We're sorry for delay on opening this program.
HASCA Workshop will take place on Saturday, 5th Oct. at Victoria Suite (Room 2).
Presentation time:
HASCA oral presentation - 15 min (10-min talk + 5-min Q&A)
Other presentation - follow the timetable
08:00-09:00 |
Registration
|
09:00-10:30 |
Session 1: HASCA session[90min] (Chair: Tsuyoshi Okita)
- Large Language Models for Generating Semantic Nursing Activity Logs: Exploiting Temporal and Contextual Information
Nazmun Nahid (Kyushu Institute of Technology), Ryuya Munemoto (Kyushu Institute of Technology), Sozo Inoue (Kyushu Institute of Technology)
- Synthetic Skeleton Data Generation using Large Language Model for Nurse Activity Recognition
Umang Dobhal (Dronacharya Collge of Engineering), Christina Alvarez Garcia (Kyushu Institute of Technology), Sozo Inoue (Kyushu Institute of Technology)
- Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition
Mengxi Liu (German Research Center for Artificial Intelligence), Daniel Geißler (German Research Center for Artificial Intelligence), Dominique Nshimyimana (DFKI), Sizhen Bian (ETH Zürich), Bo Zhou (German Research Center for Artificial Intelligence), Paul Lukowicz (DFKI)
- PrISM: Unified Framework for Task Assistants powered by Multimodal Human Activity Recognition
Riku Arakawa (Carnegie Mellon University), Mayank Goel (Carnegie Mellon University)
- DNN Model Comparison for Sensor Location Robustness
Yu Enokibori (Nagoya University), Takahiro Saito (Nagoya University), Kenji Mase (Nagoya University)
- Emotion Recognition on the Go: Utilizing Wearable IMUs for Personalized Emotion Recognition
Zikang Leng (Georgia Institute of Technology), Myeongul Jung (Hanyang University), Sungjin Hwang (Hanyang University), Seungwoo Oh (Hanyang University), Lizhe Zhang (Georgia Institute of Technology), Thomas Ploetz (Georgia Institute of Technology), Kwanguk Kim (Hanyang University)
|
10:30-11:00 |
Coffee Break
|
11:00-12:30 |
Session 2: HASCA session[30min] + WEAR sesion[60min] (Chair: Marius Bock)
HASCA
- Diffusion Model-based Classifier for Human Activity Recognition
Kosuke Ukita (Kyushu Institute of Technology), Tsuyoshi Okita (Kyushu Institute of Technology)
- Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models
Shruthi Kashinath Hiremath (Georgia Institute of Technology), Thomas Ploetz (Georgia Institute of Technology),
WEAR
- Introduction and Challenge Overview
Marius Bock
- TA-DA! - Improving Activity Recognition using Temporal Adapters and Data Augmentation
Maximilian Hopp (University of Siegen), Helge Hartleb (University of Siegen), Robin Burchard (University of Siegen)
- Left-Right Swapping and Upper-Lower Limb Pairing for Robust Multi-Wearable Workout Activity Detection
Jonas Van Der Donckt (Ghent University), Jeroen Van Der Donckt (Ghent University - imec), Sofie Van Hoecke (Ghent University - imec)
- Augmentation Approaches to Refine Wearable Human Activity Recognition
Somesh Salunkhe (University of Siegen), Shubham Pradeep Shinde (University of Siegen), Pradnyesh Patil (University of Siegen), Robin Burchard (University of Siegen)
- Results & Winners Ceremony
|
12:30-14:00 |
Lunch Break
|
14:00-15:30 |
Session 3: SHL session[90min] (Chair: Mathias Ciliberto, Kazuya Murao, Lin Wang)
- Summary talk [15 min]
- Paper 1 [12 min]
- Paper 2 [12 min]
- Paper 3 [12 min]
- Ceremony [5 min]
- Poster [10 min]
|
15:30-16:00 |
Coffee Break with SHL poster (cont'd)
|
16:00-17:30 |
Session 4: HASCA session[90min] (Chair: Yu Enokibori)
- Water Level Recognition by Analyzing the Sound when Pouring Water
Atsuhiro Fujii (Ritsumeikan University), Kazuya Murao (Ritsumeikan University)
- A System to Visualize Differences in Paddling Timing between Teammates in Rowing
Daiki Takahashi (Ritsumeikan University), Kazuya Murao (Ritsumeikan University)
- A Monocular Fisheye Video-Based 2D to 3D Pose Lift Technique with Multiperson Spatial Context Integration
Iqbal Hassan (Kyushu Institute of Technology), Nazmun Nahid (Kyushu Institute of Technology), Sozo Inoue (Kyushu Institute of Technology)
- Composite Image Generation Using Labeled Segments for Pattern-Rich Dataset without Unannotated Target
Kazuma Kano (Nagoya University), Yuki Mori (Nagoya University), Keisuke Higashiura (Nagoya University), Tahera Hossain (Nagoya University), Shin Katayama (Nagoya University), Kenta Urano (Nagoya University), Takuro Yonezawa (Nagoya University), Nobuo Kawaguchi (Nagoya University)
- User Authentication Method for Smart Glasses using Gaze Information of Registered Known Images and AI-generated Unknown Images
Masaya Inoue (Ritsumeikan University), Kazuya Murao (Ritsumeikan University)
- Face Recognition Reinforcement using Pulse Waves of Front Camera Face Image and Rear Camera Finger Image on a Smartphone
Taiki Yuma (Ritsumeikan University), Kazuya Murao (Ritsumeikan University)
|
17:30- |
Closing
|