BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
DTSTART:19791021T023000
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
TZNAME:HKT
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260818T024251Z
UID:44D86750-A33F-405F-B55B-85C25659C06A
DTSTART;TZID=Asia/Hong_Kong:20260907T103000
DTEND;TZID=Asia/Hong_Kong:20260907T113000
DESCRIPTION:A Seminar from IEEE Communications Society Distinguished Lectur
 er Program\n\nSeminar Title: Joint Semantic Source Channel Coding: GAP Bet
 ween Ideal and Reality\n\nSpeaker: Prof. Wei CHEN\n\nSchool of Electronic 
 and Information Engineering\,\n\nBeijing Jiaotong University\n\nDate: 7 Se
 ptember\, 2026.\n\nTime: 10:30am-11:30am\n\nVenue: G6302\, Yeung Kin Man A
 cademic Building\n\nAbstract:\n\nSemantic communications is considered as 
 a promising technology to increase the efficiency of next-generation commu
 nication systems\, particularly targeting human-machine and machine-type c
 ommunications. In contrast to the source-agnostic approach of conventional
  wireless communication systems\, semantic communication seeks to ensure t
 hat only the relevant information for the underlying task is communicated 
 to the receiver. Considering that most semantic communication applications
  have strict latency\, bandwidth\, and power constraints\, a prominent app
 roach is to model them as a joint source-channel coding (JSCC) problem. Al
 though JSCC has been a long-standing open problem in communication and cod
 ing theory\, remarkable performance gains have been shown recently over ex
 isting separate source and channel coding systems\, particularly in low-la
 tency and low-power scenarios. Recent progress is thanks to the adoption o
 f deep learning techniques for joint source-channel code design that outpe
 rform the concatenation of state-of-the-art compression and channel coding
  schemes\, which are results of decades-long research efforts. In this tal
 k\, I will introduce deep learning based JSCC (DeepJSCC) architecture for 
 semantic communications\, introduce its design principles and benefits\, a
 nd highlight the GAP (Generalization\, Adaptability\, Practicality) betwee
 n ideal and reality.\n\nCo-sponsored by: Department of Electrical Engineer
 ing\, City University of Hong Kong\n\nSpeaker(s): CHEN Wei\, \n\nAgenda: \
 nA Seminar from IEEE Communications Society Distinguished Lecturer Program
 \n\nSeminar Title: Joint Semantic Source Channel Coding: GAP Between Ideal
  and Reality\n\nSpeaker: Prof. Wei CHEN\n\nSchool of Electronic and Inform
 ation Engineering\,\n\nBeijing Jiaotong University\n\nDate: 7 September\, 
 2026.\n\nTime: 10:30am-11:30am\n\nVenue: G6302\, Yeung Kin Man Academic Bu
 ilding\n\nRoom: G6302\, Bldg: Kin Man Academic Building\, City University 
 of Hong Kong\, 83 Tat Chee Avenue\, Kowloon Tong\, Hong Kong\, Hong Kong\,
  Hong Kong
LOCATION:Room: G6302\, Bldg: Kin Man Academic Building\, City University of
  Hong Kong\, 83 Tat Chee Avenue\, Kowloon Tong\, Hong Kong\, Hong Kong\, H
 ong Kong
ORGANIZER:lindai@cityu.edu.hk
SEQUENCE:117
SUMMARY:Joint Semantic Source Channel Coding: GAP Between Ideal and Reality
URL;VALUE=URI:https://events.vtools.ieee.org/m/573101
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;&lt;span style=&quot;text-decoration: underline\;&quot;
 &gt;&lt;span style=&quot;color: rgb(0\, 0\, 0)\; text-decoration: underline\;&quot;&gt;&lt;stron
 g&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;A Seminar from IEEE Communicati
 ons Society Distinguished Lecturer Program&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/span&gt;&lt;/
 p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, aria
 l\, sans-serif\;&quot;&gt;&lt;strong&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;Seminar
  Title: Joint Semantic Source Channel Coding: GAP Between Ideal and Realit
 y&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;fon
 t-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;strong&gt;&lt;span data-olk-copy-so
 urce=&quot;MessageBody&quot;&gt;Speaker: Prof.&amp;nbsp\;Wei CHEN&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p
 &gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial
 \, sans-serif\;&quot;&gt;&lt;strong&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;&amp;nbsp\; 
 &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; School of Electronic and I
 nformation Engineering\,&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height
 : 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;strong
