Related papers: A Methodology to Evaluate Strategies Predicting Ra…
Link prediction, a foundational task in complex network analysis, has extensive applications in critical scenarios such as social recommendation, drug target discovery, and knowledge graph completion. However, existing evaluations of…
Stance detection concerns the classification of a writer's viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with respect to a claim vs. an (implicit) topic. Moreover, task…
Exploring search spaces is one of the most unpredictable challenges that has attracted the interest of researchers for decades. One way to handle unpredictability is to characterise the search spaces and take actions accordingly. A…
The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different…
Many latent (factorized) models have been proposed for recommendation tasks like collaborative filtering and for ranking tasks like document or image retrieval and annotation. Common to all those methods is that during inference the items…
Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…
The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data…
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…
This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence…
There are so many models in the literature that it is difficult for practitioners to decide which combinations are likely to be effective for a new task. This paper attempts to address this question by capturing relationships among…
If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown…
Recently, action proposal methods have played an important role in action recognition tasks, as they reduce the search space dramatically. Most unsupervised action proposal methods tend to generate hundreds of action proposals which include…
While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an…
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance…
Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate…
Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of…
The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…
Background subtraction (BGS) is a common choice for performing motion detection in video. Hundreds of BGS algorithms are released every year, but combining them to detect motion remains largely unexplored. We found that combination…
The data distribution commonly evolves over time leading to problems such as concept drift that often decrease classifier performance. Current techniques are not adequate for this problem because they either require detailed knowledge of…