loading
Improved Robust Video Saliency Detection Based on Long-Term Spatial-Temporal Information
2020 Edition, Volume 29, January 1, 2020 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

This paper proposes to utilize supervised deep convolutional neural networks to take full advantage of the long-term spatial-temporal information in order to improve the video saliency detection performance. The conventional methods, which use the temporally neighbored frames solely, could...

Throwing a Change-Up, Pitching a Strike: An Autoethnography of Frame Acquisition, Application, and Fit in a Pitch Development and Delivery Experience
2016 Edition, Volume 59, December 1, 2016 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

Research problem: Studies how one entrepreneur acquired, applied, and fit frames to her startup venture and stakeholders over one year. Research questions: How do pitchers acquire frames for pitches? How do pitchers apply frames to existing pitches? How do pitchers gauge...

Flow-Motion and Depth Network for Monocular Stereo and Beyond
Volume PP - IEEE - Institute of Electrical and Electronics Engineers, Inc.

We propose a learning-based method that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration, our network estimates relative camera poses and the depth map of...

Window Design for Non-Orthogonal Interference Reduction in OFDM Receivers
2006 Edition, July 1, 2006 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

For conventional orthogonal frequency-division multiplexing (OFDM) systems, the guard interval is disregarded in the receiver and rectangular shaped windows are used implicitly due to the discrete Fourier transform (DFT). We consider a Nyquist-shaped window in the...

MixPred: Video Prediction Beyond Optical Flow
Volume PP - IEEE - Institute of Electrical and Electronics Engineers, Inc.

Video prediction is a meaningful task for it has a wide range of application scenarios. And it is also a challenging task since it needs to learn the internal representation of a given video for both appearance and motion dynamics. The existing methods regard this problem as a...

Blind channel estimation for OFDM systems based on non-redundant linear recording
2003 Edition, January 1, 2003 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

In this paper we consider a novel approach that can be applied on a single transmit/receive antenna OFDM system, to increase multipath diversity, and at the same time, enable blind channel estimation at the receiver. A non-redundant linear precoder is applied on each...

Models for Static and Dynamic Texture Synthesis in Image and Video Compression
2011 Edition, Volume 5, November 1, 2011 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

In this paper, we investigate the use of linear, parametric models of static and dynamic texture in the context of conventional transform coding of images and video. We propose a hybrid approach incorporating both conventional transform coding and texture-specific methods for improvement of...

Bayesian DeNet: Monocular Depth Prediction and Frame-wise Fusion with Synchronized Uncertainty
Volume PP - IEEE - Institute of Electrical and Electronics Engineers, Inc.

Using deep convolutional neural networks (CNN) to predict depth from a single image has received considerable attention in recent years due to its impressive performance. However, existing methods process each single image independently without leveraging the multi-view information of video...

Flow-Motion and Depth Network for Monocular Stereo and Beyond
2020 Edition, Volume 5, April 1, 2020 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

We propose a learning-based method 1 1 https://github.com/HKUST-Aerial-Robotics/Flow-Motion-Depth that solves monocular stereo and can be extended to fuse depth information from multiple target frames. Given two unconstrained images from a monocular camera with known intrinsic calibration,...

Semi-blind channel estimation scheme with Bayesian DFE for PRP-OFDM system
2015 Edition, November 1, 2015 - IEEE - Institute of Electrical and Electronics Engineers, Inc.

This paper presents a novel block-based Bayesian decision feedback equalization (DFE) receiver for the Pseudo-Random Postfix (PRP) Orthogonal Frequency Division Multiplexing (OFDM) (PRP-OFDM) systems, with semi-blind channel estimation. In conventional PRP-OFDM...

Advertisement