1642480134_maxresdefault.jpg
92
15:09

Applications of Deep Neural Networks Course Overview (1.1, Spring 2022)

Spring 2022 Version. Applications of deep neural networks is a course offered in a hybrid format by Washington University in St. Louis. This course introduces Keras deep neural networks and highlights applications that neural networks are particularly adept at handling compared to previous machine learning models. Deep learning is a group of exciting new technologies […]
1641533301_maxresdefault.jpg
16
01:02:36

Trends in Computer Vision with Georgia Gkioxari – #549

Happy New Year! We’re excited to kick off 2022 joined by Georgia Gkioxari, a research scientist at Meta AI, to showcase the best advances in the field of computer vision over the past 12 months, and what the future holds for this domain. Welcome back to AI Rewind! In our conversation Georgia highlights the emergence […]
1641182808_maxresdefault.jpg
7
09:51

INTRODUCING PYTORCH LIVE | RAZIEL ALVAREZ GUEVARA & ROMAN RÄDLE

PyTorch’s mission is to accelerate the path from research prototyping to production deployment. With the growing mobile ML ecosystem, this has never been more important than before. With the aim of helping reduce the friction for mobile developers to create novel ML-based solutions, we introduce PyTorch Live: a tool to build, test and (in the […]
1640225340_maxresdefault.jpg
11
10:01

KORNIA AI: LOW LEVEL COMPUTER VISION FOR AI

Kornia is a differentiable library that allows classical computer vision to be integrated into deep learning models. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation […]
1640143282_maxresdefault.jpg
35
07:21

Using Pretrained Neural Networks with Keras (6.3)

Keras allows you make use of advanced pretrained neural networks for computer vision. You can make use this training, or perhaps only use the structure of these advanced neural networks, and train for your own images. Code for This Video: https://github.com/jeffheaton/t81_558_deep_learning/blob/master/t81_558_class_06_3_resnet.ipynb Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton Tweets by jeffheaton Support Me on Patreon: […]
1639879373_maxresdefault.jpg
12
08:47

TORCHVISION 2021 | FRANCISCO MASSA

TorchVision contains building blocks that facilitate research and experimentation in computer vision, including popular datasets, model architectures and common image transformations. In this talk, Francisco Massa (Research Engineer, Meta AI) presents the latest developments that happened over the last year, including mobile support, new models and improved IO, and discusses what to expect in the […]
1639407617_maxresdefault.jpg
4
49:26

Aaron Ames Interview – Integrative Learning for Robotic Systems

This week on the podcast we’re featuring a series of conversations from the AWS re:Invent conference in Las Vegas. I had a great time at this event getting caught up on the latest and greatest machine learning and AI products and services announced by AWS and its partners. Today we’re joined by Aaron Ames, Professor […]
1638539754_maxresdefault.jpg
4
42:21

Deep Learning for Automatic Basketball Video Production with Julian Quiroga – #389 (Video)

Today we return to our coverage of the 2020 CVPR conference with a conversation with Julian Quiroga, a Computer Vision Team Lead at Genius Sports. Julian presented his recent paper “As Seen on TV: Automatic Basketball Video Production using Gaussian-based Actionness and Game States Recognition” at the CVSports workshop. We jump right into the paper, […]
1638413192_maxresdefault.jpg
0
05:06

CoRL 2020, Spotlight Talk 526: Robust Policies via Mid-Level Visual Representations: An Experimen…

**Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation** Bryan Chen (UC Berkeley)*; Alexander Sax (UC Berkeley); Francis Lewis (Stanford); Iro Armeni (Stanford University); Silvio Savarese (Stanford University); Amir Zamir (Swiss Federal Institute of Technology (EPFL)); Jitendra Malik (University of California at Berkeley); Lerrel Pinto (NYU/Berkeley) Publication: http://corlconf.github.io/paper_526/ **Abstract** Vision-based robotics […]
1637844604_maxresdefault.jpg
89
04:35

Building Machine Learning models with Edge Impulse

Meet Jan Jongboom (CTO) and Jenny Plunkett (Engineer) at Edge Impulse (edgeimpulse.com), a company that makes it easy for developers to work with TinyML using TensorFlow. Edge Impulse has an active developer community (with 50,000 projects and growing!) See two quick demos, with links you can use to learn more. Resources: Edge Impulse → https://goo.gle/3BVQyDG […]
Two Minute Papers: This Fools Your Vision | Two Minute Papers #241
2.06K
03:11

Two Minute Papers: This Fools Your Vision | Two Minute Papers #241

The paper “Adversarial Examples that Fool both Human and Computer Vision” is available here: https://arxiv.org/abs/1802.08195 Our Patreon page with the details: https://www.patreon.com/TwoMinutePapers We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Andrew Melnychuk, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Esa Turkulainen, Lorin Atzberger, Malek […]
1636739872_maxresdefault.jpg
2
01:00:21

