Related papers: Optimal Frame Transmission for Scalable Video with…
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive…
We propose a scalable video broadcasting scheme over MIMO-OFDM systems. The scalable video source layers are channel encoded and modulated into independent signal streams, which are then transmitted from the allocated antennas in certain…
We address the design and synthesis of optimal control strategies for high-dimensional stochastic dynamical systems. Such systems may be deterministic nonlinear systems evolving from random initial states, or systems driven by random…
The interaction of neural networks with physical equations offers a wide range of applications. We provide a method which enables a neural network to transform objects subject to given physical constraints. Therefore an U-Net architecture…
3D spatial perception is the problem of building and maintaining an actionable and persistent representation of the environment in real-time using sensor data and prior knowledge. Despite the fast-paced progress in robot perception, most…
Video content delivery over wireless networks is expected to grow drastically in the coming years. In this paper, we investigate the challenging problem of video over cognitive radio (CR) networks. Although having high potential, this…
This paper considers the problem of designing a dynamical system to solve constrained optimization problems in a distributed way and in an anytime fashion (i.e., such that the feasible set is forward invariant). For problems with separable…
To deliver ultra-high resolution 360-degree video (such as 8K, 12K, or even higher) across the internet, viewport-dependent streaming becomes necessary to save bandwidth. During viewport switches, clients and servers will instantly exchange…
The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video. There are some works on similar topics like detecting scene cuts in a video, but…
In this paper, we investigate resource allocation problem in the context of multiple virtual reality (VR) video flows sharing a certain link, considering specific deadline of each video frame and the impact of different frames on video…
We propose a multicast scheduling scheme to exploit content reuse when there is asynchronicity in user requests. A unicast transmission setup is used for content delivery, while multicast transmission is employed opportunistically to reduce…
The main task of HTTP Adaptive Streaming is to adapt video quality dynamically under variable network conditions. This is a key feature for multimedia delivery especially when quality of service cannot be granted network-wide and, e.g.,…
A (unit norm) frame is scalable if its vectors can be rescaled so as to result into a tight frame. Tight frames can be considered optimally conditioned because the condition number of their frame operators is unity. In this paper we…
We introduce a multi-scale framework for low-level vision, where the goal is estimating physical scene values from image data---such as depth from stereo image pairs. The framework uses a dense, overlapping set of image regions at multiple…
We consider a general class of low complexity distributed scheduling algorithms in wireless networks, maximal scheduling with priorities, where a maximal set of transmitting links in each time slot are selected according to certain…
We investigate the network stability problem when two users are scheduled simultaneously. The key idea is to simultaneously transmit to more than one users experiencing different channel conditions by employing hierarchical modulation. For…
We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a…
Tree projections provide a unifying framework to deal with most structural decomposition methods of constraint satisfaction problems (CSPs). Within this framework, a CSP instance is decomposed into a number of sub-problems, called views,…
Autonomous systems not only need to understand their current environment, but should also be able to predict future actions conditioned on past states, for instance based on captured camera frames. However, existing models mainly focus on…
We present a novel hierarchical framework for optimal transport (OT) using string diagrams, namely string diagrams of optimal transports. This framework reduces complex hierarchical OT problems to standard OT problems, allowing efficient…