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
- Heikki A. KalviainenSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works176 from public data
- the DIARETDB1 diabetic retinopathy database and evaluation protocol921
With the proposed database and protocol, it is possible to compare different algorithms, and correspondingly, analyse their maturity for technology transfer from the research laboratories to the medical practice.
- Differential Evolution Training Algorithm for Feed-Forward Neural Networks639
In this study, differential evolution has been analyzed as a candidate global optimization method for feed-forward neural networks and seems not to provide any distinct advantage in terms of learning rate or solution quality.
- 496
- 368
- The Eighth Visual Object Tracking VOT2020 Challenge Results350
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- AR-based interaction for human-robot collaborative manufacturing252
A depth-sensor based model for workspace monitoring and an interactive Augmented Reality (AR) User Interface (UI) for safe HRC are proposed and evaluated in a realistic diesel engine assembly task.
- Simple Gabor feature space for invariant object recognition220
In this study, fundamental properties of Gabor features, construction of the simple feature space, and invariant search operations in the feature space are discussed in more detail.
- Feature representation and discrimination based on Gaussian mixture model probability densities—Practices and algorithms182
In this study maximum likelihood estimation methods for Gaussian mixture models are reviewed and discussed from a practical point of view, and good practices for utilizing probability densities in feature classification and selection are discussed for Bayesian and for non-Bayesian tasks.
- 164
- 130
- DepthTrack: Unveiling the Power of RGBD Tracking130
A new RGBD tracking dataset - Depth-Track - is introduced that has twice as many sequences and scene types than in the largest existing dataset, and three times more objects, and the average length of the sequences, number of deformable objects and the number of annotated tracking attributes have been increased.
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Object Detection in Equirectangular Panorama114
A high-resolution equirectangular panorama dataset for object detection and a multi-projection variant of the YOLO detector, which outperforms the other state-of-the-art detector, Faster R-CNN, and achieves the best accuracy with low-resolution input.
- Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters98
The proposed long-term RGB-D tracker called OTR – Object Tracking by Reconstruction performs online 3D target reconstruction to facilitate robust learning of a set of view-specific discriminative correlation filters (DCFs).
- 98
- On Finding Gray Pixels85
The grayness index, GI in short, is derived using the Dichromatic Reflection Model and is learning-free, and outperforms state-of-the-art statistical methods and many recent deep methods.
- CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark83
The CDTB dataset is the largest and most diverse dataset in RGB-D tracking, with an order of magnitude larger number of frames than related datasets, indicating a large gap between the two fields, which has not been previously detected by the prior benchmarks.
- Convolutional low-resolution fine-grained classification82
A novel resolution-aware deep model is proposed which combines convolutional image super-resolution and Convolutional fine-grained classification into a single model in an end-to-end manner and consistently performs better than conventional convolutionAL networks on classifying fine- grained object classes in low-resolution images.
- How to Make an RGBD Tracker?65
A generic framework for converting an arbitrary short-term RGB tracker into an RGBD tracker that is particularly powerful in occlusion scenarios where it provides 13.5% average improvement and 26% for the best tracker (CSR-DCF).
- 61
- Urban 3D segmentation and modelling from street view images and LiDAR point clouds59
A novel methodology that takes GPS registered LiDAR point clouds and street view images as inputs and creates semantic labels for the 3D points clouds using a hybrid of rule-based parsing and learning-based labelling that combine point cloud and photometric features is proposed.
- 55
- Anthropometric clothing measurements from 3D body scans54
A full processing pipeline to acquire anthropometric measurements from 3D measurements, based on non-rigid iterative closest point algorithm that minimizes overall energy of point distance and local stiffness energy terms is proposed.
- 52
- 48
- Projector Calibration by “Inverse Camera Calibration”47
The problem of video projector calibration is solved by inverting the standard camera calibration work flow and iteratively adjusts the projected dots to coincide with the landmarks and the final coordinates are used as inputs to a camera calibration method.
- 46
- Efficient computation of Gabor features45
The main contribution of this study is the comprehensive survey of existing and development of new improvements which can be applied to filter parameter selection, filter construction, and feature computation to provide a complete framework for optimally efficient computation of Gabor features.
- 44
- Improving similarity measures of histograms using smoothing projections43
In this study, similarity measures are analyzed in the context of ordered histogram type data, such as gray-level histograms of digital images or color spectra, and the performance of the studied similarity measures can be improved using a smoothing projection, called neighbor-bank projection.
- Revisiting Gray Pixel for Statistical Illumination Estimation40
Experiments on two real-world benchmarks show that the proposed approach outperforms state-of-the-art methods in the camera-agnostic scenario and in the setting where the camera is known, MSGP outperforms all statistical methods.
- 360 Panorama Super-resolution using Deep Convolutional Networks37
Deep convolutional neural network based super-resolution for 360 (equirectangular) panorama images used by virtual reality (VR) display devices (e.g. VR glasses) is proposed and it is demonstrated how adaptation can be performed by optimizing the trained network input size and fine-tuning the network parameters.
- Constructing Benchmark Databases and Protocols for Medical Image Analysis: Diabetic Retinopathy36
A framework consisting of reusable methods and tools for the laborious task of constructing a benchmark database for diabetic retinopathy detection algorithms is proposed and a software tool for medical image annotation helping to collect class label, spatial span, and expert's confidence on lesions is provided.
- 35
- 33
- 32
- Toward automatic forecasts for diffusion of innovations31
An automated framework for forecasting the diffusion of innovations, which utilizes existing diffusion information from any market areas or similar products introduced to the markets earlier, and which aims to move present theory toward more practical and automatic prediction tools for company analysts and diffusion researchers.
- 29
- Detection of irregularities in regular patterns29
In this study, the problem of irregularity detection is described in analytical form and three different detection methods are proposed, based on characteristics of the Fourier transform to compactly represent regular information.
- A comparison of feature detectors and descriptors for object class matching27
This work extends the benchmarks to the class matching setting and evaluates state-of-the-art detectors and descriptors with Caltech and ImageNet classes and provides important findings with regard to object class matching.
- 26
- PlaceNav: Topological Navigation through Place Recognition25
This work subdividing the robot-independent part into navigation-specific and generic computer vision components makes subgoal selection more efficient and enables leveraging large-scale datasets from non-robotics sources, increasing training data availability.
- Focus model for metric depth estimation in standard plenoptic cameras25
A closed-form model is proposed that relates the refocusing parameter with the focus distance of a plenoptic camera in order to allow for metric depth estimation and a calibration procedure is developed that allows finding the parameters of the model.
- Depth Masked Discriminative Correlation Filter25
A Depth Masked Discriminative Correlation Filter (DM-DCF) is proposed which adopts novel depth segmentation based occlusion detection that stops correlation filter updating and depth masking which adaptively adjusts the spatial support for correlation filter.
- Image Based Quantitative Mosaic Evaluation with Artificial Video25
The authors present a measuring method for evaluating mosaicing performance of different algorithms, and showcase it with the root-mean-squared error.
- Mottling Assessment of Solid Printed Areas and Its Correlation to Perceived Uniformity25
Three methods to evaluate print mottle are implemented and it is shown that when assessing low-contrast unevenness of print, humans have diverse opinions about quality, and none of the methods accurately capture the characteristics of human vision.
- 24
- 23
- 22
- Deep structured-output regression learning for computational color constancy22
Experiments demonstrate that the structured-output regression on the values of the fully-connected layers of a convolutional neural network achieves competitive performance, outperforming the state of the art on the SFU indoor benchmark.
- Design and application of a fish-shaped lateral line probe for flow measurement22
The lateral line probe (LLP) is introduced as a measurement device for natural flows and its output is compared to estimates of conventional point-based technologies to introduce a new type of measurement devices for body-centric data.
- 20
- 20
- Video Shot Boundary Detection using Visual Bag-of-Words20
This work solves the problem of shot boundary detection using a popular image analysis (object detection) approach: visual bag-of-words (BoW), and an “AND-combination” of colour and BoW histogram detection is clearly superior indicating that colour and local features provide complimentary information for video analysis.
- 20
- 19
- Bayesian network model of overall print quality: Construction and structural optimisation19
A computational model for representing and quantifying the overall visual quality of prints is proposed, a Bayesian network which connects the objective instrumental measurements to the subjective opinion distribution of human observers and reveals and represents the explanatory factors between its elements providing insight to the psychophysical phenomenon of how observers perceive visual quality.
- Full Reference Printed Image Quality: Measurement Framework and Statistical Evaluation19
The authors benchmark the state-of-the-art methods and point out similar results in the digital domain: the best digital full reference measures, such as the recently introduced visual information fidelity algorithm, perform best also for printed media.
- Fusion of Multiple Expert Annotations and Overall Score Selection for Medical Image Diagnosis19
Two problems especially important for supervised learning and classification in medical image processing are addressed in this study: how to fuse medical annotations collected from several medical experts and how to form an image-wise overall score for accurate and reliable automatic diagnosis.
- 19
- State-Conditioned Adversarial Subgoal Generation18
Comparison to state-of-the-art algorithms shows that the proposed novel HRL approach for mitigating the non-stationarity by adversarially enforcing the high- level policy to generate subgoals compatible with the current instantiation of the low-level policy improves both learning efficiency and performance in challenging continuous control tasks.
- Turning wingbeat sounds into spectrum images for acoustic insect classification18
A novel acoustic insect classifier on deep convolutional feature of frequency spectrum images generated by their wingbeat sounds is introduced, which is the first attempt to convert time-series acoustic signal processing to image recognition.
- 18
- 18
- Framework for Applying Full Reference Digital Image Quality Measures to Printed Images18
The aim is to reduce the gap by presenting a complete framework starting from the original digital image and its hard-copy reproduction to a scanned digital sample which is compared to the original reference image by using existing quality measures.
- RGBD Object Tracking: An In-depth Review17
This paper is the first to provide depth quality evaluation and analysis of tracking results in depth-friendly scenarios in RGBD tracking, and proposes robustness evaluation against input perturbations.
- 16
- Live RGB-D camera tracking for television production studios16
This work derives a real-time tracker from the cost function for a low-end GPU, designed for live television production studios, and demonstrates robust and driftless real- time camera tracking in a television production studio environment.
- Hypotheses-Driven Affine Invariant Localization of Faces in Verification Systems16
A novel framework for localizing human faces in client authentication scenarios based on correspondences between triplets of detected Gabor-based local features and their counterparts in a generic affine invariant face appearance model is proposed.
- Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation15
This work focuses on solving partial observability of contact-rich manipulation tasks as a Sequence-to-Sequence (Seq2Seq) Imitation Learning (IL) problem and is able to learn both tasks from only 50 expert demonstrations while state-of-the-art reinforcement learning and imitation learning methods fail.
- 15
- 15
- Robustness of Gabor Feature Parameter Selection15
Gabor filtering based features are analyzed in terms of filter parameters to provide new insight into advantages of Gabor filters and results show that filter responses behave in a stable manner even while the parameter selection is suboptimal.
- Cumulative attribute space regression for head pose estimation and color constancy14
It is shown how the original CA space can be generalized to multiple output by the Cartesian product (CartCA), but for target spaces with more than two outputs the CartCA becomes computationally infeasible and therefore an approximate solution - multi-view CA (MvCA) - where CartCA is applied to output pairs is proposed.
- Invariant Gabor Features for Face Evidence Extraction14
A novel illumination, translation, rotation, and scale invariant feature extraction method based on Gabor filtering is introduced and is successfully applied to invariant detection of facial features.
- 13
- 13
- Unsupervised object discovery via self-organisation13
The self-organising principle is adopted and clustering is replaced with the self- Organising map (SOM) algorithm and this method provides results comparable to the state of the art and its advantages, such as non-sensitivity against codebook histogram normalisation, advocate its usage in unsupervised object discovery.
- Towards Monocular On-Line 3D Reconstruction13
This paper proposes to combine monocular visual SLAM with dense visual reconstruction techniques in order to build geometrically correct three-dimensional models, which can be used for action generation, such as path or grasp planning in a robotic system.
- Probabilistic Subgoal Representations for Hierarchical Reinforcement learning12
This paper utilizes Gaussian Processes for the first probabilistic subgoal representation and proposes a novel learning objective to facilitate the simultaneous learning of probabilistic subgoal representations and policies within a unified framework.
- 12
- Generative part-based Gabor object detector12
This work proposes a part-based generative model that performs comparably to the state-of-the-art discriminative method and uses bio-inspired complex-valued Gabor features to describe local parts.
- Combining Multiple Image Segmentations by Maximizing Expert Agreement12
This work generates a new ground truth for the popular diabetic retinopathy benchmark, DiaRetDB1, for which the original expert markings are publicly available and produces the optimal disambiguation by maximizing the agreement and no priors are used.
- 12
- Fast Fourier Intrinsic Network11
The Fast Fourier Intrinsic Network, FFI-Net in short, is proposed that operates in the spectral domain, splitting the input into several spectral bands, allowing faster convergence to a lower error.
- Cross-dataset Color Constancy Revisited Using Sensor-to-Sensor Transfer11
A sensor-to-sensor transfer model that can be used to map datasets with known cameras to any other known camera and the only requirement is that spectral characterizations of the camera models are available is introduced.
- 11
- Cross-Granularity Graph Inference for Semantic Video Object Segmentation11
This work addresses semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling and proposes a transductive inference model which is capable of calibrating short-range noisy object tracklets with respect to long-range dependencies and high-level context cues.
- Bag-of-Features Codebook Generation by Self-Organisation11
It is claimed that exploiting the self-organisation principle is an alternative research direction to the mainstream research in visual object categorisation and its importance for the ultimate challenge, unsupervised visual objectategorisation, needs to be investigated.
- 11
- Benchmarking Visual Localization for Autonomous Navigation10
The proposed benchmark is the first to study modern visual localization methods as part of a complete navigation stack and shows major variation in the suitability of the different methods for vision-based navigation.
- 10
- 10
- 10
- Thresholding Based Detection of Fine and Sparse Details10
The provided method and measurement system prototype provide automated assessment with results comparable to manual expert evaluations in this laborious task.
- Dichromatic Gray Pixel for Camera-agnostic Color Constancy.9
A novel statistical color constancy method, especially suitable for the Camera-agnostic Color Constancy, i.e. the scenario where nothing is known a priori about the capturing devices, based on a novel gray pixel detection algorithm derived using the Dichromatic Reflection Model.
- Local Representation of Facial Features9
This chapter specifically describes in more details two prominent local facial features, the first one based on Gabor filter responses, and the second on more recently proposed local binary patterns (LBPs).
- Quantified and Perceived Unevenness of Solid Printed Areas9
A modification to the bandpass method that utilizes a contrast sensitivity function for the human visual system directly in the frequency domain and the function parameters are optimized based on the human assessment results a significant improvement in the correlation to human assessment when compared to the original bandpassmethod.
- Neural Network Controller for Autonomous Pile Loading Revised8
This work proposes a revised neural controller (NNetV2) which has a more expressive structure and uses a neural attention mechanism to focus on important parts of the sensor and control signals and achieves better robustness against drastically changing conditions and superior success rate.
- Performance analysis of single-query 6-DoF camera pose estimation in self-driving setups8
A hybrid approach that combines feature-based and mutual-information-based pose estimation methods to benefit from their complementary properties for pose estimation is evaluated.
- Keyframe-based Video Summarization with Human in the Loop8
This work introduces a human-in-the-loop step where user selects keyframes produced by the three best methods, achieves superior accuracy to learning-based methods and for many videos is on par with average human accuracy.
- Spectral attribute learning for visual regression8
An approach to automatically discover spectral attributes which avoids manual work required for defining hand-crafted attribute representations is proposed and this spectral attribute visual regression achieves state-of-the-art accuracy in multiple applications.
- Visual Print Quality Evaluation Using Computational Features8
A new approach for automating the evaluation is proposed and the approach is utilised by defining new computational level features which are able to explain visual quality evaluations performed by human experts.
- Object Evidence Extraction Using Simple Gabor Features and Statistical Ranking8
An accurate and efficient method for evidence extraction based on simple Gabor features and their statistical ranking is introduced.
- Single Pixel Spectral Color Constancy7
This work proposes a spectral data generation pipeline that can be used if the dataset camera model is known and thus its spectral characterization can be obtained and obtains the highest accuracy in the both single and cross-dataset experiments.
