investigate and tackle this problem through different computer vision tasks using a variety of input data. Compared with images, 3D point clouds provide reliable depth and precise geometric information; however, they are generally sparse with varying densities. To handle these challenges, we present a number of methods for efficient object detection and motion learning in the case of large-scale LiDAR point cloud data. In the first part, we consider the problem of 3D point cloud density, not well-explored characteristic for the task of 3D object detection. Our proposed InfoFocus method improves detection by adaptively refining features guided by the information of point cloud density in an end-to-end manner. Inspired by the success of transformer-based architectures in a variety of computer vision tasks, we consequently present another method M3DETR, which unifies multiple point cloud representations, feature scales, as well as model mutual relationships between point clouds simultaneously using transformers for 3D object detection. We also consider the problem of understanding dynamic 3D environments and identifying motion information of objects, which is critical for 3D perception. In the third part, we focus on a temporal sequence of 3D point clouds to extract point-wise motion information. Specifically, we propose a point-based spatiotemporal pyramid architecture, PointMotionNet which handles multiple frames and large-scale scenes, avoids discretization and explicitly learns from the temporal ordering. We note that having a deeper and holistic understanding of environment is quite important to help safely navigate through complex traffic scenarios. Besides accurately classifying, locating objects and predicting their behaviors, it would be crucial for the autonomous system to understand traffic rules of the road, such as spotting traffic signals or temporary road signs. The long-term goal is to build a perception system that has the ability to reason about the environment and adaptively make plans under uncertainty in real time. To reason and make real-time adjustments, the system needs to able to develop a good understanding of the road signs information. Here we address this task of Text-VQA which aims at answering questions that require understanding the textual cues in an image. In the fourth part of the thesis, we develop a method to generate high-quality and rich question-answer (QA) pairs by explicitly utilizing the existing rich text available in the scene context of the input image. The proposed architecture, TAG exploits underexplored scene text information and enhances scene understanding of Text-VQA models by producing meaningful, and accurate QA samples using a multimodal transformer. This method has the potential to be applied to identify challenging traffic situations that the autonomous vehicles will encounter on roads, such as traffic signs (stop/speed limit), one-way street, or evolving streets including road closure or a construction zone.Item EMPIRICAL ESSAYS ON FINANCIAL ECONOMICS(2019) Wang, Jun; Kyle, Albert; Shea, John; Economics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Using institutional investors’ holdings data from Thomson Reuters’ 13F filings, the first chapter studies and tests the market microstructure invariance hypothesis proposed by Kyle and Obizhaeva (2016a), and in particular its implied −2/3 law on the relationship between investors’ bets and stock trading activity, defined by the product of price, volume, and volatility. With the identifying assumption that institutional asset managers’ holdings are proportional to their bets, our empirical results support the −2/3 law implied by the invariance hypothesis. The −2/3 law is robust to a variety of estimation strategies and robustness checks. Then we study whether distributions of bets are invariant and log-normal. Data strongly support the hypothesis before March 1998, and the weak version of the invariance hypothesis (the mean of distributions of bets is invariant) continues to hold in the remaining periods. The strong version failing to hold after March 1998 may be due to adjustment costs and very tiny positions. The second chapter studies the role of convertible debt on investment. Convertible debt in the capital structure facilitates investment for a firm (especially for a firm with high leverage) since it reduces the firm's interest payments and leverage upon conversion, making it easier for the firm to issue new financial instruments. However, the same property may bring an agency issue: The potential of conversion into equity dilutes existing shareholders' profits, decreasing the firm's motivation to do investment. We hypothesize that the agency issue brought by convertible debt is minimal in very competitive markets since the external pressure is high, so that the facilitation role may outweigh the dilution role, suggesting a positive effect on investment, and that the agency issue brought by convertible debt may outweigh or just offset the facilitation role in less competitive markets since the external pressure is not high, suggesting a negative or insignificant effect on investment. Using data from Compustat, we find that convertible debt has a positive and quadratic effect on investment rates in competitive industries (industries with very low HHI), a negative and quadratic effect on investment rates in oligopoly industries (intermediate HHI), and an insignificant effect on investment rates in highly monopolistic industries (high HHI). These effects are robust to including different control variables. We also suspect the interaction of warrants and competition has similar effects. These results may have implications on the announcement effects or long term effects of convertible debt issuance under different industry structures.Item The Multivariate Variance Gamma Process and Its Applications in Multi-asset Option Pricing(2009) Wang, Jun; Madan, Dilip B; Applied Mathematics and Scientific Computation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Dependence modeling plays a critical role in pricing and hedging multi-asset derivatives and managing risks with a portfolio of assets. With the emerge of structured products, it has attracted considerable interest in using multivariate Levy processes to model the joint dynamics of multiple financial assets. The traditional multidimensional extension assumes a common time change for each marginal process, which implies limited dependence structure and similar kurtosis on each marginal. In this thesis, we introduce a new multivariate variance gamma process which allows arbitrary marginal variance gamma (VG) processes with flexible dependence structure. Compared with other multivariate Levy processes recently proposed in the literature, this model has several advantages when applied to financial modeling. First, the multivariate process built with any marginal VG process is easy to simulate and estimate. Second, it has a closed form joint characteristic function which largely simplifies the computation problem of pricing multi-asset options. Last, it can be applied to other time changed Levy processes such as normal inverse Gaussian (NIG) process. To test whether the multivariate variance gamma model fits the joint distribution of financial returns, we compare the model performance of explaining the portfolio returns with other popular models and we also develop Fast Fourier Transform (FFT)-based methods in pricing multi-asset options such as exchange options, basket options and cross-currency foreign exchange options.