 &gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;&amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; 
 &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; Beijing Jiaotong University&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;
 &lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, ar
 ial\, sans-serif\;&quot;&gt;&lt;strong&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;Date:
  7 September\, 2026.&lt;/span&gt;&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\
 ;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;strong&gt;&lt;sp
 an data-olk-copy-source=&quot;MessageBody&quot;&gt;Time: 10:30am-11:30am&lt;/span&gt;&lt;/strong
 &gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvet
 ica\, arial\, sans-serif\;&quot;&gt;&lt;strong&gt;Venue: G6302\, Yeung Kin Man Academic 
 Building&lt;/strong&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;
 &lt;strong&gt;Abstract:&lt;/strong&gt;&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;\n&lt;p&gt;&lt;span data-olk-copy-sourc
 e=&quot;MessageBody&quot;&gt;Semantic communications is considered as a promising techn
 ology to increase the efficiency of next-generation communication systems\
 , particularly targeting human-machine and machine-type communications. In
  contrast to the source-agnostic approach of conventional wireless communi
 cation systems\, semantic communication seeks to ensure that only the rele
 vant information for the underlying task is communicated to the receiver. 
 Considering that most semantic communication applications have strict late
 ncy\, bandwidth\, and power constraints\, a prominent approach is to model
  them as a joint source-channel coding (JSCC) problem. Although JSCC has b
 een a long-standing open problem in communication and coding theory\, rema
 rkable performance gains have been shown recently over existing separate s
 ource and channel coding systems\, particularly in low-latency and low-pow
 er scenarios. Recent progress is thanks to the adoption of deep learning t
 echniques for joint source-channel code design that outperform the concate
 nation of state-of-the-art compression and channel coding schemes\, which 
 are results of decades-long research efforts. In this talk\, I will introd
 uce deep learning based JSCC (DeepJSCC) architecture for semantic communic
 ations\, introduce its design principles and benefits\, and highlight the 
 GAP (Generalization\, Adaptability\, Practicality) &amp;nbsp\;between ideal an
 d reality.&lt;/span&gt;&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p&gt;&lt;span style=&quot;text-decora
 tion: underline\;&quot;&gt;&lt;span style=&quot;color: rgb(0\, 0\, 0)\;&quot;&gt;&lt;span data-olk-co
 py-source=&quot;MessageBody&quot;&gt;A Seminar from IEEE Communications Society Disting
 uished Lecturer Program&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1
 \;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;span data
 -olk-copy-source=&quot;MessageBody&quot;&gt;Seminar Title: Joint Semantic Source Channe
 l Coding: GAP Between Ideal and Reality&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-
 height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;
 span data-olk-copy-source=&quot;MessageBody&quot;&gt;Speaker: Prof.&amp;nbsp\;Wei CHEN&lt;/spa
 n&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helve
 tica\, arial\, sans-serif\;&quot;&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;&amp;nbs
 p\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; School of Electronic a
 nd Information Engineering\,&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;
 &quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;span data-o
 lk-copy-source=&quot;MessageBody&quot;&gt;&amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp\; &amp;nbsp
 \; &amp;nbsp\; Beijing Jiaotong University&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-h
 eight: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\, arial\, sans-serif\;&quot;&gt;&lt;s
 pan data-olk-copy-source=&quot;MessageBody&quot;&gt;Date: 7 September\, 2026.&lt;/span&gt;&lt;/s
 pan&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;font-family: helvetica\
 , arial\, sans-serif\;&quot;&gt;&lt;span data-olk-copy-source=&quot;MessageBody&quot;&gt;Time: 10:
 30am-11:30am&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;line-height: 1\;&quot;&gt;&lt;span style=&quot;f
 ont-family: helvetica\, arial\, sans-serif\;&quot;&gt;Venue: G6302\, Yeung Kin Man
  Academic Building&lt;/span&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR