- document
-
Garg, Chirag (author)3D indoor reconstruction has been an important research area in the field of computer vision and photogrammetry. While the initial techniques developed for this purpose use sensor devices and multiple images for data acquisition and extracting 3D information and representation of the scene, with the advent of deep learning techniques, there has...master thesis 2020
- document
-
Lelekas, Ioannis (author)Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli. On the contrary, CNNs employ a fine-to-coarse processing, moving from local, edge-detecting filters to more global ones...master thesis 2020
- document
-
Li, Xin (author)Visual context plays a key role in many computer vision tasks, and performance of eye/gaze-tracking methods also benefit from it. However, the size of contextual information (e.g. full face image) is very large w.r.t the primary input i.e. cropped image of the eye. This adds large computational costs to the algorithm and makes it inefficient,...master thesis 2019
- document
-
Pathak, Chinmay (author)Anomaly detection is a task of interest in many domains. Typical way of tackling this problem is using an unsupervised way. Recently, deep neural network based density estimators such as Normalizing flows have seen a huge interest. The ability of these models to do the exact latent-variable inference and exact log-likelihood calculation with...master thesis 2019
- document
-
Li, Jiahui (author)A cross-domain visual place recognition (VPR) task is proposed in this work, i.e., matching images of the same architectures depicted in different domains. VPR is commonly treated as an image retrieval task, where a query image from an unknown location is matched with relevant instances from geo-tagged gallery database. Different from...master thesis 2019
- document
-
Batheja, Dhruv (author)This work tackles the problem of repetition counting in videos using modern deep learning techniques. For this task, the intention is to build an end-to-end trainable model that could estimate the number of repetitions without having to manually intervene with the feature selection process. The models that exist currently perform well on videos...master thesis 2019
- document
-
Lengyel, Attila (author)This work investigates how prior knowledge from physics-based reflection models can be used to improve the performance of semantic segmentation models under an illumination-based domain shift. We implement various color invariants as a preprocessing step and find that CNNs trained on these color invariants get stuck in worse local minima...master thesis 2019
- document
-
Anand, Kanav (author)Deep learning is proving to be a useful tool in solving problems from various domains. Despite a rich research activity leading to numerous interesting deep learning models, recent large scale studies have shown that with hyperparameter optimization it is hard to distinguish these models based on their final performance. Hyperparameter...master thesis 2019
- document
-
Yang, Hongyu (author)Occlusion and crossing in Multi-Person Tracking always influence the tracking results. In this paper, we show how deep Re-Identification (ReID), which aims at matching pedestrians across non-overlapping video cameras, can be used to improve the occlusion problem on tracking. The learned ReID feature is more robust than other features used in...master thesis 2018
- document
-
Shi, Xiangwei (author)We propose a framework to interpret deep convolutional models for visual place classification. Given a deep place classification model, our proposed method produces visual explanations and saliency maps that reveal the understanding of images by the model. To evaluate the interpretability, t-SNE algorithm is used for mapping and visualization of...master thesis 2018
- document
-
Claus, Michele (author)We propose a novel Convolutional Neural Network (CNN) for Video Denoising called VidCNN, which is capable to denoise videos without prior knowledge on the noise distribution (Blind). VidCNN is a flexible model, since it tackles multiple noise types, artificial and real. The CNN architecture uses a combination of spatial and temporal filtering,...master thesis 2018
- document
-
Cheng, Zhaoyang (author)Vegetation phenology is the interaction between vegetation activities and ecosystem. Accurate monitoring of vegetation phenology is required to build models and enhance the understanding of the relationship between creatures and climate-environment. PhenoCam is a ground-level, webcam based images database recording the growing of various...master thesis 2018
- document
-
Maton, Max (author)Creating big datasets is often difficult or expensive which causes people to augment their dataset with rendered images. This often fails to significantly improve accuracy due to a difference in distribution between real and rendered datasets. This paper shows that the gap between synthetic and real-world image distributions can be closed by...bachelor thesis 2018
- document
-
Rijlaarsdam, Matthijs (author)Object detectors, much like humans, perform less well on small than on large objects. Because of this, the object size distribution of a dataset influences the average precision a network achieves on that dataset. Therefore, the object size/precision curve of a network might be a better way to compare convolutional object detectors than the...bachelor thesis 2018
- document
-
Hommos, Omar (author)Action recognition continues to receive significant attention from the research community, with new neural network architectures being developed continuously. Optical flow is by far the most popular input motion representation to these architectures, leaving a lot of undiscovered potential for other types of motion representations. Eulerian...master thesis 2018
- document
-
Uijens, Wouter (author)Convolutional Neural Networks (CNNs) are achieving state of the art performance in computer vision. One downside of CNNs is their computational complexity. One way to make CNNs more computational efficient is by implementing their convolutions in the frequency domain, using Fast Fourier Transforms (FFTs). This has as a consequence that most...master thesis 2018
- document
-
Sulzer, Raphael (author)The seismic building structural type (SBST) reflects the main load-bearing structure of a building and therefore its behaviour under seismic load. For numerous areas in earthquake prone regions this information is outdated, unavailable, or simply not existent. Traditional methods to gather this information, such as building-by-building...master thesis 2018
- document
-
Liu, Yue (author)Over the past several years, deep and wide neural networks have achieved great success in many tasks. However, in real life applications, because the gains usually come at a cost in terms of the system resources (e.g., memory, computation and power consumption), it is impractical to run top-performing but heavy networks such as VGGNet and...master thesis 2017
- document
-
Zhang, Chengqiu (author)In this thesis, we propose a novel unsupervised clean-noisy datasets adaptation algorithm based on standard deep learning networks. Specifically, we jointly learn a shared feature encoder for two tasks: 1)supervised classification trained on labeled source (clean) dataset, and 2) unsupervised adaptation to map discriminant features from both...master thesis 2017