Research
Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning for image-text and video-text tasks. It takes raw videos/images + text as inputs, and outputs task predictions. ClipBERT is designed based on 2D CNNs…
We have developed a new algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. This release accompanies our research paper. We hope to help the privacy community run more accurate…
Analyses of text corpora over time can reveal trends in beliefs, interest, and sentiment about a topic. We focus on views expressed about artificial intelligence (AI) in the New York Times over a 30-year period.…
Research code for CVPR 2021 paper “End-to-End Human Pose and Mesh Reconstruction with Transformers”
This project is a large dataset, along with baseline trained machine learning models, for the tasks of table detection and table structure recognition in scientific PDF documents. Current datasets for table structure recognition are small…
The library implements the parallel collision search algorithm by van Oorschot and Wiener (vOW) on hardware, with the goal of concretely assessing the classical security of the Supersingular Isogeny Key Encapsulation (SIKE) protocol. SIKE is…
Code for NAACL 2021 paper Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents.
Uses InfluxDB, Grafana and the Azure IoT Node.js SDK (opens in new tab) to communicate with Azure IoT Hub (opens in new tab) and showcase how the Verified Telemetry features can be utilized in real world scenarios.
Getting Started with Verified Telemetry, Azure RTOS and Azure IoT