Tue, Feb 18 AM ME1
10:00 - 11:00 |
(1)
ITE-ME |
10:00-10:15 |
Momentum-Aware Difficulty Computation for Music Games and Its Application to Stage Data Editing |
Ryosuke Nosaka, Yoshinori Dobashi (Hokkaido Univ.) |
(2)
ITE-ME |
10:15-10:30 |
Highlight Scene Extraction Using Generative AI with Video and Speech Transcription Data
-- A Study on the Accurate Understanding of Timestamp Information -- |
Tomoki Haruyama, Cheng Zhou (NTT DOCOMO) |
(3)
ITE-ME |
10:30-10:45 |
A Note on Performance Improvement of Visual Emotion Classification via Multimodal LLM Introducing Text Prompt Optimization |
Ryo Takahashi, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(4)
ITE-ME |
10:45-11:00 |
A Note on Image-to-music Generation via Musical Caption Based on In-context Learning |
Shilin Liu, Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
| |
11:00-11:10 |
Break ( 10 min. ) |
Tue, Feb 18 AM AIT
Chair: Hisaki Nate (Tokyo Polytechnic Univ.)
11:10 - 11:40 |
(5)
ITE-AIT |
11:10-11:25 |
Automatic identification of license plates that cannot be identified by humans using GAN |
Atsushi Ichiyanagi, Ryuya Uda (TUT) |
(6)
ITE-AIT |
11:25-11:40 |
Efficient Physics Informed Dynamic Neural Fluid Fields Reconstruction From Sparse Video |
Yangcheng Xiang, Yoshinori Dobashi (Hokudai) |
| |
11:40-12:50 |
Lunch Break ( 70 min. ) |
Tue, Feb 18 PM ME2
12:50 - 14:05 |
(7)
ITE-ME |
12:50-13:05 |
A Note on Interpretability of Visual Language Model by Few-shot Learning based on the Linear Representation Hypothesis |
Hiroki Okamura, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(8)
ITE-ME |
13:05-13:20 |
Study on matching method between satellite and ground images using CLIP model |
Momoko Maezawa, Rei Endo, Naotsuna Fujimori, Takahiro Mochizuki (NHK) |
(9)
ITE-ME |
13:20-13:35 |
Enhancing Attracting-and-Dispersing Source-Free Domain Adaptation with Vision-and-Language Model |
Xinqi Shu (TMU), Shuhei Tarashima (NTT Com), Norio Tagawa (TMU) |
(10)
ITE-ME |
13:35-13:50 |
Effectiveness Verification of Introducing Model Merging in Federated Learning
-- Investigation from Multi-domain Image Classification Tasks -- |
Kenta Kubota, Reb Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(11)
ITE-ME |
13:50-14:05 |
Developing an Intersection Risk Estimation Using Semantic Segmentation |
Kazuto Nakagawa, Kazuma Nishimura, Jin Kadotani, Osamu Sugiyama, Masahiro Tada (Kindai Univ.) |
| |
14:05-14:15 |
Break ( 10 min. ) |
Tue, Feb 18 PM SIP/ME3
Chair: Tomoki Haruyama(NTT Docomo)
14:15 - 15:15 |
(12)
ITE-SIP |
14:15-14:30 |
Analysis of mountain climbing motion using loads on forefoot, midfoot and rearfoot |
Satoshi Shimada, Daisuke Kawamura (Nihon Univ.) |
(13)
ITE-ME |
14:30-14:45 |
バドミントンラケット検出のための特化型データセット構築 |
Muhammad Abdul Haq (TMU), Tarashima Shuhei (NTT Com), Tagawa Norio (TMU) |
(14)
ITE-ME |
14:45-15:00 |
Evaluating Existing Dense Pose Estimators on Diverse Body Shape Images |
BoTao Zhang (TMU), Shuhei Tarashima (NTT Communications), Norio Tagawa (TMU) |
(15)
ITE-ME |
15:00-15:15 |
