T
Tanveer Syeda-Mahmood
Researcher at IBM
Publications - 280
Citations - 5196
Tanveer Syeda-Mahmood is an academic researcher from IBM. The author has contributed to research in topics: Deep learning & Image segmentation. The author has an hindex of 35, co-authored 271 publications receiving 4481 citations. Previous affiliations of Tanveer Syeda-Mahmood include Massachusetts Institute of Technology & Xerox.
Papers
More filters
Patent
Multimedia database for use over networks
TL;DR: Disclosed as discussed by the authors is a multimedia database for use in distributed network environments, where a query processing module transforms user queries into search transformations that can be used for indexing; an attentional selection module records salient information represented in images by a hierarchy of feature maps, saliency maps, and combined saliency map; a declarative memory comprises active modules that update the representations acquired over time for the same images, as well as across images, to cluster, categorize and organize information extracted from different images by the attention al- selection module; and an indexing mechanism utilizes the
BookDOI
Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support
Patent
System for selecting multimedia databases over networks
TL;DR: In this article, a network server is provided which interfaces a client with selected database sites from a plurality of database sites, including both text information and multimedia information, consisting of a meta-database, a search agent and a refining module.
Book ChapterDOI
3D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object Sizes
TL;DR: A fast converging and computationally efficient network architecture for accurate segmentation and an exponential logarithmic loss which balances the labels not only by their relative sizes but also by their segmentation difficulties is proposed.
Proceedings Article
View-invariant Alignment and Matching of Video Sequences
TL;DR: A dynamic programming approach using the similarity measurement is proposed to find the nonlinear time-warping function for videos containing human activities and shows a great improvement compared to state-of-the-art techniques.