Filters








11,321 Hits in 2.1 sec

Michael Solomon Alexander, der erste evangelische Bischof in Jerusalem. Ein Beitrag zur orientalischen Frage. J. F. A. de le Roi

A. J. Ramaker
1898 The American Journal of Theology  
Michael Solomon Alexander, der erste evangelische Bischof in Jerusalem. Ein Beitrag zur orientalischen Frage. Von Lic. J. F. A. de le Roi. (Giitersloh: C.  ...  Michael Solomon Alexander, der erste evangelische Bischof in Jerusalem. Ein Beitrag zur orientalischen Frage. Von Lic. J. F. A. de le Roi. (Giitersloh: C.  ...  Michael Solomon Alexander, der erste evangelische Bischof in Jerusalem. Ein Beitrag zur orientalischen Frage. Von Lic. J. F. A. de le Roi. (Giitersloh: C.  ... 
doi:10.1086/476945 fatcat:2edlaiiqujaydkr5f56mb2r3ve

Grid Loss: Detecting Occluded Faces [article]

Michael Opitz, Georg Waltner, Georg Poier, Horst Possegger, Horst Bischof
2016 arXiv   pre-print
Detection of partially occluded objects is a challenging computer vision problem. Standard Convolutional Neural Network (CNN) detectors fail if parts of the detection window are occluded, since not every sub-part of the window is discriminative on its own. To address this issue, we propose a novel loss layer for CNNs, named grid loss, which minimizes the error rate on sub-blocks of a convolution layer independently rather than over the whole feature map. This results in parts being more
more » ... native on their own, enabling the detector to recover if the detection window is partially occluded. By mapping our loss layer back to a regular fully connected layer, no additional computational cost is incurred at runtime compared to standard CNNs. We demonstrate our method for face detection on several public face detection benchmarks and show that our method outperforms regular CNNs, is suitable for realtime applications and achieves state-of-the-art performance.
arXiv:1609.00129v1 fatcat:atkusojtivejth6enpk6t4ckn4

Fast Approximated SIFT [chapter]

Michael Grabner, Helmut Grabner, Horst Bischof
2006 Lecture Notes in Computer Science  
We propose a considerably faster approximation of the well known SIFT method. The main idea is to use efficient data structures for both, the detector and the descriptor. The detection of interest regions is considerably speed-up by using an integral image for scale space computation. The descriptor which is based on orientation histograms, is accelerated by the use of an integral orientation histogram. We present an analysis of the computational costs comparing both parts of our approach to
more » ... conventional method. Extensive experiments show a speed-up by a factor of eight while the matching and repeatability performance is decreased only slightly.
doi:10.1007/11612032_92 fatcat:s6qqy7bbxnenxfc5k7iykmk7ji

Assessing the Quality of Web Content [article]

Elisabeth Lex and Inayat Khan and Horst Bischof and Michael Granitzer
2014 arXiv   pre-print
This paper describes our approach towards the ECML/PKDD Discovery Challenge 2010. The challenge consists of three tasks: (1) a Web genre and facet classification task for English hosts, (2) an English quality task, and (3) a multilingual quality task (German and French). In our approach, we create an ensemble of three classifiers to predict unseen Web hosts whereas each classifier is trained on a different feature set. Our final NDCG on the whole test set is 0:575 for Task 1, 0:852 for Task 2,
more » ... nd 0:81 (French) and 0:77 (German) for Task 3, which ranks second place in the ECML/PKDD Discovery Challenge 2010.
arXiv:1406.3188v1 fatcat:zp3k5u7p7basbaupohddvdf4pm

Deconstructivist Design within HCI [chapter]

Michael Heidt, Andreas Bischof, Paul Rosenthal
2014 Lecture Notes in Computer Science  
Every HCI artefact reproduces a specific stance towards its users. Influential within the academic sphere is the notion of a User-Centered-Design process. However, observing actual design practice renders the assumption of the centrality of users problematic. To this end, the text conducts an exploration of the relationship between discourse within the fields of HCI and architecture. A special focus are the formal expressions of deconstructivism within architecture and their potential counterparts within HCI design.
doi:10.1007/978-3-319-07668-3_12 fatcat:aeqe4gbjb5erjhbnh2ftfzn42a

Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly [article]

Michael Opitz, Georg Waltner, Horst Possegger, Horst Bischof
2018 arXiv   pre-print
Bischof Horst Bischof received his MSc and Ph.D. degree in computer science from the Vienna University of Technology in 1990 and 1993.  ...  Michael Horst Horst TABLE 16 16 Influence of end-to-end training on the CUB-200-2011 dataset.  ... 
arXiv:1801.04815v1 fatcat:z5ecpbthvzesfktszzafpgtfwm