- 7
- Benchmarking 6D Object Pose Estimation for Robotics.7
This work formulate the problem as a successful grasp, i.e. for a fixed set of factors affecting the task, will the given pose estimate provide sufficiently good grasp to complete the task.
- Facial Age Estimation Using Robust Label Distribution7
A novel concept of robust label distribution for scalar-valued labels is introduced, which is designed to encode the age scalars into label distribution matrices, i.e. two-dimensional Gaussian distributions along age classes and age groups respectively.
- A Framework for Constructing Benchmark Databases and Protocols for Retinopathy in Medical Image Analysis7
A framework consisting of reusable methods and tools for the laborious task of constructing a benchmark database and a medical image annotation software tool which helps to collect and store ground truth for retinopathy lesions from experts, including the fusion of spatial annotations from several experts are proposed.
- 7
- Local and global Gabor features for object recognition7
Both analytical and experimental results indicate that when certain conditions on the filter parameters are met, Gabor filtering can be reliably used in low-level feature extraction in image processing, and the filter responses can be used to construct robust invariant recognition systems.
- Measuring Translation Shiftability of Frames7
In this study, translation shiftability measures for frames of regular translates are revisited, novel measures are proposed, and numerical examples are shown.
- Synthetic vs. Real Training Data for Visual Navigation6
The proposed navigation policy architecture is a navigation policy architecture that bridges the sim-to-real appearance gap by leveraging pretrained visual representations and runs real-time on robot hardware and identifies on-policy learning as a key advantage of simulated training over training with real data.
- 6
- Micro-parenchymal patterns for breast cancer risk assessment6
Experimental evidence is provided that there are specific MP patterns identifiable as cues of breast cancer and prompt the validation of these results in larger datasets.
- Evaluation of Visual Object Trackers on Equirectangular Panorama6
This work introduces a new dataset which consists of high quality equirectangular videos captured using a high-end VR camera (Nokia OZO), and provides the original wide angle videos and densely annotated bounding boxes for evaluating object detectors and trackers.
- Object Class Detection Using Local Image Features and Point Pattern Matching Constellation Search6
A novel method for object class detection is introduced that combines supervised Gabor-based confidence-ranked image features and affine invariant point pattern matching and its potential is demonstrated on a standard face database.
- Depth-only Object Tracking5
The end-to-end trained RGBD-DiMP outperforms the recent VOT 2020 RGBD winners and generates depth maps for tracking from the scratch with the generated data and fine-tune it with the available small RGBD tracking datasets.
- 5
- Learning with Ambiguous Label Distribution for Apparent Age Estimation5
A novel concept of ambiguous label distribution for apparent age estimation is introduced under the following observations: soft labelling is beneficial for alleviating the suffering of inaccurate annotations and more reliable annotations should contribute more, and label distributions of sparse age annotations for each image are weighted according to their reliableness.
- 5
- RGB-D Tracking and Reconstruction for TV Broadcasts5
An affordable vision-based system is proposed which can compete with expensive matchmov-ing systems and is tested in a television broadcasting studio, where it demonstrates driftless and precise camera tracking in real-time.
- 5
- 4
- 4
- Flash Lightens Gray Pixe4
It is shown that flash photography significantly improves the performance of gray pixel detection without illuminant prior, training data, calibration of the flash, and a novel flash photography dataset generated from the MIT intrinsic dataset is introduced.
- 4
- Lifelog Scene Change Detection Using Cascades of Audio and Video Detectors4
It is pointed out that audio cues are exceptionally strong for lifelog processing; cascades of audio and video detectors improve accuracy and enable fast (super frame rate) processing speed; and separating the detector and cascade optimisation stages simplify training and results to a fast and accurate processing pipeline.
- 4
- Thresholding-based detection of fine and sparse details4
The provided method and measurement system prototype provide automated assessment with results comparable to manual expert evaluations in this laborious task.
- Detection and decision-support diagnosis of diabetic retinopathy using machine vision4
The IMAGERET project consists of an image annotation tool for medical expert annotation, diabetic retinopathy databases, an evaluation framework for development and comparison of methods, image-based and pixel-based methods, and new imaging solutions.
- 3
- 3
- 3
- Indoor Objects and Outdoor Urban Scenes Recognition by 3D Visual Primitives3
This work proposes an alternative appearance-driven approach which first extracts 2D primitives justified by Marr’s primal sketch and the most stable ones are “promoted” to 3D visual primitives, which represent both structure and appearance.