Trust in AI – TWiML Online Meetup – April 2018

**SUBSCRIBE AND TURN ON NOTIFICATIONS** **twimlai.com** This video is a recap of our April 2018 TWiML Online Meetup. In this month’s community segment we chatted about explainability, Carlos Guestrin’s LIME paper, Europe’s attempt to ban “untrustworthy” AI systems and finally, Community member Nicolas Teague (@Nic_T) shares a blog post he wrote entitled “A Sight for […]
1636237797_maxresdefault.jpg
0
14:53

Research talk: WebQA: Multihop and multimodal

Speaker: Yonatan Bisk, Assistant Professor, Carnegie Mellon University Web search is fundamentally multimodal and multihop. Often, even before asking a question, individuals go directly to image search to find answers. Further, rarely do we find an answer from a single source, opting instead to aggregate information and reason through implications. Despite the frequency of this […]
1636226783_maxresdefault.jpg
0

Panel Discussion: Large-scale neural platform models: Opportunities, concerns, and directions

Speakers: Eric Horvitz, Chief Scientific Officer, Microsoft Miles Brundage, Head of Policy Research, OpenAI Yejin Choi, Professor, University of Washington / AI2 Percy Liang, Associate Professor, Standord University Large-scale, pretrained neural models are driving significant research and development across multiple AI areas. They have played a major role in research efforts and have been at […]
1636104681_maxresdefault.jpg
19
37:28

All Data AI with Dr. Andrew Fitzgibbon

Episode 80 | June 12, 2019 You may not know who Dr. Andrew Fitzgibbon is, but if you’ve watched a TV show or movie in the last two decades, you’ve probably seen some of his work. An expert in 3D computer vision and graphics, and head of the new All Data AI group at Microsoft […]
1636101007_maxresdefault.jpg
32
01:08:12

AI for Earth’s Land Cover Mapping

High-resolution land cover mapping is a process of assigning land use labels, such as “impervious surface,” or “tree canopy” to each pixel in high resolution (&lt1m) aerial or satellite imagery. Such maps are an essential component in environmental science, agriculture, forestry, urban development, the insurance and banking industries, and for demography in developing countries. Traditional […]
1636093461_maxresdefault.jpg
13
01:27:21

AI-Driven Image Captioning For Inclusive Productivity

Advances in hybrid intelligence, deep learning, and related artificial intelligence techniques have provided us with a remarkable opportunity to ensure the future of work will be even more inclusive to more people than ever before. Because the communication and products of work increasingly comprise images—photos, charts, maps, and the like—that are often not accessible, people […]
1636022699_hqdefault.jpg
12
02:13

Powered by AI: How we’ve advanced Smart Camera for new Portal video-calling devices

Smart Camera was built on Facebook AI’s groundbreaking Mask R-CNN framework for object instance segmentation and keypoint detection. We’ve made additional speed and precision improvements in the computer vision models that power Smart Camera. We’re now using Detectron2, the new, second-generation object detection platform created by Facebook AI, to train Smart Camera’s pose estimation models. […]
1635985695_maxresdefault.jpg
32
00:20

PyTorchVideo: A deep learning library for video understanding

The complexity of understanding video for computer vision is one of the biggest challenges in AI. PyTorchVideo aims to meet this demand by offering a unified repository of reproducible and efficient video, AI models, and datasets in PyTorch. Learn more on the blog: https://ai.facebook.com/blog/pytorchvideo-a-deep-learning-library-for-video-understanding/ YouTube Source for this Meta AI (Facebook AI) Video
1635962766_maxresdefault.jpg
2
41:41

Computer Vision for Remote AR with Flora Tasse – #390 (Video)

Today we conclude our CVPR coverage joined by Flora Tasse, Head of Computer Vision & AI Research at Streem. Flora, a keynote speaker at the AR/VR workshop at CVPR, walks us through some of the interesting use cases at the intersection of AI, computer vision, and augmented reality technology. In our conversation, we discuss how […]
1635959951_maxresdefault.jpg
78
00:14

Advancing the state of the art in computer vision with self-supervised Vision Transformers

Working with @Inria researchers, we’ve developed DINO, a method to train Vision Transformers (ViT) with no supervision. This model can discover and segment objects in an image or video with no supervision. #computervision Get the code: https://ai.facebook.com/blog/dino-paws-computer-vision-with-self-supervised-transformers-and-10x-more-efficient-training/ YouTube Source for this Meta AI (Facebook AI) Video
1635926440_maxresdefault.jpg
922
04:11

Building 3D deep learning models with PyTorch3D

In the same way that Torchvision and Detectron2 offer highly optimized libraries for 2D computer vision, PyTorch3D offers capabilities that support 3D data. Our open source library for 3D deep learning includes support for easy batching of heterogeneous meshes and point clouds, optimized implementations of common 3D operators such as Chamfer Loss and Graph Conv, […]