SimAnMo—A parallelized runtime model generator

Michael Burger, Giang Nam Nguyen, Christian Bischof
2021 Concurrency and Computation  
In this article, we present the novel features of the recent version of SimAnMo, the Simulated Annealing Modeler. The tool creates models that correlate the size of one input parameter of an application to the corresponding runtime and thus SimAnMo allows predictions for larger input sizes. A focus lies on applications whose runtime grows exponentially in the input parameter size. Such programs are, for example, of high interest for cryptanalysis to analyze practical security of traditional and
more » ... post-quantum secure schemes. However, SimAnMo also generates reliable models for the widespread case of polynomial runtime behavior and also for the important case of factorial runtime increase. SimAnMo's model generation is based on a parallelized simulated annealing procedure and heuristically minimizes the costs of a model. Those may rely on different quality metrics. Insights into SimAnMo's software design and its usage are provided. We demonstrate the quality of SimAnMo's models for different algorithms from various application fields. We show that our approach also works well on ARM architectures.
doi:10.1002/cpe.6771 fatcat:an4urywvxfhejbphqmkhk6y2cm

Beyond Pairwise Shape Similarity Analysis [chapter]

Peter Kontschieder, Michael Donoser, Horst Bischof
2010 Lecture Notes in Computer Science  
This paper considers two major applications of shape matching algorithms: (a) query-by-example, i. e. retrieving the most similar shapes from a database and (b) finding clusters of shapes, each represented by a single prototype. Our approach goes beyond pairwise shape similarity analysis by considering the underlying structure of the shape manifold, which is estimated from the shape similarity scores between all the shapes within a database. We propose a modified mutual kNN graph as the
more » ... ng representation and demonstrate its performance for the task of shape retrieval. We further describe an efficient, unsupervised clustering method which uses the modified mutual kNN graph for initialization. Experimental evaluation proves the applicability of our method, e. g. by achieving the highest ever reported retrieval score of 93.40% on the well known MPEG-7 database. The authors gratefully acknowledge financial support from Research Studios Austria Project µSTRUCSCOP under project number 818651.
doi:10.1007/978-3-642-12297-2_63 fatcat:rsr7ngfmnfefhmwgzcbuxx3aeq

Highly Consistent Sequential Segmentation [chapter]

Michael Donoser, Martin Urschler, Hayko Riemenschneider, Horst Bischof
2011 Lecture Notes in Computer Science  
This paper deals with segmentation of image sequences in an unsupervised manner with the goal of getting highly consistent segmentation results from frame-to-frame. We first introduce a segmentation method that uses results of the previous frame as initialization and significantly improves consistency in comparison to a single frame based approach. We also find correspondences between the segmented regions from one frame to the next to further increase consistency. This matching step is based
more » ... a modified version of an efficient partial shape matching method which allows identification of similar parts of regions despite topology changes like merges and splits. We use the identified matched parts to define a partial matching cost which is then used as input to pairwise graph matching. Experiments demonstrate that we can achieve highly consistent segmentations for diverse image sequences, even allowing to track manually initialized moving and static objects.
doi:10.1007/978-3-642-21227-7_5 fatcat:t4hlj3kjuzgtphmhft6252geou

Surgical Intervention for Pulmonary Metastases

Joachim Pfannschmidt, Gerlinde Egerer, Marc Bischof, Michael Thomas, Hendrik Dienemann
2012 Deutsches Ärzteblatt International  
►Cite this as: Pfannschmidt J, Egerer G, Bischof M, Thomas M, Dienemann H: Surgical intervention for pulmonary metastases.  ...  shows two solid foci on the right (segments 5 and 6) and a single metastasis with central necrosis in the left lower lobe (segment 6) Figure 2 : 2 Intraoperative Professor Pfannschmidt and Professor Bischof  ... 
doi:10.3238/arztebl.2012.0645 pmid:23094000 pmcid:PMC3476611 fatcat:svv5apxxrzhzrckmgaw7xkbzaq

FAST3D: Flow-Aware Self-Training for 3D Object Detectors [article]

Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger, Horst Bischof
2021 arXiv   pre-print
In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g., geographic location, sensor setup, weather condition). State-of-the-art self-training approaches, however, mostly ignore the temporal nature of autonomous driving data. To address this issue, we propose a flow-aware self-training method that enables unsupervised
more » ... omain adaptation for 3D object detectors on continuous LiDAR point clouds. In order to get reliable pseudo-labels, we leverage scene flow to propagate detections through time. In particular, we introduce a flow-based multi-target tracker, that exploits flow consistency to filter and refine resulting tracks. The emerged precise pseudo-labels then serve as a basis for model re-training. Starting with a pre-trained KITTI model, we conduct experiments on the challenging Waymo Open Dataset to demonstrate the effectiveness of our approach. Without any prior target domain knowledge, our results show a significant improvement over the state-of-the-art.
arXiv:2110.09355v1 fatcat:26y4ehaejvg4lhwvij7fpqgdda

