| 8:30-9:30 |
KEYNOTE: Title: E2EdgeAI: Energy Efficient Edge AI for On-device Situation Awareness | Tinoosh Mohsenin |
| 09:30-10:00 |
Linear Transformers beat YOLO for Embedded Object Detection |
Alberto Ancilotto, Edoardo Castagnini and Elisabetta Farella |
| 10:00-10:30 |
Coffee break |
| 10:30-11:00 |
Quantization-Aware Training for Autoencoder-Based Partitioning of CNNs |
Oscar Artur Bernd Berg, Eiraj Saqib, Isaac Sánchez Leal,
Axel Jantsch, Irida Shallari, Silvia Krug and Mattias O’Nils |
| 11:00-11:30 |
A Real-Time FPGA-Based Edge Computing Approach for Pedestrian Trajectory Prediction |
Wen-Hui Chen and Zong-Hua Ho |
| 11:30-12:00 |
TAVIC-DAS: Task and Channel-Aware Variable-Rate Image Compression for Distributed Autonomous System |
Gaurav Shinde, Anuradha Ravi, Emon Dey, Jared Lewis and
Nirmalya Roy |
| 12:00-13:30 |
LUNCH |
| 13:30-14:00 |
Learn More by Using Less: Distributed Learning with Energy-Constrained Devices |
Roberto Pereira, Cristian Jesus Vaca Rubio and Luis Blanco |
| 14:00-14:30 |
Neural Architecture Search for Efficient Mixed-Precision Quantization in Audio Denoising |
Alessandro Cerioli, Clement Laroche, Tobias Piechowiak,
Luca Pezzarossa and Martin Schoeberl |
| 14:30-15:00 |
Distributed VLMs: Efficient Vision-Language Processing through Cloud-Edge Collaboration |
Yuyang Li, Devika Gumaste, Mehmet Turkcan, Javad Ghaderi,
Gil Zussman and Zoran Kostic |
| 15:00-15:30 |
Coffee break |
| 15:30-16:00 |
EdgeSync: Efficient Edge-Assisted Video Analytics via Network Contention-Aware Scheduling |
Qiang Xu, Ravi K. Rajendran, Murugan Sankaradas and Srimat
T. Chakradhar |
| 16:00-16:30 |
Y-Net: A Compact Edge-Friendly Model for Multi-Modal Medical Image Segmentation |
Soma Dasgupta, Swarnava Dey, Avik Ghosh, Arijit Mukherjee
and Arpan Pal |
