Laura Antanas | KU Leuven (original) (raw)

Papers by Laura Antanas

Springer eBooks, 2011

Biological processes where every gene and protein participates is an essential knowledge for desi... more Biological processes where every gene and protein participates is an essential knowledge for designing disease treatments. Nowadays, these annotations are still unknown for many genes and proteins. Since making annotations from in-vivo experiments is costly, computational predictors are needed for different kinds of annotation such as metabolic pathway, interaction network, protein family, tissue, disease and so on. Biological data has an intrinsic relational structure, including genes and proteins, which can be grouped by many criteria. This hinders the possibility of finding good hypotheses when attribute-value representation is used. Hence, we propose the generic Modular Multi-Relational Framework (MMRF) to predict different kinds of gene and protein annotation using Relational Data Mining (RDM). The specific MMRF application to annotate human protein with diseases verifies that group knowledge (mainly protein-protein interaction pairs) improves the prediction, particularly doubling the area under the precision-recall curve.

of the MA Thesis: Realtime road user detection with single pass deep learningstatus: accepte

All in-text references underlined in blue are linked to publications on ResearchGate, letting you... more All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.

Understanding images in terms of hierarchical and logical structures is crucial for many semantic... more Understanding images in terms of hierarchical and logical structures is crucial for many semantic tasks, including image retrieval, scene understanding and robot vision. This paper combines compositional hierarchies, qualitative spatial relations, relational instance-based learning and robust feature extraction in one framework. For each layer in the hierarchy, substructures in the images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures, by making use of qualitative spatial relations. The approach is applied to street view images. We employ a four-layer hierarchy in which subsequently corners, windows and doors, and individual houses are detected.

2013 IEEE Workshop on Applications of Computer Vision (WACV), 2013

Real-world scenes involve many objects that interact with each other in complex semantic patterns... more Real-world scenes involve many objects that interact with each other in complex semantic patterns. For example, a bar scene can be naturally described as having a variable number of chairs of similar size, close to each other and aligned horizontally. This high-level interpretation of a scene relies on semantically meaningful entities and is most generally described using relational representations or (hyper-) graphs. Popular in early work on syntactic and structural pattern recognition, relational representations are rarely used in computer vision due to their pure symbolic nature. Yet, today recent successes in combining them with statistical learning principles motivates us to reinvestigate their use. In this paper we show that relational techniques can also improve scene classification. More specifically, we employ a new relational language for learning with kernels, called kLog. With this language we define higher-order spatial relations among semantic objects. When applied to a particular image, they characterize a particular object arrangement and provide discriminative cues for the scene category. The kernel allows us to tractably learn from such complex features. Thus, our contribution is a principled and interpretable approach to learn from symbolic relations how to classify scenes in a statistical framework. We obtain results comparable to state-ofthe-art methods on 15 Scenes and a subset of the MIT indoor dataset. Figure 1: Sample indoor scenes belonging to classes pool inside, restaurant, bar and office (from left to right).

Lecture Notes in Computer Science, 2012

While relational representations have been popular in early work on syntactic and structural patt... more While relational representations have been popular in early work on syntactic and structural pattern recognition, they are rarely used in contemporary approaches to computer vision due to their pure symbolic nature. The recent progress and successes in combining statistical learning principles with relational representations motivates us to reinvestigate the use of such representations. More specifically, we show that statistical relational learning can be successfully used for hierarchical image understanding. We employ kLog, a new logical and relational language for learning with kernels to detect objects at different levels in the hierarchy. The key advantage of kLog is that both appearance features and rich, contextual dependencies between parts in a scene can be integrated in a principled and interpretable way to obtain a qualitative representation of the problem. At each layer, qualitative spatial structures of parts in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and successfully detect corners, windows, doors, and individual houses.

Lecture Notes in Computer Science, 2013

Opening doors is an essential task that a robot should perform. In this paper, we propose a logic... more Opening doors is an essential task that a robot should perform. In this paper, we propose a logical approach to predict the action of opening doors, together with the action point where the action should be performed. The input of our system is a pair of bounding boxes of the door and door handle, together with background knowledge in the form of logical rules. Learning and inference are performed with the probabilistic programming language ProbLog. We evaluate our approach on a doors dataset and we obtain encouraging results. Additionally, a comparison to a propositional decision tree shows the benefits of using a probabilistic programming language such as ProbLog.