Trial for Investigating Relationship between Older Drivers' Physical Function and Vehicle Control Behavior Using RTK-GNSS |
Ayumu Tsujimura (Kindai Univ..), Shohei Kagino (Morinomiya Univ. of Medical Sciences), Shingo Moriizumi (Tezukayama Univ..), Yoshio Fujita (CPUOHS), Kazumi Renge (Tezukayama Univ..), Osamu Sugiyama, Masahiro Tada (Kindai Univ..) |
| |
15:15-15:25 |
Break ( 10 min. ) |
Tue, Feb 18 PM ME4
15:25 - 16:40 |
(16)
ITE-ME |
15:25-15:40 |
Improving Object Detection Performance in Low-Light Scenes using Add-On Far-Infrared System |
Hikaru Fukushima, Isamu Takai (TOYOTA CENTRAL R&D LABS., INC.) |
(17)
ITE-ME |
15:40-15:55 |
A Note on Sensitivity Evaluation of Novel View Synthesis Metrics in 3D Scenes with Limited Conditions |
Haoyang Wang, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(18)
ITE-ME |
15:55-16:10 |
A Note on Personalized Anomaly Detection Based on Vision Language Model Using Image Prompt |
Haruka Matsuda, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(19)
ITE-ME |
16:10-16:25 |
Experimental Discussion on the Attention Mechanism of HEVC and 3D CG images Using Vision Transformer |
Norifumi Kawabata (Computational Imaging Lab) |
(20)
ITE-ME |
16:25-16:40 |
Trial for Recognizing Hazards in Traffic Scene Using a Vision-Language Model |
Kazuma Nishimura, Kazuto Nakagawa, Temma Okamoto, Osamu Sugiyama, Masahiro Tada (Kindai Univ.) |
Tue, Feb 18 AM IE1
09:15 - 10:30 |
(21)
IE |
09:15-09:30 |
Online Continual Learning on a Synthetic Contaminated Datastream |
Maorong Wang, Nicolas Michel, Jiafeng Mao, Toshihiko Yamasaki (UTokyo) |
(22)
IE |
09:30-09:45 |
Llava-Planner: Enhancing Spatial Awareness of LLaVA for Cost-Effective Path Planning |
Ling Xiao, Hiromasa Yamanishi, Toshihiko Yamasaki (UTokyo) |
(23)
IE |
09:45-10:00 |
Dataset Construction and Quality Classification Model Development for Automating Agricultural Crop Sorting Tasks |
Koyu Mizutani, Toshihiko Yamasaki (UTokyo) |
(24)
IE |
10:00-10:15 |
Learned Image Compression with State Space Model |
Shimon Murai (Waseda Univ.), Heming Sun (YNU), Jiro Katto (Waseda Univ.) |
(25)
IE |
10:15-10:30 |
Deep learning study of the relationship between aesthetic evaluations by category |
Akihiro Tsuchiya, Shunsuke Haga, Yoshiaki Yasumura (SIT) |
| |
10:30-10:40 |
Break ( 10 min. ) |
Tue, Feb 18 AM IE2
10:40 - 11:40 |
(26)
IE |
10:40-10:55 |
Leveraging Multimodal Large Language Models for Japanese Recipe Generation from Food Photos |
Yuki Imajuku, Yoko Yamakata, Kiyoharu Aizawa (Univ. of Tokyo) |
(27)
IE |
10:55-11:10 |
A Benchmark and Evaluation for Hard Out-of-Distribution Detection Using Vision-Language Model |
Shiho Noda, Atsuyuki Miyai, Qing Yu (UTokyo), Irie Go (TUS), Kiyoharu Aizawa (UTokyo) |
(28)
IE |
11:10-11:25 |
Pseudo-anomaly data generation method based on SVDD for anomaly detection |
Bourouis mouad, Tsuchio shuta, Kitamura takuya (NIT) |
(29)
IE |
11:25-11:40 |
Recipe suggestion system with generative AI based on flyer image |
Koga Tanaka, Takuya Kitamura (NIT) |
| |
11:40-12:50 |
Lunch Break ( 70 min. ) |
Tue, Feb 18 PM ITS1
12:50 - 13:50 |
