Learn More
Captions in videos often play an important role in video information indexing and retrieval. In this paper, we present a novel video caption detection approach. We first apply a new Multiple Frames Integration (MFI) method to minimize the variation of the background of the image. A time-based minimum (or maximum) pixel value search is employed and Sobel(More)
We propose a novel approach for auto image annotation. In our approach, we first perform the segmentation of images into regions, followed by clustering of regions, before learning the relationship between concepts and region clusters using the set of training images with pre-assigned concepts. The main focus of this paper is two-fold. First, in the(More)
Automatic image annotation has been intensively studied for content-based image retrieval recently. In this paper, we propose a novel approach for this task. Our approach first performs the segmentation of images into regions, followed by the clustering of regions, before learning the associations between concepts and region clusters using the set of(More)
This year we have participated in all the four tasks including shot boundary determination, story segmentation, high-level feature extraction and video search task. Several low-level visual, audio and text features are extracted for each of the tasks. In order to reduce the semantic gap between low-level features and high-level concepts, we have tried to(More)
In this paper, we present a method for texturing arbitrary surface using minimum cut algorithm. This method is a general texturing method, where the user provides a 3D mesh and a texture sample, and gets the textured mesh as the output. Our method is very simple. We repeatedly paste texture patches onto the surface, which is segmented from a sample image.(More)
  • 1