Related papers: ANT: Learning Accurate Network Throughput for Bett…
Improvements in networking technologies and the steadily increasing numbers of users, as well as the shift from traditional broadcasting to streaming content over the Internet, have made video applications (e.g., live and Video-on-Demand…
Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over the Internet by offering several encoded versions for each video sequence. Each version (or representation) has a different resolution and bit…
Residual radio resources are abundant in wireless networks due to dynamic traffic load, which can be exploited to support high throughput for serving non-real-time (NRT) traffic. In this paper, we investigate how to achieve this by resource…
The increasing number of wireless communication technologies and standards bring immense opportunities and challenges to provide seamless connectivity in Hybrid Vehicular Networks (HVNs). HVNs could not only enhance existing applications…
We present Adaptive Memory Networks (AMN) that processes input-question pairs to dynamically construct a network architecture optimized for lower inference times for Question Answering (QA) tasks. AMN processes the input story to extract…
Visual explanation enables human to understand the decision making of Deep Convolutional Neural Network (CNN), but it is insufficient to contribute the performance improvement. In this paper, we focus on the attention map for visual…
This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the…
With the growing demand for dynamic real-time applications, online admission control for time-critical event-triggered (ET) traffic in Time-Sensitive Networking (TSN) has become a critical challenge. The main issue lies in dynamically…
Quality of Service (QoS) is provided in IEEE 802.11e protocol by means of HCF Controlled Channel Access (HCCA) scheduler which is efficient for supporting Constant Bit Rate (CBR) applications. Numerous researches have been carried out to…
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this…
This paper aims to improve video streaming by leveraging a simple observation: users are more sensitive to low quality in certain parts of a video than in others. For instance, rebuffering during key moments of a sports video (e.g., before…
An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting…
Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…
Optical wireless communication offers unprecedented communication speeds that can support the massive use of the Internet on a daily basis. In indoor environments, optical wireless networks are usually multi-user multiple-input…
Speech bandwidth extension (BWE) has demonstrated promising performance in enhancing the perceptual speech quality in real communication systems. Most existing BWE researches primarily focus on fixed upsampling ratios, disregarding the fact…
Video activity recognition has become increasingly important in robots and embodied AI. Recognizing continuous video activities poses considerable challenges due to the fast expansion of streaming video, which contains multi-scale and…
360-degree video provides an immersive 360-degree viewing experience and has been widely used in many areas. The 360-degree video live streaming systems involve capturing, compression, uplink (camera to video server) and downlink (video…
This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…
Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over…
Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. With recent state-of-the-art attention-based automatic speech recognition (ASR) structure, NAR can realize promising real-time factor (RTF)…