no code implementations • 1 Jun 2023 • Leonard Hackel, Kai Norman Clasen, Mahdyar Ravanbakhsh, Begüm Demir
Visual question answering (VQA) methods in remote sensing (RS) aim to answer natural language questions with respect to an RS image.
no code implementations • 10 Oct 2022 • Tim Siebert, Kai Norman Clasen, Mahdyar Ravanbakhsh, Begüm Demir
To make the intrinsic information of each RS image easily accessible, visual question answering (VQA) has been introduced in RS.
no code implementations • 5 Oct 2022 • Tom-Lukas Breitkopf, Leonard W. Hackel, Mahdyar Ravanbakhsh, Anne-Karin Cooke, Sandra Willkommen, Stefan Broda, Begüm Demir
In this study, we introduce two DL-based models: i) improved U-Net architecture; and ii) Visual Transformer-based encoder-decoder in the framework of tile drainage pipe detection.
no code implementations • 28 Jul 2022 • Tom Burgert, Mahdyar Ravanbakhsh, Begüm Demir
In this paper, we investigate three different noise robust CV SLC methods and adapt them to be robust for multi-label noise scenarios in RS.
no code implementations • 19 Apr 2022 • Georgii Mikriukov, Mahdyar Ravanbakhsh, Begüm Demir
To address this problem, in this paper we introduce a novel unsupervised cross-modal contrastive hashing (DUCH) method for text-image retrieval in RS.
1 code implementation • 26 Feb 2022 • Georgii Mikriukov, Mahdyar Ravanbakhsh, Begüm Demir
The proposed CHNR includes two training phases: i) meta-learning phase that uses a small portion of clean (i. e., reliable) data to train the noise detection module in an adversarial fashion; and ii) the main training phase for which the trained noise detection module is used to identify noisy correspondences while the hashing module is trained on the noisy multi-modal training set.
no code implementations • 20 Jan 2022 • Georgii Mikriukov, Mahdyar Ravanbakhsh, Begüm Demir
To address this problem, in this paper we introduce a novel deep unsupervised cross-modal contrastive hashing (DUCH) method for RS text-image retrieval.
1 code implementation • 12 May 2021 • Ahmet Kerem Aksoy, Mahdyar Ravanbakhsh, Tristan Kreuziger, Begum Demir
The proposed CCML identifies, ranks and corrects training images with noisy multi-labels through four main modules: 1) discrepancy module; 2) group lasso module; 3) flipping module; and 4) swap module.
1 code implementation • 8 May 2021 • Gencer Sumbul, Mahdyar Ravanbakhsh, Begüm Demir
The proposed method selects a small set of the most representative and informative triplets based on two main steps.
1 code implementation • 19 Dec 2020 • Ahmet Kerem Aksoy, Mahdyar Ravanbakhsh, Begüm Demir
To address this problem, the publicly available thematic products, which can include noisy labels, can be used to annotate RS images with zero-labeling cost.
no code implementations • 9 Apr 2019 • Mahdyar Ravanbakhsh
Novelty detection is one of the fundamental requirements of a good classification or identification system since sometimes the test data contains observations that were not known at the training time.
no code implementations • 8 Jun 2018 • Mahdyar Ravanbakhsh, Mohamad Baydoun, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Carlo S. Regazzoni
In this work, a hierarchical model is introduced by means of a cross-modal Generative Adversarial Networks (GANs) processing high dimensional visual data.
no code implementations • 7 Jun 2018 • Mahdyar Ravanbakhsh, Mohamad Baydoun, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Carlo S. Regazzoni
This paper presents a novel approach for learning self-awareness models for autonomous vehicles.
no code implementations • 17 Mar 2018 • Mohamad Baydoun, Mahdyar Ravanbakhsh, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Andrea Cavallaro, Carlo S. Regazzoni
This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations.
no code implementations • 31 Aug 2017 • Mahdyar Ravanbakhsh, Moin Nabi, Enver Sangineto, Lucio Marcenaro, Carlo Regazzoni, Nicu Sebe
In this paper we address the abnormality detection problem in crowded scenes.
Ranked #4 on Abnormal Event Detection In Video on UCSD Ped2
no code implementations • 23 Jun 2017 • Mahdyar Ravanbakhsh, Enver Sangineto, Moin Nabi, Nicu Sebe
Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios.
no code implementations • 21 Nov 2016 • Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi, Lucio Marcenaro, Carlo Regazzoni
We use binary encoding of CNN features to overcome the difficulty of the clustering on the high-dimensional CNN feature space.
no code implementations • 2 Oct 2016 • Mahdyar Ravanbakhsh, Moin Nabi, Hossein Mousavi, Enver Sangineto, Nicu Sebe
In this paper, we show that keeping track of the changes in the CNN feature across time can facilitate capturing the local abnormality.
no code implementations • 29 Sep 2016 • Mahdyar Ravanbakhsh, Hossein Mousavi, Moin Nabi, Mohammad Rastegari, Carlo Regazzoni
To the best of our knowledge our method is the first attempt on general semantic image segmentation using CNN.
no code implementations • 13 Dec 2015 • Mahdyar Ravanbakhsh, Hossein Mousavi, Mohammad Rastegari, Vittorio Murino, Larry S. Davis
Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model.