Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction of data/task-driven features instead of handcrafted features. Although location information of regionof-interests (ROIs) gives good prior for object localiz...

In this paper, we introduce a supervised machine learning framework for the link prediction problem. The social network we conducted our empirical evaluation on originates from the restaurant review portal, yelp.com. The proposed framework not only uses the structure of the social network to predict non-existing edges in it, but also makes use of further graphs that were constructed based on im...

Temporal expressions are words or phrases that describe a point, duration or recurrence in time. Automatically annotating these expressions is a research goal of increasing interest. Recognising them can be achieved with supervised machine learning, but interpreting them accurately (normalisation) is a complex task requiring human knowledge. In this paper, we present TIMEN, a community-driven t...

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts explain approaches lag behind. Motivated by this observation, we introduce a novel visual probing framework explaining models leveraging tasks employed previously in natural language processing. The require knowledg...

This paper provides insights into the interpretation beyond simply combining self-supervised learning (SSL) with remote sensing (RS). Inspired by improved representation ability brought SSL in natural image understanding, we aim to explore and analyze compatibility of sensing. In particular, propose a pre-training framework for first time applying masked modeling (MIM) method RS research order ...

This study proposes an implementation of incremental neural network (INN) that was initially designed for affective computing tasks. INNs are a family machine learning algorithms combine prototype-based classifiers with networks. They achieve state-of-the-art performance less data than traditional approaches. In this research, we conduct in-depth review INN mechanisms and present research-grade...

The purpose of aluminum alloy metallographic image segmentation is to automatically recognize and segment the microstructures alloy, which an important topic in fields materials science research product assessment. In order achieve satisfactory results, we always need label each pixel image. This labeling work very costly terms time human effort. this paper, propose a semi-supervised learning f...

Clustering ensemble refers to combine a number of base clusterings for a particular data set into a consensus clustering solution. In this paper, we propose a novel self-supervised learning framework for clustering ensemble. Specifically, we treat the base clusterings as pseudo class labels and learn classifiers for each of them. By adding priors to the parameters of these classifiers, we captu...