Related papers: Visual Person Understanding through Multi-Task and…

This paper presents an approach to tackle the re-identification problem. This is a challenging problem due to the large variation of pose, illumination or camera view. More and more datasets are available to train machine learning models…

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these…

Person Re-Identification is still a challenging task in Computer Vision due to a variety of reasons. On the other side, Incremental Learning is still an issue since deep learning models tend to face the problem of over catastrophic…

The present work investigates whether different quantification mechanisms (set comparison, vague quantification, and proportional estimation) can be jointly learned from visual scenes by a multi-task computational model. The motivation is…

Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance. Like other computer vision tasks, this task has gained much with the…

Human behavior understanding is arguably one of the most important mid-level components in artificial intelligence. In order to efficiently make use of data, multi-task learning has been studied in diverse computer vision tasks including…

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…

Despite the recent progress in deep learning, most approaches still go for a silo-like solution, focusing on learning each task in isolation: training a separate neural network for each individual task. Many real-world problems, however,…

Body segmentation is an important step in many computer vision problems involving human images and one of the key components that affects the performance of all downstream tasks. Several prior works have approached this problem using a…

We propose a task we name Portrait Interpretation and construct a dataset named Portrait250K for it. Current researches on portraits such as human attribute recognition and person re-identification have achieved many successes, but…

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human…

It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and…

In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately.…

We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network. Learning multiple problems simultaneously involves minimizing a weighted sum of multiple…

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human…

We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize…

In recent years, multi-task learning has turned out to be of great success in various applications. Though single model training has promised great results throughout these years, it ignores valuable information that might help us estimate…

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…