Microsoft Research

Computer Vision Natural Language Processing

Convergence between CV and NLP Modeling and Learning

Han Hu and Li Dong from Microsoft Research Asia talk about the convergence between computer vision, natural language processing, and machine learning in the following talk.

Read More
Computer Vision Robotics

Visual Recognition beyond Appearances, and its Robotic Applications

The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance. Yezhou Yang, among others, recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk will present the speaker’s efforts over the last decade. […]

Read More
Computer Vision Natural Language Processing Research

Tightly Connecting Vision and Language

Remarkable progress has been made at the intersection of vision and language. While showing great promise, current vision and language models may only weakly “connect” the two modalities and often fail in the wild. In this talk, Goggle’s Soravit Changpinyo will present recent efforts aiming to bridge this gap along two dimensions: informativeness and controllability. […]

Read More
IoT

Dependable IoT- Making data from IoT Devices Dependable and Trustworthy

The Internet of Things has been around for a while now and many businesses and organizations now depend on data from these systems to make critical decisions. At the same time, it is also well recognized that this data- even up to 40% of it- can be spurious, and this obviously can have a tremendously […]

Read More
AI Research

Introducing Retiarii: A deep learning exploratory-training framework on NNI

Traditional deep learning frameworks such as TensorFlow and PyTorch support training on a single deep neural network (DNN) model, which involves computing the weights iteratively for the DNN model. Designing a DNN model for a task remains an experimental science and is typically a practice of deep learning model exploration. Retrofitting such exploratory-training into the […]

Read More
AI Bioinformatics

Leveraging Computing in Biomedical Sciences and Public Health

Computational tools, with their power in big data processing and complex pattern modeling, may play an important role in helping us push the boundaries of our medical knowledge and what can be done for public health. During the past few years, Microsoft Research Asia (MSRA) has been actively exploring opportunities to leverage artificial intelligence and […]

Read More
Computer Vision Research Virtual Reality

Synthetic Data with Digital Humans

Microsoft Research posted this video where  Erroll Wood and Tadas Baltrusaitis discuss how synthetics drives work on understanding human faces and hands, including how it powers Fully Articulated Hand Tracking on HoloLens 2.

Read More
AI Research

SOLOIST: Building Task Bots at Scale

In this video tutorial by Microsoft Research, researchers demonstrate how pretrain grounded text generated (GTG) model can be finetuned and adapted to a specific task using conversation learner, a pretraining, finetuning and machine teaching framework to build task bots at scale.

Read More
AI Research

Knowledge Distillation as Semiparametric Inference

Microsoft Research highlights this research topic on Knowledge Distillation. More accurate machine learning models often demand more computation and memory at test time, making them difficult to deploy on CPU- or memory-constrained devices. Knowledge distillation alleviates this burden by training a less expensive student model to mimic the expensive teacher model while maintaining most of […]

Read More
Research Speech and Voice

Sound Capture and Speech Enhancement for Communication and Distant Speech Recognition

Microsoft Research discusses the general architecture of speech enhancement pipelines for the needs of hands-free telecommunication and distant speech recognition. The talk will discuss both classical approaches using statistical signal processing and deep learning using neural networks. It will be illustrated with real-life examples from the speech enhancement audio pipelines in Kinect, HoloLens, and Teams.

Read More