Neurocomputing, 2014

Understanding images in terms of logical and hierarchical structures is crucial for many semantic... more Understanding images in terms of logical and hierarchical structures is crucial for many semantic tasks, including image retrieval, scene understanding and robotic vision. This paper combines robust feature extraction, qualitative spatial relations, relational instance-based learning and compositional hierarchies in one framework. For each layer in the hierarchy, qualitative spatial structures in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and subsequently detect corners, windows, doors, and individual houses.

Medical Image Analysis, 2013

Histological image analysis plays a key role in understanding the effects of disease and treatmen... more Histological image analysis plays a key role in understanding the effects of disease and treatment responses at the cellular level. However, evaluating histology images by hand is time-consuming and subjective. While semi-automatic and automatic approaches for image segmentation give acceptable results in some branches of histological image analysis, until now this has not been the case when applied to skeletal muscle histology images. We introduce Charisma, a new top-down cell segmentation framework for histology images which combines image processing techniques, a supervised trained classifier and a novel robust clump splitting algorithm. We evaluate our framework on real-world data from intensive care unit patients. Considering both segmentation and cell property distributions, the results obtained by our method correspond well to the ground truth, outperforming other examined methods.

Being able to understand complex dynamic scenes of real-world activities from low-level sen-sor d... more Being able to understand complex dynamic scenes of real-world activities from low-level sen-sor data is of central importance for truly intelli-gent systems. The main difficulty lies in the fact that complex scenes are best described in high-level, logical formalisms, whereas sensor data – for example images derived from a video camera – usually consists of many low-level, numerical and presumably noisy feature values. In this work, we consider the problem of learning high-level, logi-cal descriptions of dynamic scenes based on only the input video stream. As an example, consider a surveillance cam-era in a metro station. Whereas the video data will consist of many noisy images, a high-level

Robot grasping is a critical and difficult problem in robotics. The problem of simply finding a s... more Robot grasping is a critical and difficult problem in robotics. The problem of simply finding a stable grasp is difficult enough, but to perform a useful grasp, we must also consider other aspects of the task: the object, its properties, and any task-related constraints. The choice of grasping

State representation for intelligent agents is a continuous challenge as the need for abstraction... more State representation for intelligent agents is a continuous challenge as the need for abstraction is unavoidable in large state spaces. Predictive representations offer one way to obtain state abstraction by replacing a state with a set of predictions about future interactions

Abstract. Augmenting vision systems with high-level knowledge and reasoning can improve lower-lev... more Abstract. Augmenting vision systems with high-level knowledge and reasoning can improve lower-level vision processes, such as object detection, with richer and more structured information. In this paper we tackle the problem of delimiting conceptual elements of street views based on spatial relations between lowerlevel components, e.g. the element ‘house ’ is composed of windows and a door in a spatial arrangement. We use structured data: each concept can be seen as a graph representing spatial relations between components, e.g. in terms of right, up, close. We employ distances between logical interpretations to match parts of images with known examples and describe experimental results. 1

Abstract—While grasps must satisfy the grasping stability cri-teria, good grasps depend on the sp... more Abstract—While grasps must satisfy the grasping stability cri-teria, good grasps depend on the specific manipulation scenario: the object, its properties and functionalities, as well as the task and grasp constraints. In this paper, we consider such infor-mation for robot grasping by leveraging manifolds and symbolic object parts. Specifically, we introduce a new probabilistic logic module to first semantically reason about pre-grasp configurations with respect to the intended tasks. Further, a mapping is learned from part-related visual features to good grasping points. The probabilistic logic module makes use of object-task affordances and object/task ontologies to encode rules that generalize over similar object parts and object/task categories. The use of probabilistic logic for task-dependent grasping contrasts with current approaches that usually learn direct mappings from visual perceptions to task-dependent grasping points. We show the benefits of the full probabilistic logi...

ArXiv, 2014

While grasps must satisfy the grasping stability criteria, good grasps depend on the specific man... more While grasps must satisfy the grasping stability criteria, good grasps depend on the specific manipulation scenario: the object, its properties and functionalities, as well as the task and grasp constraints. In this paper, we consider such information for robot grasping by leveraging manifolds and symbolic object parts. Specifically, we introduce a new probabilistic logic module to first semantically reason about pre-grasp configurations with respect to the intended tasks. Further, a mapping is learned from part-related visual features to good grasping points. The probabilistic logic module makes use of object-task affordances and object/task ontologies to encode rules that generalize over similar object parts and object/task categories. The use of probabilistic logic for task-dependent grasping contrasts with current approaches that usually learn direct mappings from visual perceptions to task-dependent grasping points. We show the benefits of the full probabilistic logic pipeline ...