Learn More
A typical gaze estimator needs an explicit personal calibration stage with many discrete fixation points. This limitation can be resolved by mapping multiple eye images and corresponding saliency maps of a video clip during an implicit calibration stage. Compared to previous calibration-free methods, our approach clusters eye images by using Gaussian(More)
One of the most hazardous driving scenario is the overtaking of a slower vehicle, indeed, in this case the front vehicle (being overtaken) can occlude an important part of the field of view of the rear vehicle's driver. This lack of visibility is the most probable cause of accidents in this context. Recent research works tend to prove that augmented reality(More)
Photo collections and its applications today attempt to reflect user interactions in various forms. Moreover, photo collections aim to capture the users’ intention with minimum effort through applications capturing user intentions. Human interest regions in an image carry powerful information about the user’s behavior and can be used in many photo(More)
We address the problem of composing a story out of multiple short video clips taken by a person during an activity or experience. Inspired by plot analysis of written stories, our method generates a sequence of video clips ordered in such a way that it reflects plot dynamics and content coherency. That is, given a set of multiple video clips, our method(More)
The best summary of a long video differs among different people due to its highly subjective nature. Even for the same person, the best summary may change with time or mood. In this paper, we introduce the task of generating customized video summaries through simple text. First, we train a deep architecture to effectively learn semantic embeddings of video(More)
Human gaze tracking has gathered much attention due to its capability to detect intuitive attention. Appearance-based methods can work with a single camera in ordinary conditions to track human gaze. An effective way to generate eye appearances is proposed using the Kinect. The head pose information is obtained from the Kinect after a series of(More)
An iterative detection scheme enhances the performance of bit-interleaved coded modulation (BICM) by exploiting frequency diversity gains. Additionally, space-time block coding (STBC) scheme can significantly improve the system performance in fading channels by proper coordinating of the signaling over multiple antennas. In this paper, STBC technique based(More)
This paper presents the 1024-QAM transmission system design, implementation and performance for providing UHDTV services over HFC network. The CNR@TOV (Threshold Of Visibility, BER of 3.6e-6) of proposed system is 32.7dB under AWGN and data throughput is 48.54Mbps within 6MHz bandwidth. In this paper, we provide a detail description of UHDTV(Ultra High(More)
  • 1