Learning Features for Tracking

Michael Grabner, Helmut Grabner, Horst Bischof
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
We treat tracking as a matching problem of detected keypoints between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to incorporate background information. Contrary to existing approaches, we are able to start tracking of the object from scratch requiring no off-line training phase before tracking. The tracker is initialized by a region of interest in the first frame. Afterwards an on-line boosting technique is used for learning
more » ... ons of detected keypoints lying within the region of interest. New frames provide new samples for updating the classifiers which increases their stability. A simple mechanism incorporates temporal information for selecting stable features. In order to ensure correct updates a verification step based on estimating homographies using RANSAC is performed. The approach can be used for real-time applications since on-line updating and evaluating classifiers can be done efficiently.
doi:10.1109/cvpr.2007.382995 dblp:conf/cvpr/GrabnerGB07 fatcat:apq6paydbbfl5manngsbjdaufu

S-adenosylhomocysteine hydrolase regulates anterior patterning in Dugesia japonica [article]

Kristina Reinmets, Johanna Bischof, Emily Taketa, Michael Levin, Stephen M M Fuchs
2020 bioRxiv   pre-print
Biological methylation requires S-adenosylmethionine (SAM) and participates in a range of processes from modulation of gene expression via histone modifications to neurotransmitter synthesis. An important factor in all methylation reactions is the concentration ratio of SAM to methylation byproduct S-adenosylhomocysteine (SAH). SAH hydrolase, also known as adenosylhomocysteinase, depletes SAH and thereby facilitates metabolite recycling and maintains the methylation permissive SAM/SAH ratio.
more » ... le the importance of SAH hydrolase in sustaining methylation is obvious on the cellular level, the function of this metabolic process on the organismal scale is not clear. Results: We used planarian Dugesia japonica to investigate the role SAH hydrolase in physiological homeostasis on the body-wide scale. Remarkably, pharmacological inhibition of the SAH hydrolase results in regression of anterior tissues and is accompanied by extensive apoptosis throughout the planarian body. Moreover, exposure to the SAHH inhibitor AdOx leads to changes in brain morphology and spatial shift in the expression of Wnt-modulator Notum. Strikingly, planarians are able to overcome these destructive patterning defects through regeneration of the anterior tissues and adaptation to the used inhibitor. Transcriptome analysis indicates that resistance to the SAHH inhibitor is at least partly mediated by changes in folate cycle and lipid metabolism. Conclusions: SAH hydrolase plays a critical role in planarian homeostasis and anterior patterning potentially through modulation of Wnt signaling. Moreover, planarian adaptation to the SAHH inhibitor via metabolic reprogramming suggests potential targets for addressing methylation-related human conditions.
doi:10.1101/2020.01.22.916072 fatcat:owkearzlhjfqdm5mizy5sx5or4

Diffusion Processes for Retrieval Revisited

Michael Donoser, Horst Bischof
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper we revisit diffusion processes on affinity graphs for capturing the intrinsic manifold structure defined by pairwise affinity matrices. Such diffusion processes have already proved the ability to significantly improve subsequent applications like retrieval. We give a thorough overview of the state-of-the-art in this field and discuss obvious similarities and differences. Based on our observations, we are then able to derive a generic framework for diffusion processes in the scope
more » ... f retrieval applications, where the related work represents specific instances of our generic formulation. We evaluate our framework on several retrieval tasks and are able to derive algorithms that e. g. achieve a 100% bullseye score on the popular MPEG7 shape retrieval data set.
doi:10.1109/cvpr.2013.174 dblp:conf/cvpr/DonoserB13 fatcat:y4rw2gsjefbstgmfo3icytvwmy

Efficient Partial Shape Matching of Outer Contours [chapter]

Michael Donoser, Hayko Riemenschneider, Horst Bischof
2010 Lecture Notes in Computer Science  
This paper introduces a novel efficient partial shape matching method named IS-Match. We use sampled points from the silhouette as a shape representation. The sampled points can be ordered which in turn allows to formulate the matching step as an order-preserving assignment problem. We propose an angle descriptor between shape chords combining the advantages of global and local shape description. An efficient integral image based implementation of the matching step is introduced which allows
more » ... ecting partial matches an order of magnitude faster than comparable methods. We further show how the proposed algorithm is used to calculate a global optimal Pareto frontier to define a partial similarity measure between shapes. Shape retrieval experiments on standard shape databases like MPEG-7 prove that state-of-the-art results are achieved at reduced computational costs.
doi:10.1007/978-3-642-12307-8_26 fatcat:mrd324tginfdndwg5xwszkj5cu
« Previous Showing results 1 — 15 out of 11,321 results