J
John R. Smith
Researcher at IBM
Publications - 371
Citations - 20289
John R. Smith is an academic researcher from IBM. The author has contributed to research in topics: Image retrieval & TRECVID. The author has an hindex of 69, co-authored 371 publications receiving 19618 citations. Previous affiliations of John R. Smith include Moving Picture Experts Group & Columbia University.
Papers
More filters
Proceedings ArticleDOI
VisualSEEk: a fully automated content-based image query system
John R. Smith,Shih-Fu Chang +1 more
TL;DR: The VisualSEEk system is novel in that the user forms the queries by diagramming spatial arrangements of color regions by utilizing color information, region sizes and absolute and relative spatial locations.
Journal ArticleDOI
Adapting multimedia Internet content for universal access
TL;DR: This work presents a system that adapts multimedia Web documents to optimally match the capabilities of the client device requesting it using a representation scheme called the InfoPyramid that provides a multimodal, multiresolution representation hierarchy for multimedia.
Journal ArticleDOI
Large-scale concept ontology for multimedia
Milind Naphade,John R. Smith,Jelena Tesic,Shih-Fu Chang,Winston H. Hsu,Lyndon Kennedy,Alexander G. Hauptmann,Jon Curtis +7 more
TL;DR: The large-scale concept ontology for multimedia (LSCOM) is the first of its kind designed to simultaneously optimize utility to facilitate end-user access, cover a large semantic space, make automated extraction feasible, and increase observability in diverse broadcast news video data sets.
Proceedings ArticleDOI
Tools and techniques for color image retrieval
John R. Smith,Shih-Fu Chang +1 more
TL;DR: This work proposes a technique by which the color content of images and videos is automatically extracted to form a class of meta-data that is easily indexed and evaluates the retrieval effectiveness of the color set back-projection method and compares its performance to other color image retrieval methods.
Proceedings ArticleDOI
Learning Locally-Adaptive Decision Functions for Person Verification
TL;DR: The decision function for verification is proposed to be viewed as a joint model of a distance metric and a locally adaptive thresholding rule, and the inference on the decision function is formulated as a second-order large-margin regularization problem, and an efficient algorithm is provided in its dual from.