J
Jarrell Waggoner
Researcher at University of South Carolina
Publications - 20
Citations - 342
Jarrell Waggoner is an academic researcher from University of South Carolina. The author has contributed to research in topics: Image segmentation & Scale-space segmentation. The author has an hindex of 7, co-authored 20 publications receiving 323 citations.
Papers
More filters
Proceedings Article
Video in sentences out
Andrei Barbu,Alexander Bridge,Zachary Burchill,Dan Coroian,Sven Dickinson,Sanja Fidler,Aaron Michaux,Sam Mussman,Siddharth Narayanaswamy,Dhaval Salvi,Lara Schmidt,Jiangnan Shangguan,Jeffrey Mark Siskind,Jarrell Waggoner,Song Wang,Jinlian Wei,Yifan Yin,Zhiqi Zhang +17 more
TL;DR: In this article, the authors present a system that produces sentential descriptions of video: who did what to whom, and where and how they did it, and extract the information needed to render these linguistic entities requires an approach to event recognition that recovers object tracks, the track-to-role assignments, and changing body posture.
Proceedings ArticleDOI
Two perceptually motivated strategies for shape classification
TL;DR: Two new, perceptually motivated strategies to better measure the similarity of 2D shape instances that are in the form of closed contours are proposed and can be integrated into available shape matching methods to improve the performance of shape classification on several widely-used shape data sets.
Proceedings ArticleDOI
Handwritten text segmentation using average longest path algorithm
TL;DR: This paper uses a graph model that describes the possible locations for segmenting neighboring characters, and develops an average longest path algorithm to identify the globally optimal segmentation, which finds the text segmentation with the maximum average likeliness for the resulting characters.
Proceedings ArticleDOI
Free-shape subwindow search for object localization
TL;DR: This paper proposes a new graph-theoretic approach for object localization by searching for an optimal subwindow without pre-specifying its shape, and requires the resulting subwindow to be well aligned with edge pixels that are detected from the image.
Journal ArticleDOI
3D Materials Image Segmentation by 2D Propagation: A Graph-Cut Approach Considering Homomorphism
TL;DR: This paper develops a propagation framework for materials image segmentation where each propagation is formulated as an optimal labeling problem that can be efficiently solved using the graph-cut algorithm.