Sciweavers

CVPR
2012
IEEE
11 years 6 months ago
WhittleSearch: Image search with relative attribute feedback
We propose a novel mode of feedback for image search, where a user describes which properties of exemplar images should be adjusted in order to more closely match his/her mental m...
Adriana Kovashka, Devi Parikh, Kristen Grauman
ICDAR
2011
IEEE
12 years 3 months ago
Character n-Gram Spotting in Document Images
—In this paper, we present a novel approach to search and retrieve from document image collections, without explicit recognition. Existing recognition-free approaches such as wor...
M. Sudha Praveen, K. Pramod Sankar, C. V. Jawahar
CIS
2008
Springer
13 years 6 months ago
A Novel Motion Based Lip Feature Extraction for Lip-Reading
In a lip-reading system, one key issue is how to extract the visual features, which greatly impact on the lip-reading recognition accuracy and efficiency. In this paper, we propos...
Meng Li, Yiu-ming Cheung
AAAI
2007
13 years 6 months ago
Template-Independent News Extraction Based on Visual Consistency
Wrapper is a traditional method to extract useful information from Web pages. Most previous works rely on the similarity between HTML tag trees and induced template-dependent wrap...
Shuyi Zheng, Ruihua Song, Ji-Rong Wen
CIVR
2006
Springer
126views Image Analysis» more  CIVR 2006»
13 years 8 months ago
Semantics Supervised Cluster-Based Index for Video Databases
High-dimensional index is one of the most challenging tasks for content-based video retrieval (CBVR). Typically, in video database, there exist two kinds of clues for query: visual...
Zhiping Shi, Qingyong Li, Zhiwei Shi, Zhongzhi Shi
FGR
2000
IEEE
161views Biometrics» more  FGR 2000»
13 years 8 months ago
Learning and Synthesizing Human Body Motion and Posture
A novel approach is presented for estimating human body posture and motion from a video sequence. Human pose is defined as the instantaneous image plane configuration of a singl...
Rómer Rosales, Stan Sclaroff
CASES
2004
ACM
13 years 9 months ago
A low power architecture for embedded perception
Recognizing speech, gestures, and visual features are important interface capabilities for future embedded mobile systems. Unfortunately, the real-time performance requirements of...
Binu K. Mathew, Al Davis, Michael Parker
MLDM
2005
Springer
13 years 9 months ago
Unsupervised Learning of Visual Feature Hierarchies
We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method c...
Fabien Scalzo, Justus H. Piater
MIR
2005
ACM
176views Multimedia» more  MIR 2005»
13 years 10 months ago
Hybrid visual and conceptual image representation within active relevance feedback context
Many of the available image databases have keyword annotations associated with the images. In spite of the availability of good quality low-level visual features that reflect wel...
Marin Ferecatu, Nozha Boujemaa, Michel Crucianu
IROS
2006
IEEE
131views Robotics» more  IROS 2006»
13 years 10 months ago
Implementing Planar Motion Tracking Algorithms on CMOS+FPGA Vision System
— This paper describes a 1,000Hz visual feedback using the CMOS+FPGA vision. It is required to obtain positional and angular signals around 1,000Hz to control a mechanical system...
Kazuhiro Shimizu, Shinichi Hirai