Schedule
13:30 | Opening Remarks |
13:35 | Keynote 1: DIANE LARLUS, NAVER LABS EUROPE AND MIAI GRENOBLE - Towards Geometric Understanding in Egocentric Videos |
14:20 | ORAL SESSION 1 |
15:00 | POSTER SESSION AND COFFEE BREAK |
16:00 | Keynote 2: LAURA LEAL-TAIXÉ, NVIDIA AND TECHNICAL UNIVERSITY OF MUNICH (TUM) - Towards scalable, low-maintenance, privacy-aware visual localization |
16:45 | ORAL SESSION 2 |
17:25 | Doctoral Consortium |
17:33 | Abstracts |
18:00 | Closing Remarks |
Oral Session 1 (8 minutes presentation + 2 minutes Q&A)
- Personalized Monitoring in Home Healthcare: An Assistive System for Post Hip Replacement Rehabilitation
- Real-Time Optimisation-Based Path Planning for Visually Impaired People in Dynamic Environments
- Vision-Based Treatment Localization with Limited Data: Automated Documentation of Military Emergency Medical Procedures
- Is context all you need? Scaling Neural Sign Language Translation to Large Domains of Discourse
Poster Session
- Enhancing Human-Robot Collaborative Object Search through Human Behavior Observation and Dialog
- Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
- IFPNet: Integrated Feature Pyramid Network with Fusion Factor for Lane Detection
- Multi-Camera 3D Position Estimation Using Conditional Random Field
- VLMAH: Visual-Linguistic Modeling of Action History for Effective Action Anticipation
- Towards estimation of human intent in assistive robotic teleoperation using kinaesthetic and visual feedback
- Learnt Contrastive Concept Embeddings for Sign Recognition
- A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset
- Multimodal Error Correction with Natural Language and Pointing Gestures
- Modeling Visual Impairments with Artificial Neural Networks: a Review
- Continuous Hand Gesture Recognition for Human-Robot Collaborative Assembly
- From Scarcity to Understanding: Transfer Learning for the Extremely Low Resource Irish Sign Language
- FewFaceNet: A Lightweight Few-Shot Learning-based Incremental Face Authentication for Edge Cameras
Oral Session 2 (8 minutes presentation + 2 minutes Q&A)
- SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction
- Affordance segmentation of hand-occluded containers from exocentric images
- Autonomous mobile robot for automatic out of stock detection in a supermarket
- Repetition-aware Image Sequence Sampling for Recognizing Repetitive Human Actions
Doctoral Consortium (6 minutes presentation + 2 minutes Q&A)
Abstracts (3 minutes presentations, Q&A at the end of the session)
- Pretrained Language Models as Visual Planners for Human Assistance
- HealthWalk: Promoting Health and Mobility through Sensor-Based Rollator Walker Assistance
- A Driver Warning System Based on Anticipation of Ego-Involved Accident Objects
- Few-Shot Object Pose Estimation for Functional Robotic Manipulation
- Eye Gaze Prediction System on Tablet Devices for People with Speech and Mobility Impairment
- Current Challenges with Modern Multi-Object Trackers
- Attention-based performance improvement for gaze localization
- Light Weight Computation and Compact Network for 3D Hand Pose Estimation from Depth