C
C.-C. Jay Kuo
Researcher at University of Southern California
Publications - 1070
Citations - 20283
C.-C. Jay Kuo is an academic researcher from University of Southern California. The author has contributed to research in topics: Computer science & Wavelet. The author has an hindex of 59, co-authored 955 publications receiving 16671 citations. Previous affiliations of C.-C. Jay Kuo include Ningbo University & Beihang University.
Papers
More filters
Journal ArticleDOI
On theory and regularization of scale-limited extrapolation
Li-Chien Lin,C.-C. Jay Kuo +1 more
TL;DR: It is proved that the scale-limited signal space can be decomposed into the direct sum of two subspaces and only the component in one subspace can be exactly reconstructed, where the reconstructible subspace could be interpreted as a space consisting of scale/time-limited signals.
Proceedings ArticleDOI
Box Refinement: Object Proposal Enhancement and Pruning
TL;DR: This work proposes a box refinement method by searching for the optimal contour for each initial bounding box that minimizes the contour cost, and shows that this method can significantly improve the object recall at a high overlapping threshold while maintaining a similar recalls at a loose one.
Proceedings ArticleDOI
Multi-order-residual (MOR) video coding: framework, analysis, and performance
TL;DR: A novel multi-order-residual (MOR) coding approach is proposed for high-bit-rate video compression in this work that encodes prediction residuals in multiple stages according to their correlation characteristics and outperforms H.264/AVC by a significant margin.
Proceedings ArticleDOI
Stochastic approach for motion vector estimation in video coding
Sungook Kim,C.-C. Jay Kuo +1 more
TL;DR: This research proposes a new fast MV estimation algorithm by using a statistical approach that allows the center and the size of the search window to vary according to the motion vectors obtained in coding previous frames.
Posted Content
Object Boundary Guided Semantic Segmentation
TL;DR: Zhang et al. as mentioned in this paper proposed an object boundary guided FCN (OBG-FCN), which is able to integrate the distinct properties of object shape and class features elegantly in a fully convolutional way with a designed masking architecture.