Sciweavers

161 search results - page 32 / 33
» Area-Feature Boundary Labeling
Sort
View
ICCV
1998
IEEE
13 years 11 months ago
Condensing Image Databases when Retrieval is Based on Non-Metric Distances
One of the key problems in appearance-based vision is understanding how to use a set of labeled images to classify new images. Classification systems that can model human performa...
David W. Jacobs, Daphna Weinshall, Yoram Gdalyahu
ADL
1998
Springer
164views Digital Library» more  ADL 1998»
13 years 11 months ago
Story Segmentation and Detection of Commercials in Broadcast News Video
The Informedia Digital Library Project [Wactlar96] allows full content indexing and retrieval of text, audio and video material. Segmentation is an integral process in the Informe...
Alexander G. Hauptmann, Michael J. Witbrock
GIS
2009
ACM
13 years 11 months ago
Classification of raster maps for automatic feature extraction
Raster maps are widely available and contain useful geographic features such as labels and road lines. To extract the geographic features, most research work relies on a manual st...
Yao-Yi Chiang, Craig A. Knoblock
EMNLP
2007
13 years 9 months ago
Finding Good Sequential Model Structures using Output Transformations
In Sequential Viterbi Models, such as HMMs, MEMMs, and Linear Chain CRFs, the type of patterns over output sequences that can be learned by the model depend directly on the modelâ...
Edward Loper
NIPS
2008
13 years 9 months ago
Semi-supervised Learning with Weakly-Related Unlabeled Data: Towards Better Text Categorization
The cluster assumption is exploited by most semi-supervised learning (SSL) methods. However, if the unlabeled data is merely weakly related to the target classes, it becomes quest...
Liu Yang, Rong Jin, Rahul Sukthankar