CVPR Meetup Turkey 2021
inzva held its first CVPR 2021 Meetup for AI enthusiasts on July 11, 2021.
We had received 70 applications from 55 different institutions from both Turkey and abroad. inzva organizes the CVPR Meetup with an aim to bring experienced local AI enthusiasts from different universities, who either submitted a paper to the conference or follow the sessions closely, together with those who are ready to dive in-depth into the journey of the academic world of artificial intelligence. We plan to gather computer vision researchers and students to discuss and meet with fellow CVPR followers each year.
Take a look at the presentations below:
Zeynep Akata, University of Tübingen - ‘’Explainability and Compositionality in Deep Visual Recognition’’
Zeynep Akata started her speech with an introduction to Compositionality in Deep Visual Recognition. She then introduced CVPR 2021 papers she co-authored with her colleagues;
Learning Graph Embeddings for Compositional Zero-shot Learning. Mohammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021
https://arxiv.org/abs/1902.01780
Learning Graph Embeddings for Compositional Zero-shot Learning. Mohammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021,
https://arxiv.org/abs/2102.01987
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning. Yanbei Chen, Yongqin Xian, Almut Sophia Koepke, Zeynep Akata
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021,
https://arxiv.org/abs/2104.10955
Open World Compositional Zero-Shot Learning. Massimiliano Mancini, Mohammad Ferjad Naeem, Yongqin Xian, Zeynep Akata
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021,
https://arxiv.org/abs/2101.12609
Gül Varol, École des Ponts ParisTech - ‘Read and Attend: Temporal Localization in Sign Language Videos’
Gül Varol is an Assistant Professor at the IMAGINE team of École des Ponts ParisTech. She shared a little background about sign language and domain specific problems and then continued with her presentation on scaling up automatic sign language analysis that was published at CVPR 2021.
BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues, ECCV'20
https://arxiv.org/abs/2007.12131
Watch, read and lookup: learning to spot signs from multiple supervisors, ACCV'20
https://arxiv.org/abs/2010.04002
Read and Attend: Temporal Localisation in Sign Language Videos, CVPR'21
https://arxiv.org/abs/2103.16481
Aligning Subtitles in Sign Language Videos, arXiv'21
inzva is supported by BEV Foundation, an education foundation for the digital native generation which aims to build communities that foster peer-learning and encourage mastery through one-to-one mentorship.
Subscribe to our newsletter here and stay tuned for more hacker-driven activities by following us on social media.