CVC celebrated the 7th Annual Catalan Meeting on Computer Vision (ACMCV 2020) that was held online this year, on September 22nd. ACMCV is annually organized by the Master in Computer Vision coordinators of the Catalan universities UAB, UOC, UPC and UPF. The aims of this meeting are to strengthen the Catalan academic and industrial computer vision network, to disseminate the most relevant works and to allow students from the Master in Computer Vision meet with members of the Catalan computer vision community.
This year’s edition started, as always, with the presentation of the final master thesis by the students from the Master in Computer Vision in parallel with a virtual poster session. A total of 53 papers were accepted in the poster session, all of them were papers already published between 2019 and 2020 either in top impact factor journals and highly ranked conferences. Each author had the access to a virtual room where they could discuss and present their work to the community.
The event was followed by the Keynote Lecture, carried out this year by Dr. Jordi Pont-Tuset, research scientist at Google Research in Switzerland, who talked on “Connecting Vision and Language with Localized Narratives”. After the conference, Dr. Jordi Pont-Tuset answered the audience’s questions and gave important advice to students that are about to start their professional careers.
After the Keynote Lecture, the event continued with a spotlight session in which 11 papers from the poster session were presented. The authors had 5 minutes to highlight the main issues of their work. The list of authors and papers presented in the spotlight session is the following:
- Vacit Oguz Yacizi (CVC / Wide Eyes Technologies) | Orderless Recurrent Models for Multi-label Classification (CVPR 2020)
- Ciprian Adrian Corneanu (UB) | Computing the Testing Error without a Testing Set (CVPR 2020)
- Yaxing Wang (CVC) | MineGAN: effective knowledge transfer from GANs to target domains with few images (CVPR 2020)
- Lei Kang (CVC) | GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images (ECCV 2020)
- Pau Rodriguez (ElementAI) | Embedding Propagation: Smoother Manifold for Few-Shot Classification (ECCV2020)
- Raquel Gil (University of Giessen / UPF) | Color matching images with unknown non-linear encodings (IEEE Transactions on Image Processing)
- Yi Xiao (CVC) | Multimodal end-to-end autonomous driving (IEEE Transactions on Intelligent Transportation Systems)
- Adriana Fernandez (UPF) | CoGANs for unsupervised visual speech adaptation to new speakers (ICASSP)
- Miriam Bellver (BSC) | Mask-guided sample selection for Semi-Supervised Instance Segmentation (Multimedia Tools and Applications)
- Jordi Gené Mola (UdL) | Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry (Computers and Electronics in Agriculture)
- Maria Gonzalez-i-Calabuig (UPC) | Curriculum Learning for Recurrent Video Object Segmentation (ECCV Workshops)
Finally, the event was closed with Dr. Maria Vanrell, Director of the Master in Computer Vision, giving the awards to this year’s top 5 Graduated Students and to the Best Master Dissertation.
ACMCV 2020 program and more details can all be found at its website: http://acmcv.cat/