Search Constraints

Start Over
Filtering by: Creator Bormann, Bernard T. Remove constraint Creator: Bormann, Bernard T. Contributor Li, Fuxin Remove constraint Contributor: Li, Fuxin

Search Results

  • Detecting Anomalies in Object Appearance and Motion Dynamics

    Creator:
    Alotaibi, Mazen
    Abstract:
    Machine common sense remains a broad, potentially unbounded problem in AI. Our focus is to move toward AI systems that can develop common-sense reasoning similar to humans to detect anomalies. In particular, we study the problem of detecting the violation of expectations when object appearance or motion dynamics change from...
    Resource Type:
    Capstone Project
    Full Text:
    quantify the tracker’s overall performance. MOTA = 1− ∑ t (FNt + FPt + IDSWt)∑ t GTt TABLE I TRACKERS

  • Leveraging Structures of the Data in Deep Learning

    Creator:
    Li, Xingyi
    Abstract:
    The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
    Resource Type:
    Dissertation
    Full Text:
    (ln d)1/2 max t,t′  N∑ i=1  m∑ j=1 xijt − m∑ j=1 xijt′ 21/2 (2.15) Putting those