(30)
ITS |
12:50-13:05 |
Towards optimized remote operation of driverless buses
-- Prelimanry study on evaluating remote monitoring performance using VR -- |
Koki Masuda (AIST/TUS), Yanbin Wu, Naohisa Hashimoto (AIST) |
(31)
ITS |
13:05-13:20 |
Research on a system for identifying pedestrians' intention to cross the road by posture estimation |
Daina Fujii (TUS) |
(32)
ITS |
13:20-13:35 |
Impainting of Preceding Vehicles from In-vehicle Camera Images based on Spatio-Temporal Image Processing
-- Aiming for Real Video Driving Simulator -- |
Shintaro Ono, Kazuki Matsumoto, Yudai Inoue, Da Li (Fukuoka Univ.) |
(33)
ITS |
13:35-13:50 |
Stress Reduction Method for Self-Driving Car by AR Information in Obstacle Avoidance |
Ryosuke Shigeto, Isidro Butaslac, Taishi Sawabe (NAIST), Masayuki Kanbara (NAIST/Konan Univ), Hirokazu Kato (NAIST) |
| |
13:50-14:00 |
Break ( 10 min. ) |
Tue, Feb 18 PM IE3
14:00 - 15:15 |
(34)
IE |
14:00-14:15 |
Difficulty-aware Generation for Image Classification |
Zerun Wang (UTokyo), Jiafeng Mao, Xueting Wang (CyberAgent), Toshihiko Yamasaki (UTokyo) |
(35)
IE |
14:15-14:30 |
Momentum Knowledge Distillation for Enhanced Online Continual Learning |
Nicolas Michel, Wang Maorong, Ling Xiao, Toshihiko Yamasaki (UTokyo) |
(36)
IE |
14:30-14:45 |
Exploiting LLM Quantization |
Kazuki Egashira (Univ. of Tokyo), Mark Vero, Robin Staab, Jingxuan He, Martin Vechev (ETHZ) |
(37)
IE |
14:45-15:00 |
Proposal of an object detection model based on intermediate feature fusion of visible light and infrared light images |
Keito Sasamori (MIT), Kousuke Hirasawa (KONICA MINOLTA), Satoshi Kondo (MIT) |
(38)
IE |
15:00-15:15 |
Automatic Scoring of Sports Based on Scene Segmentation and Motion Feature Learning Using Video Analysis |
Shun Tateuchi, Satoshi Kondo (Muroran Institute of Tech.) |
| |
15:15-15:25 |
Break ( 10 min. ) |
Tue, Feb 18 PM IE4
15:25 - 16:55 |
(39)
IE |
15:25-15:40 |
TourLMM: Task-Adaptive Retrieval-Augmented Multimodal Model for Tourism Domain |
Hiromasa Yamanishi, Xiao Ling, Toshihiko Yamasaki (UTokyo) |
(40)
IE |
15:40-15:55 |
StyleRec: Multimodal Recommendation Using Visual-Language Features Containing Sentimental Styles |
Chi Zhang, Luwei Zhang, Toshihiko Yamasaki (UTokyo) |
(41)
IE |
15:55-16:10 |
Feature Point Matching Accuracy Using Hyperspectral Images for High-performance 3D Reconstruction |
Tomohiro Yuguchi, Kaito Houjho, Ryota Fuse, Terumasa Aoki (TUT) |
(42)
IE |
16:10-16:25 |
Research on Lightweight Models for Speeding up Human Pose Estimation |
Akihiro Mizuki, Kazuki Ikeda, Shoto Morishita, Qiu Chen (Kogakuin Univ.) |
(43)
IE |
16:25-16:40 |
Adversarial Attack-Based Method for Protecting Facial Images from Generative AI |
Tomohiro Isono, Seishu Matsui, Terumasa Aoki (TUT) |
(44)
IE |
16:40-16:55 |
Explainable Image Aesthetic Assessment Leveraging Vision-Language Models |
Supatta Viriyavisuthisakul (PIM), Shun Yoshida, Kaede Shiohara, Ling Xiao, Toshihiko Yamasaki (UTokyo) |
Wed, Feb 19 AM ME Special Session 1
Chair: Yusuke Mizutani (Hokkaido Univ.)
