Blog(8)

• [CVPR 2022 Series #6] Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders

  Variational Autoencoder (VAE) [5,6] is one of the most popular deep latent variable models in modern machine learning. In VAE, we have a rich representational capacity to model a complex generative process of synthesizing images (x) from the latent variables (z).

• [CVPR 2022 Series #5] P>M>F: The Pre-Training, Meta-Training and Fine-Tuning Pipeline for Few-Shot Learning

  Many technical challenges must be overcome to provide excellent AI experience to users of Samsung devices. The Cambridge AI Center focuses on 'multimodal AI' technology, 'data efficient AI' and 'On-device AI technology that makes AI models work efficiently and robustly on Samsung's devices'. First, it is essential to handle multimodality for a natural interaction experience with users.

• Fast and Accurate Inference in Variational Autoencoders

  Variational Autoencoders (VAE) [2,3] and Generative Adversarial Networks (GAN) [4] are the most popular deep generative models for high dimensional data (e.g., images).

View More

Research Areas(0)

Publications(7)

• Reviving Iterative Training with Mask Guidance for Interactive Segmentation

  AuthorAnton Konushin

  PublishedIEEE International Conference on Image Processing (ICIP)

  Date2022-10-23

• Real-time RGBD-based Extended Body Pose Estimation

  AuthorRenat Bashirov, Anastasia Ianina, Karim Iskakov, Yevgeniy Kononenko, Valeriya Strizhkova, Victor Lempitsky, Alexander Vakhitov

  PublishedIEEE Winter Conference on Applications of Computer Vision (WACV)

  Date2021-01-05

• Foreground-aware Semantic Representations for Image Harmonization

  AuthorKonstantin Sofiiuk, Polina Popenova, Anton Konushin

  PublishedIEEE Winter Conference on Applications of Computer Vision (WACV)

  Date2021-01-05

View More

News(5)

• [Blog] Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-Stage Action Localization

  Samsung AI Center Cambridge (SAIC-C) performs world-class blue-sky AI research with an open and collaborative approach to science. SAIC-C publishes its results in top scientific venues and releases open source code and datasets to facilitate engagement with the wider academic community.

• Hamid Sheikh and Sven Dickinson of Samsung Electronics Named IEEE Fellows

  Samsung Electronics today announced that Dr. Hamid Sheikh of Samsung Research America (SRA) and Dr. Sven Dickinson of the Samsung AI Center (SAIC) in Toronto have both been named a Fellow of the Institute of Electrical and Electronics Engineers (IEEE), the world’s largest technical professional organization.

• Samsung AI Center – Montreal Researchers Win the Best Paper Award at IEEE GLOBECOM 2021

  Researchers from Samsung AI Center – Montreal (SAIC-Montreal) received the Best Paper Award at the annual IEEE (Institute of Electrical and Electronics Engineers) Global Communications Conference (GLOBECOM) 2021 Mobile and Wireless Networks Symposium. GLOBECOM is the IEEE Communications

View More

Others(4)

• Samsung Research AI Center

  About Us Papers Samsung Research Artificial Intelligence Center (SAIC) was established in November 2017, consolidating various AI-related research teams within the Samsung Electronics Corporate R&D Center. SAIC is the flagship research institute of Samsung Electronics and is a center for the coordination of all AI-themed research at global AI centers newly established in the United States, Canada, the United Kingdom, and Russia, as well as collaboration with top eng...

• Samsung AI Center - Toronto

  About Us Papers The greater Toronto area is the epicenter of machine learning, and is one of the world’s foremost hubs for AI research and development. It is home not only to world-class talents but also to some of the most innovative start-ups in the field of artificial intelligence. SAIC Toronto will serve as a center of excellence for collaborative research in Canada. As the second Samsung AI center to be established in North America, SAIC-Toronto is led by Dr....

• Samsung AI Forum 2019

  Seoul, November 4 ~ 5 Samsung AI Forum is an academic event for the foremost minds of today’s world to come together and share their views on the current and future development of Artificial Intelligence technology. On-line pre-registration will open on September 24, 2019. Samsung AI Forum 2019Play Participants Anyone with an interest in AI technology including undergraduate and graduate students, university faculty members, researchers, and members of the general ...

View More