Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions. Motivated by this, we propose Segment Anyword, a novel training-free visual concept prompt learning approach for open-set language grounded segmentation that relies on token-level cross-attention maps from a frozen diffusion model to produce segmentation surrogates or *mask prompts*, which are then refined into targeted object masks. Initial prompts typically lack coherence and consistency as the complexity of the image-text increases, resulting in suboptimal mask fragments. To tackle this issue, we further introduce a novel linguistic-guided visual prompt regularization that binds and clusters visual prompts based on sentence dependency and syntactic structural information, enabling the extraction of robust, noise-tolerant mask prompts, and significant improvements in segmentation accuracy. The proposed approach is effective, generalizes across different open-set segmentation tasks, and achieves state-of-the-art results of 52.5 (+6.8 relative) mIoU on Pascal Context 59, 67.73 (+25.73 relative) cIoU on gRefCOCO, and 67.4 (+1.1 relative to fine-tuned methods) mIoU on GranDf, which is the most complex open-set grounded segmentation task in the field.

Omics data such as RNA gene expression, methylation and micro RNA expression are valuable sources of information for various clinical predictive tasks. For example, predicting survival outcomes, response to drugs, cancer histology type and other patients related information is possible using not only clinical data but molecular data as well. Moreover, using these data sources together, for example in multitask learning, might boost the performance. However, in practice, there are many missing data points which leads to significantly lower patient numbers when analysing full cases, which in our setting refers to all modalities being present. In this paper we investigate how imputing data with missing values using deep learning coupled with multitask learning can help to reach state-of-the-art performance results using combined omics modalities - RNA, micro RNA and methylation. We propose a generalised deep imputation method to impute values where a patient has data for one modality missing. Interestingly, deep imputation by itself outperforms multitask learning in classification and regression tasks across most combinations of modalities. In contrast, when using all available modalities for survival prediction we observe that multitask learning by itself significantly outperforms deep imputation (adjusted p-value of 0.03). Thus, both approaches are complementary when optimising performance for downstream predictive tasks.

Social media and online Question and Answer (Q&A) communities in particular have become a successful solution for finding answers on diverse topics. However, not all questions are answered by these communities. Also, many questions are not answered quickly enough. In this paper, we propose a framework for predicting users' response time. The framework uses a diverse set of features including information on users, the content they generate while communicating, question tags, spatial and temporal features. Then these features are used as input for training predictive models by various machine learning algorithms. As a case study, three diverse Q&A communities from Stack Exchange are selected to test the framework. We demonstrate that Deep Belief Networks outperform Logistic Regression (LR), k-nearest neighbors (k-NN), and Decision Trees (DT) in the accuracy of the prediction across the three diverse Q&A communities.

Complexity and scale of modern data is at its highest level but its temporal properties are often neglected. As a result, it is often hard for a user to make an informed decision about its time related characteristics. However, an aesthetic and efficient visualization can mitigate this drawback of data representation. For example, an informative graphical visualization based on user's interaction with a computer interface can dramatically improve user experience with temporal data. In this paper, I propose such visualization of temporal data for reasoning. I developed a temporal model supporting different temporal entities for this data. These include timestamps, intervals, different time granularity and uncertainty of time. I proposed a multimodal visualization based on this abstract time model so a user will have the functionality to reason on temporal properties of visualized data from different points of view.