09:00 - 10:25 |
(45)
ITE-ME |
09:00-09:15 |
[Special Talk]
Efforts at Hokkaido University Data-Driven Interdisciplinary Research Emergence Department
-- Establishing Foundations for Advanced Interdisciplinary Research and Digital Core Human Resource Development to Address Regional Issues -- |
Miki Haseyama, Yusuke Mizutani, Kosui Horiuchi, Hiroyuki Sasaki (Hokkaido Univ.) |
(46)
ITE-ME |
09:15-09:30 |
[Special Talk]
Developing Next-generation Infrastructure Maintenance Technologies with NEXCO EAST Group |
Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(47)
ITE-ME |
09:30-09:45 |
[Special Talk]
Development and Practice of Problem-Solving Research for Promoting Social Implementation in Collaboration with Nitori Holdings Co., Ltd |
Atsuo Maruyama, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(48)
ITE-ME |
09:45-10:00 |
[Special Talk]
Development and operation of Hokkaido University's Digital Reskilling Program |
Hisashi Ukawa, Takahiro Ogawa, Keisuke Maeda, Yusuke Mizutani, Katsutoshi Kondo, Miki Haseyama (Hokkaido Univ.) |
(49)
ITE-ME |
10:00-10:15 |
[Special Talk]
Government-academia collaboration efforts with the Hokkaido Development Bureau |
Katsutoshi Kondo (Hokkaido Univ.), Mitsuaki Yonemoto (Hokkaido Regional Development Bureau, Ministry of Land, Infrastr) |
| |
10:15-10:25 |
Q&A ( 10 min. ) |
| |
10:25-10:40 |
Break ( 15 min. ) |
Wed, Feb 19 AM ME Special Session 2
Chair: Takahiro Ogawa (Hokkaido Univ.)
10:40 - 12:00 |
(50)
ITE-ME |
10:40-10:50 |
[Special Talk]
Withered Tree Detection Technology by Semantic Segmentation and Depth Estimation for Efficient Daily Inspection on Highways |
Naoki Saito, Kazuki Yamamoto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(51)
ITE-ME |
10:50-11:00 |
[Special Talk]
Technology of Finding Generation Using Vision Language Model for Efficient Bridge Inspection on Highway |
Tatsuki Seino, Naoki Saito, Keisuke Maeda, Takahiro Ogawa, MIki Haseyama (Hokkaido Univ) |
(52)
ITE-ME |
11:00-11:10 |
[Special Talk]
A Note on Customer Interest Estimation Method Based on Multiple Transformer Models Using Real Store Video Data |
Teruhisa Yamashiro (NDB), Ren Togo (Hokkaido Univ.), Yuki Honma, Yu Yoshida (NDB), Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(53)
ITE-ME |
11:10-11:20 |
[Special Talk]
A Note on Supporting Interior Coordination Using Image Generation and Complementary Recommendation Techniques |
Keigo Sakurai, Hiroki Okamura, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(54)
ITE-ME |
11:20-11:30 |
[Special Talk]
Damage Classification Using Road Attachment Images Based on Vision Transformer and Vision Language Model |
Koshi Watanabe, Keisuke Maeda, Reb Togo, Takahiro Ogawa, Miki Haseyama (HU) |
(55)
ITE-ME |
11:30-11:40 |
[Special Talk]
Advanced Finding Generation AI Based on In-context Learning for Inspection Report Creation |
Masaya Sato, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(56)
ITE-ME |
11:40-11:50 |
[Special Talk]
Event Location Prediction from Urgent Calls based on Fine-tuning of Speech Recognition Models for Geographic Name Recognition |
Masaki Yoshida, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
| |
11:50-12:00 |
Q&A ( 10 min. ) |
| |
12:00-13:10 |
Lunch Break ( 70 min. ) |
Wed, Feb 19 PM MMS
Chair: Daisuke Kato (NHK)
13:10 - 13:55 |
(57)
ITE-MMS |
13:10-13:25 |
