Image for post
Image for post

3D face geometry needs to be recovered from 2D images in many real-world applications, including face recognition, face landmark detection, 3D emoticon animation, etc. However, this task remains challenging especially under the large pose, when much of the information about the face is unknowable.

Jiang and Wu from Jiangnan University (China) and Kittler from University of Surrey (UK) suggest a novel 3D face reconstruction algorithm, which significantly improves the accuracy of reconstruction even under extreme pose.

But let’s first shortly review the previous work on 3D face models and 3D face reconstruction.

Related Work

The research mentions four publicly available 3D deformation…

Image for post
Image for post

Robotics, augmented reality, autonomous driving — all these scenarios rely on recognizing 3D properties of objects from 2D images. This puts 3D object recognition as one of the central problems in computer vision.

Remarkable progress has been achieved in this field after the introduction of several databases that provide 3D annotations to 2D objects (e.g., IKEA, Pascal3D+). However, these datasets are limited in scale and include only about a dozen object categories.

This is not even close to the large-scale image datasets such as ImageNet or Microsoft COCO, while these are these huge datasets that stay behind the significant progress in image classification task in recent years. …

Image for post
Image for post

Human pose estimation is another fundamental problem in computer vision. Computer’s ability to recognize and understand humans in images and videos is crucial for multiple tasks including autonomous driving, action recognition, human-computer interaction, augmented reality and robotics vision.

In recent years, significant progress has been achieved in 2D human pose estimation. The crucial factor behind this success is the availability of large-scale annotated human pose datasets that allow training networks for 2D human pose estimation. …

Image for post
Image for post
Samples from the Need for Speed (NfS) dataset

Object tracking in the wild is far from being solved. Existing object trackers do quite a good job on the established datasets (e.g., VOT, OTB), but these datasets are relatively small and do not fully represent the challenges of real-life tracking tasks. Deep learning is at the core of the most state-of-the-art trackers today. However, a dedicated large-scale dataset to train deep trackers is still lacking.

In this article, we discuss three recently introduced datasets for object tracking. They differ in scale, annotations and other characteristics but all of them can contribute something to solving object tracking problem: TrackingNet is a first large-scale dataset for object tracking in the wild, MOT17 is a benchmark for multiple object tracking, and Need for Speed is the first higher frame rate video dataset. …

Image for post
Image for post

Action recognition is vital for many real-life applications, including video surveillance, healthcare, and human-computer interaction. What do we need to do to classify video clips based on the actions being performed in these videos?

Original article: New Datasets for Action Recognition

We need to identify different actions from video clips where the action may or may not be performed throughout the entire duration of the video. This looks similar to the image classification problem, but in this case, the task is extended to multiple frames with further aggregation of the predictions from each frame. And we know that after the introduction of ImageNet dataset, deep learning algorithms are doing a pretty good job in image classification. …

Image for post
Image for post

Face recognition is a common task in deep learning and convolutional neural networks (CNNs) are doing a pretty good job here. I guess Facebook usually performs great at recognizing you and your friends in the uploaded images.

Original article: New Datasets for Disguised Face Recognition

But is this really a solved problem? What if the picture is obfuscated? What if the person impersonates somebody else? Can heavy makeup trick the neural network? How easy is it to recognize a person who wears glasses?

In fact, disguised face recognition is still quite a challenging task for neural networks and primarily due to the lack of corresponding datasets. In this article, we are going to feature several face datasets presented recently. Each of them reflects different aspects of face obfuscation but their goal is the same — to help developers create better models for disguised face recognition. …

Being a parent for two amazing boys of 2.5 years and 7 months, I suddenly realized that being childfree can be a great choice for many people. Not for me, though. I am happy with my choice to become a parent, and we are even thinking with my husband about giving birth to a girl or two one day. But really — parenting is not for everyone.

You have to make so many sacrifices and the benefits are so vague. I believe that people are different. And they all have different needs and different possibilities. …


Kate Koidan

Research Analyst & Editor @ TOPBOTS | Data Science Writer @ Vertabelo Academy. LinkedIn:

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store