| 09:00-10:30 |
Session 1: HASCA paper session 1 [90 min] (Chair: Kazuya Murao)
- Opening talk (10 min)
- Where Are the Best Positions of IMUs for HAR?- Investigation with four DNN models of different characteristics (15 min)
Yu Enokibori, Takahiro Sato, Kenji Mase (Nagoya University)
- Smartphone-Based Activity Recognition in a Logistics Warehouse Using Self-supervised Representation Learning (15 min)
Kisho Watanabe, Kazuma Kano, Tahera Hossain, Shin Katayama, Kenta Urano, Takuro Yonezawa, Nobuo Kawaguchi (Nagoya University)
- Identifying Routine from Sequences of Activities of Daily Living in Smart-homes (15 min)
Sayeda Shamma Alia, Paula Lago (Concordia University)
- One-Class Classifier-based Incremental Learning Method to Personalize Multi-Class Human Activity Recognition Models from Streaming Data (15 min)
Pekka Siirtola (University of Oulu)
- FedFitTech: A Baseline in Federated Learning for Fitness Tracking (15 min)
Zeyneddin Oz, Shreyas Korde, Marius Bock, Kristof Van Laerhoven (University of Siegen)
|
| 11:00-12:30 |
Session 2: WEAR challenge session [90 min] (Chair: Marius Bock)
|
| 14:30-16:00 |
Session 3: SHL challenge session [90min] (Chair: Mathias Ciliberto)
- Opening Remarks (5 min)
- (Summary Task 1)Summary of SHL Challenge 2025: Locomotion and Transportation Mode Recognition Using Foundation Models (12 min)
Lin Wang (Queen Mary University of London), Mathias Ciliberto (University of Cambridge), Hristijan Gjoreski (University in Skopje), Paula Lago (Concordia University), Kazuya Murao (Ritsumeikan University), Tsuyoshi Okita (Kyushu Institute of Technology), Daniel Roggen (University of Sussex)
- (Summary Task 2)Foundation Models to Tackle Activity Recognition in Unknown Domain: Sussex-Huawei Locomotion Challenge 2025 Task 2 (12 min)
Tsuyoshi Okita, Kosuke Ukita, Asahi Miyazaki, Daichi Kubota, Jukichi Ota, Naoki Kagiyama, Asahi Nishikawa, Daichi Nagayasu, Syunya Tomitaka, Daisuke Nozaki, Yuki Odo, Raku Yamashita, Xiaolong Ye, Huayu Gao, Kazuki Okahashi, Koki Matsuishi, Masaharu Kagiyama, Kodai Hirata, Haruki Kai (Kyushu Institute of Technology), Lin Wang (Queen Mary University of London), Hristijan Gjoreski (University in Skopje), Mathias Ciliberto (University of Cambridge), Paula Lago (Concordia University), Kazuya Murao (Ritsumeikan University), Daniel Roggen (University of Sussex)
- (Oral Presentation Task 2)Robust Sensor-Based Activity Recognition under Domain Shift via Fine-Tuning the Time-Series Foundation Model (12 min)
Ryoichi Sekiguchi, Hiroshi Minowa, Masaki Kawakatsu (Tokyo Denki University)
- Video show - Task 1 (8 min)
- (Oral Presentation Task 1)Revisiting Foundation Models for Human Activity Recognition: Multiresolution Sensor Fusion with TimesFM (12 min)
Takumi Hyugaji, Itsuki Theo Terashita, Masaki Kawakatsu (Tokyo Denki University)
- (Oral Presentation Task 1)Ensemble of Foundation Models for Sensor-Based Locomotion and Transportation Mode Recognition (12 min)
Mohammad Foad Abdi, Yousef Alikhani, Mohammad Mahdi Azizi, Mohammad Saleh Azizikia, Bagher BabaAli, Mohammad Mahdi Mohebbizadeh, Arash Nasr Esfahani
- (Oral Presentation Task 1)IMU2IMG: IMU in the Language of Vision Foundation Models (12 min)
Sunkyung Lee, Hyuntae Jeong, Seungeun Chung, Kyoung Ju Noh, Jeong Mook Lim, Gyuwon Jung, Se Won Oh
- Ceremony (5 min)
|
| 16:30-17:45 |
Session 4: HASCA paper session [75min] (Chair: Pekka Siirtola)
- Mouth Gesture Recognition Using PPG Sensors in Earbuds (15 min)
Taiki Yuma, Kazuya Murao (Ritsumeikan University)
- Evaluating Rhythmic Representations in Mental Health from Wearable Devices Using the GLOBEM Datasets (15 min)
Melika Mirzaseyedi, Abdelwahab Hamou-lhadj, Paula Lago (Concordia University)
- Fingerprint Spoof Detection during Fingerprint Authentication Using Active Acoustic Sensing (15 min)
Koki Okeda, Kazuya Murao (Ritsumeikan University)
- Controlling the Influence of Ranking Information on Preference Judgments by Information Presentation Across Perceptual Channels (15 min)
Sho Nakazawa, Kyosuke Futami, Kazuya Murao (Ritsumeikan University)
- Silent Speech-Based Personal Authentication Using a Mask-Type Device with Infrared Sensors (15 min)
Takumi Sakamoto, Kyosuke Futami, Kazuya Murao (Ritsumeikan University)
|