Experiments on image recognition by optelectronic deep neural network with scattering medium insertion |
Kaito Inoue, Takumi Hashiguchi, Taichi Takatsu, Rio Tomioka, Masanori Takabayashi (KIT) |
(58)
ITE-MMS |
13:25-13:40 |
Wavefront shaping-assisted multisite two-photon microscopy for recording distributed neuronal activity across the mouse cortex |
Hyojeong Shon (Hokkaido Univ.), Atsushi Shibukawa, Hideharu Mikami (RIES, Hokkaido Univ.) |
(59)
ITE-MMS |
13:40-13:55 |
Investigation of the dependence of the accuracy of signal beam detection on the center wavelength during the partially coherent readout by the Transport of Intensity Equation method |
Tomohiro Nishimura, Masatoshi Bunsen (Fukuoka Univ.) |
| |
13:55-14:05 |
Break ( 10 min. ) |
Wed, Feb 19 PM ME5
14:05 - 15:20 |
(60)
ITE-ME |
14:05-14:20 |
Reducing Computational Cost of 3D Human Pose and Shape Estimation Using Group-Mix Attention |
Yushan Wang (TMU), Shuhei Tarashima (NTT Com), Norio Tagawa (TMU) |
(61)
ITE-ME |
14:20-14:35 |
Study on Investigating Effectiveness of Lane Positioning Assistance from Road-Side Equipment in Low-Visibility Conditions Using Eye-Tracking HMD |
Kidai Morimoto, Ryutaro Ohta (Kindai Univ.), Hidekatsu Hamaoka (Akita Univ.), Toru Hagiwara (RMEC), Sho Takahashi (Hokkaido Univ.), Toshihiro Hiraoka (JARI), Kazumi Renge, Shingo Moriizumi (Tezukayama Univ.), Masahiro Tada (Kindai Univ.) |
(62)
ITE-ME |
14:35-14:50 |
Retrieval-based Nutrition Estimation from Food Images |
Satayu Parinayok, Yoko Yamakata, Kiyoharu Aizawa (UTokyo) |
(63)
ITE-ME |
14:50-15:05 |
A Note on the Effectiveness of Brain Activity Information Against Adversarial Attacks
-- Utilization of Image Reconstruction Method from Brain Signals Using Generative Models -- |
Tasuku Nakajima, Keisuke Maeda, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
(64)
ITE-ME |
15:05-15:20 |
A Note on Consideration of Spatial Integrity in Continuous 3D Scene Generation Method |
Yuki Era, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Wed, Feb 19 AM IE5
09:00 - 10:15 |
(65)
IE |
09:00-09:15 |
A Human Posture Detection Method Based on Robust Hausdorff Distance |
Shanqian Sun, Kohei Inoue (Kyushu Univ.) |
(66)
IE |
09:15-09:30 |
Application of Adversarial Defense Methods for High-Accuracy Underwater Object Detection |
Seishu Matsui, Terumasa Aoki (Tokyo University of Technology) |
(67)
IE |
09:30-09:45 |
Vision Transformer Construction Method Suitable for Medical Image |
Fumito Shimizu, Terumasa Aoki (TUT) |
(68)
IE |
09:45-10:00 |
Distinction Between Real and AI-Generated Images Based on Anomaly Detection |
Sora Kawai, Terumasa Aoki (TUT) |
(69)
IE |
10:00-10:15 |
A Study of Spectrally-varying PSFs-based Compressive Spectral Imaging with Structured Illumination |
Ryo Shirakawa, Yoko Sogabe, Shoichiro Saito, Masaki Kitahara (NTT) |
| |
10:15-10:25 |
Break ( 10 min. ) |
Wed, Feb 19 AM ITS2/IE6
10:25 - 11:55 |
(70)
ITS |
10:25-10:40 |
Communication-Efficient Real-Time External Abnormality Detection for AVs Using MLLMs |
Kiminobu Makino, Naoya Kaneko, Toru Furusawa, Haruka Futatsubashi, Shota Mishima (TMC) |
(71)
ITS |
10:40-10:55 |
A preliminary evaluation of a Lighting HMI to Improve Passengers' Safety and Comfort in Driverless Buses. |
Satoru Ogino (AIST/TUS), Yanbin Wu, Toru Kumagai, Takahiro Miura, Naohisa Hashimoto (AIST), Kosei Ido (AIST/TUS) |
(72)
ITS |
10:55-11:10 |
