The Annual Catalan Meeting on Computer Vision (ACMCV) brings together the Computer Vision community of Catalonia, connecting research, talent generation and industry in one day. This meeting aims to strengthen the links among the Catalan Computer Vision actors, to disseminate within the community the most relevant works that have already been published abroad and to allow students from the Master’s Degree in Computer Vision to meet with members of the Catalan computer vision community and prospective employers.
Dates & Venue
Submission deadline | September 11, 2024
Registration deadline | September 16, 2024
ACMCV 2023 | September 18, 2024
Computer Vision Center & UAB School of Engineering
Program
| Start | End | Session | Location | More information |
|---|---|---|---|---|
| 14:00 | 14:45 | Track1: Msc Defences | EE Rooms / CVC Rooms | More info |
| 14:45 | 15:30 | Track2: Msc Defences | EE Rooms / CVC Rooms | More info |
| 15:30 | 16:15 | Track3: Msc Defences | EE Rooms / CVC Rooms | More info |
| 16:15 | 17:00 | Track4: Msc Defences | EE Rooms / CVC Rooms | More info |
| 17:00 | 17:45 | Track5: Msc Defences | EE Rooms / CVC Rooms | More info |
| 17:00 | 17:30 | Accreditation & poster setup | CVC Garden | |
| 17:30 | 17:50 | Industry pitch | CVC Garden | More info |
| 17:50 | 18:30 | Poster session and networking | CVC Garden | More info |
| 18:30 | 19:15 | Keynote talk: Dr Adrià Recasens: “A Multimodal Journey” | CVC Garden | More info |
| 19:15 | 19:30 | Awards & Closing | CVC Garden |
Keynote talk
A multimodal journey
Multimodal learning has seen unprecedented improvements over the last decade. The availability of large scale data combined with modeling and compute improvements have been the perfect environment for machine learning models to excel at understanding modalities beyond text. In this talk, we will do a brief review of the history of multimodal learning with special focus on techniques involving vision and audio – from early self-supervised learning techniques such as MMV to large language models such as Gemini that are able to process text, vision and audio combined.
Dr. Adrià Recasens
Staff Research Scientist at Google DeepMind
Resources
Organizers
Organizing Committee
- Maria Vanrell, CVC & UAB
- Josep Lladós, CVC & UAB
- Núria Martínez, CVC
- Marc Compte, CVC
- Aurora García, CVC
Poster Session Chair:
- Danna Xue, CVC