°ê¥ß°ª¶¯¤j¾Ç¸ê¤u112¾Ç¦~«×²Ä¤G¾Ç´Á®Ñ³ø°Q½×º[±MÃDºtÁ¿

°ê¥ß°ª¶¯¤j¾Ç¸ê°T¤uµ{¾Ç¨t

 

¤é´Á

®É¶¡

¦aÂI

Á¿ªÌ

¤º®e

2¤ë22¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

Ĭ®a½÷

¶}¾Ç·Ç³Æ©P

2¤ë29¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

¤u¬ã°|¹q¥ú©Ò´¼¼zµøı²Õ

³¯¾_¦t ³Õ¤h

´¼¼z¤u¦wXR¼ÒÀÀ°V½m§Þ³N

3¤ë7¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

±i©ú©Ó

©P§B¾±

­S³ÍÚô

¾G¤Sºú

ªLÀ³¾§

l   ±i©ú©Ó

Emotion recognition using spatial-temporal EEG features

through convolutional graph attention network

l   ©P§B¾±

TransUNet-Transformers Make Strong Encoders for Medical Image Segmentation

l   ­S³ÍÚô

Impact of Bandwidth Part(BWP) Switching on 5G NR System Performance

l   ªLÀ³¾§

ACTION++: Improving Semi-supervised Medical Image Segmentation

with Adaptive Anatomical Contrast

3¤ë14¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

§f«T§Ê

²Å®m¹Å

¸³®¦¦ö

§d©ö¾§

§E¬F¿«

l  §f«T§Ê

Ãþ¦ü Deutsch-Jozsa °ÝÃD¤§¬ã¨s

l  ²Å®m¹Å

An End-To-End Model Using Raw Waveform And Max Feature Map

For Deepfake Voice Detection

l  ¸³®¦¦ö

ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection

l  §d©ö¾§

Detection and Prediction of Probe Mark Damage in

Wafer Testing of IC Packaging and Testing

l  §E¬F¿«

POTENTIAL THREAT VECTORS TO 5G INFRASTRUCTURE WITH Multi-access Edge Computing

3¤ë21¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

¼ï¬X¦w

Ĭ¶²§{

²ø©ú©_

³\³Í´S

³\¬¥Þ³

l  ¼ï¬X¦w

Improved HMM by Deep Learning for Ear Classification

l  Ĭ¶²§{

ICDANE: Image-Centric Data Augmentation for Discontinuous Named Entity Recognition

l  ²ø©ú©_

Anonymization of Set-Valued Data via Top-Down, Local Generalization

l  ³\³Í´S

FedGEMS:Federated Learning of Larger Server Models via Selective Knowledge Fusion

l  ³\¬¥Þ³

Multi-document extractive text summarization based on firefly algorithm

3¤ë28¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

§d«ÉÁ¾

±i¨Øªâ

¨H§±»T

¬x¹ç¿[

¤ý«aÚ]

ªL¥ú¨°

l   §d«ÉÁ¾

TFLite hybrid model CNN-LSTM approach for automated lung disease detection through cough sound

l   ±i¨Øªâ

Audiovisual speech recognition based on a deep convolutional neural network

l   ¨H§±»T

Joint Control and Shared Channel Scheduling for Downlink in 3GPP Narrowband-IoT

l   ¬x¹ç¿[

TINYSTORIES: HOW SMALL CAN LANGUAGE MODELS BE AND STILL SPEAK COHERENT ENGLISH?

l   ¤ý«aÚ]

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

l   ªL¥ú¨°

CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework

4¤ë4¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

©ñ°²

©ñ°²

4¤ë11¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

¤ýÞ³ÄQ

ªL¸q¾±

³\µ¤¯ö

§d­Y¤Z

±i爲¶¶

¸­«T§Ê

l   ¤ýÞ³ÄQ

Automatic License Plate Recognition

l   ªL¸q¾±

Adaptive Traffic Management System based on Real-time Traffic Conditions

l   ³\µ¤¯ö

Cross-domain Recommendation with Bridge-Item Embeddings

l   §d­Y¤Z

Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving

l   ±i爲¶¶

DIE BOND ¨}²v¤ÀªR DIE BOND Yield Analysis

l   ¸­«T§Ê

Analyzing Transfer Learning of Vision Transformers for Interpreting Chest Radiography

4¤ë18¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

´Á¤¤¦Ò

´Á¤¤¦Ò

4¤ë25¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

¼ÚùÚ¸Î

¸¯¬R½å

ÃC¥ç¨j

Á©Ӧö

±ç¤åÃv

¼B¨|ºû

²øÞm¥Á

±i¹Åªå

5¤ë2¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

³¯®aºÂ

¶À©Ó¿Õ

§f©{»T

±i´I¬v

³¯¥°Ùy

5¤ë9¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

ÀuªÖ¼Æ¦ì´CÅ馳­­¤½¥q

ÁÂëÞªl¸g²z

5G+AIOT

5¤ë16¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

¡uµøı¦Û¾r¬ì§Þº[5G´¼¼zÁpºô§Þ³N¤§¼Æ¦ì³Ð·sÀ³¥Î¡vºØ¤l±Ð®v°ö°V¬ã°Q·|

°ê¥ß«ÌªF¤j¾Ç  ªL±M³Ó±Ð±Â 

5¤ë23¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

°ê®õª÷±±°ª¶¯¸ê°T¶}µo¤¤¤ß±MÃDºtÁ¿

5¤ë30¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

«n¬ì¶é°Ï

ÄP¹©¬ì§ÞªÑ¥÷¦³­­¤½¥q

 

6¤ë6¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

«n¬ì¶é°Ï

´¼´Q¸ê°TªÑ¥÷¦³­­¤½¥q

 

6¤ë13¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

«n¬ì¶é°Ï¼t°Ó²¤¶-2

6¤ë20¤é

13:30-15:00

¤u¾Ç°|1FºtÁ¿ÆU

´Á¥½¦Ò

½T»{¤À¼Æ