Search Constraints

Start Over
Filtering by: Creator Zheng, Lei Remove constraint Creator: Zheng, Lei Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science Rights Statement In Copyright Remove constraint Rights Statement: In Copyright

Search Results

  • Modeling and Design of Interconnects and Passive Components for Millimeter-Wave Integrated Circuits in Silicon

    Creator:
    Zheng, Lei
    Abstract:
    For mmWave Integrated Circuit (IC) design, co-integration of passives can reduce size and power consumption, increase reliability, and reduce overall cost. However, skin and proximity effects in the metallization are aggravated at mmWave frequencies, resulting in increased attenuation and degradation of overall performance. Furthermore, tight integration of passive components (to...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Lei Zheng for the degree of Doctor of

  • Pixel- and Frame-level Video Labeling using Spatial and Temporal Convolutional Networks

    Creator:
    Lei, Peng
    Abstract:
    This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Peng Lei for the degree

  • Towards Direct Simultaneous Speech Translation

    Creator:
    Chen, Junkun
    Abstract:
    Simultaneous speech translation (SimulST) is widely useful in many cross-lingual communication scenarios, including multinational conferences and international traveling. Since text-based simultaneous machine translation (SimulMT) has achieved great success in recent years. The conventional cascaded approach for SimulST uses a pipeline of streaming ASR followed by simultaneous MT but suffers from...
    Resource Type:
    Dissertation
    Full Text:
    Zheng, Juneki Hong, Göksu Öztürk Miraç, Atsuhito Kita, Ning Dai, Liang Zhang, He Zhang, and Sizhen Li

  • Atomic Bifurcations of Degenerate Curves in 3D Linear Symmetric Tensor Fields

    Creator:
    Hongyu, Nie
    Abstract:
    Tensor field topology is of importance to research areas of medicine, science, and engineering. Degenerate curves are one of the crucial topological features that provide valuable insights for tensor field visualization. In this thesis, we study the atomic bifurcations of degenerate curves in 3D linear second-order symmetric tensor fields, and...
    Resource Type:
    Masters Thesis
    Full Text:
    - ness. To my parents and grandparents who gave me life and strength. To my husband Lei Feng who always

  • Action Segmentation in Videos: Deep Models, Prediction Diffusion, and Deep-Temporal Augmentations

    Creator:
    Aziere, Nicolas
    Abstract:
    This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
    Resource Type:
    Dissertation

  • Action Segmentation with Limited Supervision

    Creator:
    Li, Jun
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    , Nicolas Aziere, Peng Lei, Jialin Yuan, Xingyi Li, Lawrence Neal, Neale Ratzlaff, Wenxuan Wu, Hung Nguyen

  • Visual object discovery and understanding

    Creator:
    Yuan, Jialin
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    , Xian- fang, Xingyi, Xinyao, Zehuan, Zheng, Zhongang, and Ziwen. They patiently listened to countless

  • Analysis and modeling of monolithic on-chip transformers on silicon substrates

    Creator:
    Mayevskiy, Yevgeniy
    Abstract:
    Passive components, including spiral inductors and transformers, fabricated on silicon-based substrates are placing an increasing demand on radio-frequency integrated circuit (RFIC) design. Performance of the RFIC suffers from several non-ideal effects that must be taken into account in order to create a successful design. In particular, monolithic transformers can be...
    Resource Type:
    Masters Thesis
    Full Text:
    losses described in the section 2.2.2 (Rei-Lei loops). The second set of Coupled to all segments L r

  • Design of Compact Passive Components and Circuits for RF and Millimeter-Wave Integrated Circuit in Silicon

    Creator:
    Dong, Xuanyi
    Abstract:
    Emerging fifth generation (5G) and beyond 5G communication networks are stimulating the design of radio-frequency (RF) and millimeter-wave (mmWave) integrated circuits for wireless transceivers systems. While co-integration of active circuits and diverse passive components becomes feasible at these high operating frequencies, circuit design is faced with significant challenges due to...
    Resource Type:
    Dissertation
    Full Text:
    important projects. I want to thank my former colleague Lei Zheng for valuable discussions and sugges

  • A case for application-based linear transformers : applied towards text-to-spectrogram

    Creator:
    Agostinelli, Victor
    Abstract:
    Various natural language processing (NLP) tasks necessitate deep models that are fast, efficient, and small based on their ultimate application at the edge or elsewhere. While significant investigation has furthered the efficiency and reduced the size of these models, reducing their downstream latency without significant trade-offs remains a difficult task....
    Resource Type:
    Masters Thesis