Related papers: An End-to-End Multi-Task Learning Model for Image-…

With massive explosion of social media such as Twitter and Instagram, people daily share billions of multimedia posts, containing images and text. Typically, text in these posts is short, informal and noisy, leading to ambiguities which can…

Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. Since many natural phenomenon exhibit sparse structures, enforcing sparsity on…

A systematic analysis of the cell behavior requires automated approaches for cell segmentation and tracking. While deep learning has been successfully applied for the task of cell segmentation, there are few approaches for simultaneous cell…

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and…

Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets. In this paper, we present a label efficient approach and look at jointly learning of multiple dense…

We present TableSeq, an image-only, end-to-end framework for joint table structure recognition, content recognition, and cell localization. The model formulates these tasks as a single sequence-generation problem: one decoder produces an…

Named Entity Recognition and Relation Extraction are two crucial and challenging subtasks in the field of Information Extraction. Despite the successes achieved by the traditional approaches, fundamental research questions remain open.…

Deep learning models have gained remarkable performance on a variety of image classification tasks. However, many models suffer from limited performance in clinical or medical settings when data are imbalanced. To address this challenge, we…

Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of…

Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task…

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…

Recent recommender system advancements have focused on developing sequence-based and graph-based approaches. Both approaches proved useful in modeling intricate relationships within behavioral data, leading to promising outcomes in…

Traditional recommender systems heavily rely on ID features, which often encounter challenges related to cold-start and generalization. Modeling pre-extracted content features can mitigate these issues, but is still a suboptimal solution…

We present a joint model for entity-level relation extraction from documents. In contrast to other approaches - which focus on local intra-sentence mention pairs and thus require annotations on mention level - our model operates on entity…

A significant portion of the data available today is found within tables. Therefore, it is necessary to use automated table extraction to obtain thorough results when data-mining. Today's popular state-of-the-art methods for table…

Tabular deep-learning methods require embedding numerical and categorical input features into high-dimensional spaces before processing them. Existing methods deal with this heterogeneous nature of tabular data by employing separate…

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…

Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. Then, based on our…

We propose an end-to-end driving model that integrates a multi-task UNet (MTUNet) architecture and control algorithms in a pipeline of data flow from a front camera through this model to driving decisions. It provides quantitative measures…

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…