The Computer Vision Center at CVPR 2022
The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022, took place on 19-24 June in New Orleans and online. The Computer Vision Center contributed with the following papers:
CVPR Oral. An important milestone for CVC’s history!
- LaTr: Layout-Aware Transformer for Scene-Text VQA, by Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, and R. Manmatha
- Continually Learning Self-Supervised Representations with Projected Functional Regularization, by Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, and Joost van de Weijer - CVPR BEST PAPER AWARD
- Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization, by Francesco Pelosin (CVC PhD visiting student), Saurav Jha (CVC PhD student for some months), Andrea Torsello, Bogdan Raducanu, and Joost van de Weijer - CVPR RUNNER-UP PAPER AWARD
- Transferring Unconditional to Conditional GANs with Hyper-Modulation, by Héctor Laria, Yaxing Wang, Joost van de Weijer, and Bogdan Raducanu
- Slimmable Video Codec, by Z.Liu, Luis Herranz, Fei Yang, S. Zhang, S. Wan, M. Mrak, and M. Gorriz-Blanch
- Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition, by Kai Wang, Xialei Liu, Andy Bagdanov, Luis Herranz, Shangling Jui, and Joost van de Weijer
- 3DRRDB: Super Resolution of Multiple Remote Sensing Images using 3D Residual in Residual Dense Blocks, by Mohamed Ramzy Ibrahim, Robert Benavente, Felipe Lumbreras, and Daniel Ponsa
CVC researchers presented their work in New Orleans as well as online. Should you have any question, do not hesitate to contact them.