On the Effectiveness of Information Screens Applied Nudegs for Decreasing Passage Time of Airport Security Checkpoint |
Taisei Ichimura, Tetsuya Manabe (Saitama Univ.) |
(73)
IE |
11:10-11:25 |
View Generation of the Subject from Free Viewpoint Images and Its Evaluation |
Sota Yamazaki, Kaito Houjho, Aoki Terumasa (TUT) |
(74)
IE |
11:25-11:40 |
Skin Cancer Classification Using Hyperspectral Images Generated from RGB Images |
Ryota Fuse, Koki Shimizu, Terumasa Aoki (TUT) |
(75)
IE |
11:40-11:55 |
A Method of Free Viewpoint Image Methods Using for Deep-Learning Super-Resolution Techniques |
Kaito Houjho, Ren Nakasato, Terumasa Aoki (TUT) |
| |
11:55-13:05 |
Lunch Break ( 70 min. ) |
Wed, Feb 19 PM IE7
13:05 - 14:20 |
(76)
IE |
13:05-13:20 |
Optimal Bit Allocation in Multilayer Coding |
Yuichi Kondo, Yuichi Kusakabe, Atsuro Ichigaya (NHK) |
(77)
IE |
13:20-13:35 |
Effect of image feature localization by patching on subjective evaluation of coding distortion by binary decision |
Soichiro Honda, Kohei Hayashi, Hirokazu Kamei (NITech), Yoshihiro Maeda (SIT), Norishige Fukushima (NITech) |
(78)
IE |
13:35-13:50 |
Image Quality Enhancement of 3D Vascular Images Using Diffusion Models |
Masahiro Maruichi (SIT) |
(79)
IE |
13:50-14:05 |
3D Point Cloud Compression Using Multi-Stage Context Model |
Hayato Shimizu, Jiro Katto (Waseda) |
(80)
IE |
14:05-14:20 |
A Study of Frequency Domain Image Super-Resolution Using Discrete Cosine Transform |
Junichi Nakajima, Takayuki Kurozumi (NTT) |
| |
14:20-14:30 |
Break ( 10 min. ) |
Wed, Feb 19 PM IE8
14:30 - 15:45 |
(81)
IE |
14:30-14:45 |
Automatic Classification of Fundamental Sports Movements in Children's Developmental Stages Using a Depth Camera |
Kousei Yoshino (Muroran Institute of Tec.), Hajime Toda (Sapporo Medical Univ.), Satoshi Kondo (Muroran Institute of Tec.) |
(82)
IE |
14:45-15:00 |
Evaluation of Doctor Proficiency Using Behavioral Quality Assessments from Surgical Videos |
Manato Yatabe, Satoshi Kondo (MIT) |
(83)
IE |
15:00-15:15 |
Bowing Motion Analysis and Skill Evaluation Using Violin-Mounted Cameras and Image Recognition AI |
Kosei Sabato, Nobutaka Kuroki, Masahiro Numa (Kobe Univ.) |
(84)
IE |
15:15-15:30 |
Research on Handwritten Character Beautification Using Generative Adversarial Networks |
Kota Fukushima, Akihiro Ito, Qiu Chen (Kogakuin Univ.) |
(85)
IE |
15:30-15:45 |
Amodal Human Segmentation Using Human Pose Estimation |
Taiki Sugiura, Toru Tamaki (Nitech) |
| |
15:45-15:55 |
Break ( 10 min. ) |
Wed, Feb 19 PM IE9
15:55 - 16:55 |
(86)
IE |
15:55-16:10 |
Report generation of chest X-ray images by LLM using RAG |
Ayato Ota (MIT), Chiharu Kai, Satoshi Kasai (NUHW), Satoshi Kondo (MIT) |
(87)
IE |
16:10-16:25 |
Alignment of mammograms using a registration model |
Masahiro Shirahata (MIT), Chiharu Kai, Satoshi Kasai (NUHW), Satoshi Kondo (MIT) |
(88)
IE |
16:25-16:40 |
Development of a 360-Degree Video-Based Virtual Indoor Exploration System and Its Application to Train Stations |
Zhuofan Sun, Leslie Woehler (The Univ. of Tokyo), Satoshi Ikehata (NII), Kiyoharu Aizawa (The Univ. of Tokyo) |
(89)
IE |
16:40-16:55 |
Construction of a Perception-Based Facial Image Similarity Scale and Its Application to Face Anonymization |
Haruka Kumagai, Leslie Woehler (UTokyo), Satoshi Ikehata (NII), Kiyoharu Aizawa (UTokyo) |
: ie-
n
