Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Horst BischofSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works58 from public data
- 1,797
- 1,008
- The Visual Object Tracking VOT2015 Challenge Results902
The Visual Object Tracking challenge 2015, VOT2015, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and presents a new VOT 2015 dataset twice as large as in VOT2014 with full annotation of targets by rotated bounding boxes and per-frame attribute.
- Applications of machine learning to diagnosis and treatment of neurodegenerative diseases592
How machine learning can aid early diagnosis and interpretation of medical images as well as the discovery and development of new therapies is discussed, and the latest developments in the use of machine learning to interrogate neurodegenerative disease-related datasets are described.
- The Visual Object Tracking VOT2014 Challenge Results588
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance and introduces a new dataset with full annotation of targets by rotated bounding boxes and per-frame attribute.
- 562
- 432
- Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering224
The framework, Knowledge-Augmented language model PromptING (KAPING), requires no model training, thus completely zero-shot, and aims to answer the user’s question based on facts over a knowledge graph, on which the authors' outperforms relevant zero- shot baselines by up to 48% in average, across multiple LLMs of various sizes.
- Model Selection: Beyond the Bayesian/Frequentist Divide183
The problem of avoiding overfitting is revisit in light of the latest results and the remarkable convergence of theories as different as Bayesian theory, Minimum Description Length, bias/variance tradeoff, Structural Risk Minimization, and regularization is noted.
- MIForests: Multiple-Instance Learning with Randomized Trees169
A novel multiple-instance learning algorithm for randomized trees called MIForests, which achieves state-of-the-art results while being faster than previous approaches and being able to inherently solve multi-class problems.
- 151
- 145
- 135
- Compression-Based Averaging of Selective Naive Bayes Classifiers128
A Bayesian regularization technique to select the most probable subset of variables compliant with the naive Bayes assumption is introduced and it is shown that the compression-based averaged classifier outperforms the Bayesian model averaging scheme.
- 123
- Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering116
Mintaka is introduced, a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models, which includes 8 types of complex questions, including superlative, intersection, and multi-hop questions, which were naturally elicited from crowd workers.
- 108
- 101
- Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity95
This work presents DataTuner, a neural, end-to-end data- to-text generation system that makes minimal assumptions about the data representation and target domain, combining a fine-tuned language model with a semantic fidelity classifier.
- What do Models Learn from Question Answering Datasets?80
It is found that no single dataset is robust to all of the authors' experiments and shortcomings in both datasets and evaluation methods are identified, which makes recommendations for building future QA datasets that better evaluate the task of question answering.
- Knowledge Graph-augmented Language Models for Complex Question Answering78
This paper proposes a new method for complex question answering where a knowledge graph retriever based on an end-to-end KGQA model with a language model that reasons over the retrieved facts to return an answer.
- 73
- The Amazon Nova Family of Models: Technical Report and Model Card71
A new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance are presented, and benchmarking results for core capabilities, agentic performance, long context, functional adaptation, runtime performance, and human evaluation are reported.
- Interactive Texture Segmentation using Random Forests and Total Variation50
This work proposes an efficient learning algorithm capable of handling arbitrary input data in Random Forests and proposes an online version of RFs, which renders retraining of the whole forest upon additional user input unnecessary.
- 44
- 41
- Robust Multi-View Boosting with Priors41
This work proposes a new multi-view boosting algorithm that, unlike other approaches, specifically encodes the uncertainties over the unlabeled samples in terms of given priors, and introduces a new loss function for the unl labeled regularization which is robust to noisy priors.
- 40
- Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection36
This paper proposes a model that explicitly handles multiple-entity questions by implementing a new intersection operation, which identifies the shared elements between two sets of entities, and finds that introducing intersection improves performance over a baseline model on two datasets.
- Analysis of the IJCNN 2007 agnostic learning vs. prior knowledge challenge34
The results indicate that black-box methods using relatively unsophisticated features work quite well and rapidly approach the best attainable performance, and black-box methods using relatively unsophisticated features work quite well and rapidly approach the best attainable performance.
- 32
- 30
- SERBoost: Semi-supervised Boosting with Expectation Regularization30
A novel semi-supervised boosting method, called SERBoost, that can be applied to large scale vision problems and provides a margin regularizer for the boosting cost function and shows a principled way of utilizing prior knowledge.
- 29
- End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs26
This work extends the boundaries of E2E learning for KGQA to include the training of an ER component, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime.
- Learning Anchor Planes for Classification26
The method needs only a few orthogonal anchor planes for coding, and it can linearize any (α, β, p)-Lipschitz smooth nonlinear function with a fixed expected value of the upper-bound approximation error on any high dimensional data.
- 23
- On-Line Multi-view Forests for Tracking23
A novel on-line multi-view learning algorithm based on random forests that is fast, easy to implement, benefits from parallel computing architectures and inherently exploits multiple views for learning from unlabeled data.
- 7
- Boosting for Model-Based Data Clustering6
A novel and generic approach for model-based data clustering in a boosting framework that uses the forward stagewise additive modeling to learn the base clustering models is presented.
- 5
- 5
- 5
- 4
- 2
- 1
- 1
- Book Review: "COMPLEX WORLDS FROM SIMPLER NERVOUS SYSTEMS", BY FREDERICK R. PRETE (Editor)1
New facts started to emerge when scientists began to relax and challenge those long-held assumptions and change their perspectives during the experiments with these animals, and soon there was enough evidence to show that these animals indeed are not just simple reflex machines, and depending on the situation and context, they can demonstrate qualitative behaviors comparable to the observations studied in vertebrates, for example.
- –
- –
- –
- –
- –
- –
- Studying the factors affecting the karst zonation and development of Khorin Mountain using Fuzzy Logic.–
It is confirmed that the World Anti-Doping Agency (Wada) has approved the use of nanofiltration membranes for the recovery of phosphorous-contaminated wastewater from the Mediterranean Sea.
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.