output
19962026
most citedSemi-Supervised Learning with Ladder Networks

582 citations

Showing 2021Show all

13 papers · 1 filter

cs.IT2021★ 2 cited

Optimal Probing Sequences for Polarization-Multiplexed Coherent Phase OTDR

Christian Dorize, Elie Awwad, Sterenn Guerrier +1

We introduce dual-polarization probing codes based on two circularly shifted frequency sweep signals enabling perfect channel estimation. This is achieved with a probing length equ…

cs.NI2021★ 33 cited

Multi-Connectivity in Mobile Networks: Challenges and Benefits

Carlos Pupiales, Daniela Laselva, Quentin De Coninck +2

Satisfying the stringent 5G Quality of Service (QoS) requirements necessitates efficient resource utilization by the mobile networks. Consequently, we argue that Multi-Connectivity…

cs.HC2021★ 30 cited

ComFeel: Productivity is a Matter of the Senses Too

Marios Constantinides, Sanja Šćepanović, Daniele Quercia +3

Indoor environmental quality has been found to impact employees' productivity in the long run, yet it is unclear its meeting-level impact in the short term. We studied the relation…

cs.CV2021★ 118 cited

Image coding for machines: an end-to-end learned approach

Nam Le, Honglei Zhang, Francesco Cricri +2

Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for thos…

cs.IT2021★ 9 cited

The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning

Mateus P. Mota, Alvaro Valcarce, Jean-Marie Gorce +1

In this paper, we propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MADDPG) algorithm, to enable a base station (BS) and user equipment (UE) t…

cs.NI2021★ 2 cited

Optimal Latency-Oriented Scheduling in Parallel Queuing Systems

Andrea Bedin, Federico Chiariotti, Stepan Kucera +1

The evolution of 5G and Beyond networks has enabled new applications with stringent end-to-end latency requirements, but providing reliable low-latency service with high throughput…