CVPR internal seminar
As every year, the CVC will be present at the most important gathering in the Computer Vision Science Community, the annual Computer Vision and Pattern Recognition conference (CVPR). In this edition, CVC researchers will present a total of seven papers. The conference will be held 19-24 June in New Orleans and online.
CVC will contribute with the following papers:
CVPR Oral. An important milestone for CVC’s history!
LaTr: Layout-Aware Transformer for Scene-Text VQA, by authors Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, R. Manmatha.
Continually Learning Self-Supervised Representations with Projected Functional Regularization, by authors Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, Joost van de Weijer.
Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization, by authors Francesco Pelosin (CVC PhD visiting student), Saurav Jha (CVC PhD student for some months), Andrea Torsello, Bogdan Raducanu, Joost van de Weijer.
Transferring Unconditional to Conditional GANs with Hyper-Modulation, by authors Héctor Laria, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu.
Slimmable Video Codec, by authors Z. Liu, Luis Herranz, Fei Yang, S. Zhang, S. Wan, M. Mrak, M. Gorriz-Blanch.
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition, by authors Kai Wang, Xialei Liu, Andy Bagdanov, Luis Herranz, Shangling Jui, Joost van de Weijer.
3DRRDB: Super Resolution of Multiple Remote Sensing Images using 3D Residual in Residual Dense Blocks, by authors Mohamed Ramzy Ibrahim, Robert Benavente, Felipe Lumbreras, Daniel Ponsa.