- Narrow Baseline GLSL Multiview Stereo3
GPGPU processing using standard OpenGL, GLSL, and ARB extensions provides extremely low CPU consumption and Arbitrary viewpoints, as long as views overlap.
- 3
- 3
- 2
- Progressive Visual Object Detection with Positive Training Examples Only2
A two-step framework by training a generative detector with positive samples first and then utilising a discriminative model to get rid of false positives in those detected bounding box candidates by the generative detectors is proposed.
- Goniometric Imaging of Paper Gloss2
The behavior of gloss is studied using goniometric imaging and spectral color information to capture reflection images that reveal the spatial variation of the gloss over paper samples.
- 2
- Automating Visual Inspection of Print Quality2
The experimental results are evidence how the human assessment can be automated with the help of machine vision, thus making the test more repeatable and accurate.
- 2
- 1
- 1
- 1
- 1
- 1
- Pose Estimation using a Hierarchical 3D Representation of Contours and Surfaces1
This work defines an object model in terms of a simple context descriptor of the contour and texture features to provide a sparse, yet descriptive object representation to detect the pose of rigid objects using texture and contour information.
- Supervised Object Class Colour Normalisation1
A colour normalisation technique where true colours are not important per se but where examples of same classes have photometrically consistent appearance is developed, achieved by supervised estimation of a class specific canonical colour space where the examples have minimal variation in their colours.
- Unsupervised Visual Object Categorisation with BoF and Spatial Matching1
This work proposes a novel unsupervised image categorisation method which uses the BoF to find initial matches for each image (pre-filter) and then refines and ranks them using spatial matching of local features.
- 1
- Forecasting the Critical Mass of Wireless Communications1
The findings suggest that critical mass is achieved faster and on lower penetration levels in later adopting countries.
- Minimum error contrast enhancement1
The main contribution of this study is to express the contrast enhancement as a mapping from N-channel image data to 1-channel gray-level image, and to devise a projection method which results to an image with minimal error to the correct contrast image.
- Toward Automatic Motor Condition Diagnosis1
The method is based on a statistical discriminance measure which can be used to select the most discriminative features and is verified using real measurements from induction motors in normal condition and with bearing faults.
- 1
- –
- –
- –
- –
- Evaluation of RGB and LiDAR Combination for Robust Place Recognition–
A study on the utility of fine-tuned Deep Convolutional Neural Network with three MAC, SpoC and GeM pooling layers to learn global image representation for place recognition in an end-to-end manner using three different sensor data modalities.
- Evaluation of Long-term Deep Visual Place Recognition–
This paper studies recent visual place recognition and image retrieval methods and utilizes them to conduct extensive and comprehensive experiments on two diverse and large long-term indoor and outdoor robot navigation datasets, e.g., COLD and Oxford Radar RobotCar.
- Monolithic vs. hybrid controller for multi-objective Sim-to-Real learning–
This work shows that the training of a hybrid controller is easier and obtains a better success-failure trade-off than a monolithic controller in the multi-objective setting of a robot manipulator to reach a target while avoiding an obstacle.
- –
- –
- –
- –
- –
- –
- –
- Hierarchical Deformable Part Models for Heads and Tails–
The proposed Hierarchical Deformable Part Model consistently achieves significant performance improvement in visual detection and is compared with other sub-category aware visual detection methods with a moderate size dataset.
- –
- Discovering Multi-relational Latent Attributes by Visual Similarity Networks–
An unsupervised framework for network construction based on pairwise visual similarities is introduced and it is experimentally demonstrated that the constructed network can be used to automatically discover multiple discrete (e.g. sub-classes) and continuous (pose change) latent attributes.
- Best of 18th Scandinavian Conference On Image Analysis 2013–
This special section includes the two best paper winners from the 18th Scandinavian Conference on Image Analysis (SCIA), which took place in Espoo, Finland in June 17–3.
- From Full-Reference to No-Reference in Quality Assessment of Printed Images–
A no-reference quality assessment approach based on a Bayesian network model of print quality is proposed and its quantitative results are reported by using subjective data.
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.