Quick search
Advanced search in
Field to searchTerm
Add rule
Filters (4)
Download Results
2,184 research outcomes, page 1 of 219
  • publication . Preprint . 2019
    Open Access English
    Authors:
    Im, Sunghoon; Jeon, Hae-Gon; Lin, Stephen; Kweon, In So;

    Multiview stereo aims to reconstruct scene depth from images acquired by a camera under arbitrary motion. Recent methods address this problem through deep learning, which can utilize semantic cues to deal with challenges such as textureless and reflective regions. In th...

  • publication . Preprint . 2020
    Open Access English
    Authors:
    Gaujac, Benoit; Feige, Ilya; Barber, David;

    Disentangled representation learning has undoubtedly benefited from objective function surgery. However, a delicate balancing act of tuning is still required in order to trade off reconstruction fidelity versus disentanglement. Building on previous successes of penalizi...

  • publication . Preprint . 2020
    Open Access English
    Authors:
    De Cao, Nicola; Izacard, Gautier; Riedel, Sebastian; Petroni, Fabio;

    Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive...

  • publication . Conference object . Preprint . 2019
    Open Access
    Authors:
    Xiaofeng Liu; Zhenhua Guo; Site Li; Ping Jia; Lingsheng Kong; Jane You; B. V. K. Vijaya Kumar;
    Persistent Identifiers
    Publisher: IEEE

    We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images. We use feature restructuring to exploit the correlations of both inner$\&$inter-set images. Specifically, the residual self-attention c...

    Add to ORCIDorcid
  • publication . Preprint . 2017
    Open Access English
    Authors:
    Bae, Sung-Ho; Elgharib, Mohamed; Hefeeda, Mohamed; Matusik, Wojciech;

    Single-image-based view generation (SIVG) is important for producing 3D stereoscopic content. Here, handling different spatial resolutions as input and optimizing both reconstruction accuracy and processing speed is desirable. Latest approaches are based on convolutiona...

  • publication . Preprint . 2021
    Open Access English
    Authors:
    Zhan, Ni;

    This paper examines deposits of individuals ("retail") and large companies ("wholesale") in the U.S. banking industry, and how these deposit types are impacted by macroeconomic factors, such as quantitative easing (QE). Actual data for deposits by holder are unavailable...

  • publication . Conference object . Preprint . 2018
    Open Access English
    Authors:
    Ziyan Wang; Buyu Liu; Samuel Schulter; Manmohan Chandraker;
    Persistent Identifiers

    In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model of road layouts in a top-view representation, which is not only intuitive for human visuali...

    Add to ORCIDorcid
  • publication . Preprint . 2018
    Open Access English
    Authors:
    Abate, Carmine; de Amorim, Arthur Azevedo; Blanco, Roberto; Evans, Ana Nora; Fachini, Guglielmo; Hritcu, Catalin; Laurent, Théo; Pierce, Benjamin C.; Stronati, Marco; Thibault, Jérémy; ...
    Project: NSF | TWC: Medium: Micro-Polici... (1513854), EC | SECOMP (715753)

    We propose a new formal criterion for evaluating secure compilation schemes for unsafe languages, expressing end-to-end security guarantees for software components that may become compromised after encountering undefined behavior---for example, by accessing an array out...

  • publication . Preprint . 2018
    Open Access English
    Authors:
    Che, Chengqian; Luan, Fujun; Zhao, Shuang; Bala, Kavita; Gkioulekas, Ioannis;

    We introduce inverse transport networks as a learning architecture for inverse rendering problems where, given input image measurements, we seek to infer physical scene parameters such as shape, material, and illumination. During training, these networks are evaluated n...

  • publication . Preprint . 2020
    Open Access English
    Authors:
    Tian, Stephen; Nair, Suraj; Ebert, Frederik; Dasari, Sudeep; Eysenbach, Benjamin; Finn, Chelsea; Levine, Sergey;

    A generalist robot must be able to complete a variety of tasks in its environment. One appealing way to specify each task is in terms of a goal observation. However, learning goal-reaching policies with reinforcement learning remains a challenging problem, particularly ...

2,184 research outcomes, page 1 of 219