Ghostboard pixel

Subscribe to Our Newsletter

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn't arrive within 3 minutes, check your spam folder.

Ok, Thanks
Data Phoenix Digest - ISSUE 53

Data Phoenix Digest - ISSUE 53

Charity AI webinar, review YOLOv6, GNN in TensorFlow, recent advances and applications of DL methods in materials science, a conversational paradigm for program synthesis, YOLOv7, ASE, PyMAF-X, CVPR 2022 papers, datasets, news, courses, and more.

Dmitry Spodarets profile image
by Dmitry Spodarets

The Data Phoenix Events team invites you all on September 28 to our "The A-Z of Data" charity webinar. The topic — deploying deep learning models with Kubernetes and Kubeflow.

In this talk, we'll learn about deploying Keras models. First, we'll see how to do it with TF-Serving and Kubernetes, and in the second part of the talk, we'll do it with KFServing and Kubeflow.

We resume our series of webinars as charity webinars to raise money for KOLO. This project was created by Ukrainian technology industry experts to help Ukraine fight the war against Russia by supplying high-tech equipment to the front lines.


By answering some questions related to your experience, skills, and toolset, you will help us determine the industry's state in 2022 and prepare the report.


Why Use k-fold Cross Validation?
Generalizing things is easy for us humans but challenging for ML models. This is where Cross-Validation comes into the picture. Learn how it works, from the basics to advanced concepts!

YOLOv6: Next-Generation Object Detection — Review and Comparison
What’s new with YOLO? Is YOLOv6 any good? And how does it work? Check out this review and comparison post about YOLOv6 model to find the answers. Spoiler: YOLOv6 is awesome!

Automatic Vehicle Number Plate Detection Using YOLOv5 and Extraction of Text Using OCR
In this comprehensive, practical article, you’ll learn the method of using a combination of YOLO5 and OCR to detect and extract vehicle number plates data quickly and efficiently.

Computer Vision and Deep Learning for Customer Service
This series is about CV and DL for Industrial and Big Business Applications. This lesson is the 2nd in the 5-lesson course. Make sure that you check out lesson 1 in advance.

Word2Vec: A Study of Embeddings in NLP
We slowly step into the territory of modern-day Natural Language Processing (NLP) with today’s spotlight: Word2Vec. This lesson is the 3rd in a 4-part series on NLP 101.


TF-GNN: Graph Neural Networks in TensorFlow
In this paper, Oleksandr Ferdulin et al. propose TensorFlow GNN, a scalable library for GNNs in TensorFlow designed to support rich heterogeneous graph data in today's information ecosystems.

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
In this paper, the authors explore the possibility of training extreme convolutions larger than 31x31 and test whether the performance gap can be eliminated by strategically enlarging convolutions.

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-time Object Detectors
YOLOv7 surpasses all known object detectors in both speed and accuracy. It outperforms both transformer-based and convolutional-based detectors, as well as many others.

Differentiable Signed Distance Function Rendering
Physically-based differentiable rendering emerges as a new technique for solving inverse problems. In this article, the authors show how to extend the commonly used sphere tracing algorithms.

R^2VOS: Robust Referring Video Object Segmentation via Relational Multimodal Cycle Consistency
In this paper, the authors emphasize that studying semantic consensus is necessary to improve the robustness of R-VOS. Check it out to learn the details!

Recent Advances and Applications of Deep Learning Methods in Materials Science
This article presents a high-level overview of DL methods followed by a discussion of recent developments of DL in atomistic simulation, materials imaging, spectral analysis, and NLP.

ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
In this paper, the authors present a large-scale data-driven framework for learning versatile and reusable skill embeddings for physically simulated characters. Check it out!

Symmetry-driven 3D Reconstruction from Concept Sketches
This paper presents an algorithm that can decomposes the sketch into locally-symmetric groups of strokes and identify pairs of strokes symmetric with respect to triplets of axis-aligned planes.

A Conversational Paradigm for Program Synthesis
The researchers propose a conversational program synthesis approach via large language models, accounting for searching over a vast program space and prior user intent specifications.

PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images
The authors propose a Pyramidal Mesh Alignment Feedback (PyMAF) loop in the regression network for well-aligned body mesh recovery and extend it to PyMAF-X for the recovery of expressive full-body models.


CVPR 2022 papers
Here you can find open access version of papers presented at CVPR 2022. Please note that the final published versions of the papers are available on IEEE Xplore.


Transformers United [Stanford Course]
Explore the details of how transformers work, find out about different kinds of transformers and how they're applied. A combination of instructor lectures, guest lectures, and classroom discussions.


The WorldStrat Dataset
Nearly 10,000 km² of free high-resolution and matched low-resolution satellite imagery of unique locations which ensure stratified representation of all types of land-use across the world.

Dmitry Spodarets profile image
by Dmitry Spodarets

Data Phoenix Digest

Subscribe to the weekly digest with a summary of the top research papers, articles, news, and our community events, to keep track of trends and grow in the Data & AI world!

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn’t arrive within 3 minutes, check your spam folder.

Ok, Thanks

Read More