Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks103 from public data
- 145
- 132
- 106
- Eye pupil localization with an ensemble of randomized trees103
A framework for eye pupil localization based on an ensemble of randomized regression trees that compares well with reported state-of-the-art and runs in real-time on hardware with limited processing power, such as mobile devices.
- 95
- 94
- Fast facial expression recognition using local binary features and shallow neural networks93
The proposed algorithm (LBF-NN) compares favorably with state-of-the-art algorithms while achieving an order of magnitude improvement in execution time.
- 73
- Model-based coding : extraction, coding, and evaluation of face model parameters70
This thesis deals with model-based coding of human faces for low bitrate communication and finds that the appearance and motion of a human face are analysed.
- The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results66
A significant general improvement of results has been observed, which partly compensate for the more difficult sequences introduced into the dataset in VOT-TIR2016.
- AN UPDATED PARAMETERISED FACE62
This report documents an updated version of C ANDIDE, fulfilling the demands set by MPEG-4 and being somewhat less crude.
- 60
- Herbivore grazing—or trampling? Trampling effects by a large ungulate in cold high‐latitude ecosystems59
In replicated factorial experiments, high‐resolution 3D laser scanning was used to quantify lichen volume loss from trampling by a reindeer hoof, and the lichen humidity appears to be an important factor for trampling loss, in addition to the extent of reindeers movement.
- 49
- A method for object detection based on pixel intensity comparisons48
A method for visual object detection based on an ensemble of optimized decision trees organized in a cascade of rejectors that uses pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast.
- A Method for Object Detection Based on Pixel Intensity Comparisons Organized in Decision Trees48
A method for visual object detection based on an ensemble of optimized decision trees organized in a cascade of rejectors that uses pixel intensity comparisons in their internal nodes and this makes them able to process image regions very fast.
- 47
- Fitting 3D face models for tracking and active appearance model training44
Two appearance-based methods that only require a simple statistical facial texture model and do not require any information about an empirical or analytical gradient matrix are proposed, since the best search directions are estimated on the fly.
- Detecting Rails and Obstacles Using a Train-Mounted Thermal Camera39
The proposed method includes a novel way of detecting the rails in the imagery, as well as a way to detect anomalies on the railway, using a monocular thermal camera.
- 39
- 36
- Face tracking for model‐based coding and face animation35
A face and facial feature tracking system able to extract animation parameters describing the motion and articulation of a human face in real‐time on consumer hardware is presented.
- 33
- 32
- Regression-based methods for face alignment: A survey31
The latest development in regression-based approaches that have led towards nearly solving the face alignment problem in an unconstrained scenario are presented and a benchmark comparison of the most successful methods is presented to provide a comprehensive overview of this dynamic research field.
- 31
- Enhanced analysis of thermographic images for monitoring of district heat pipe networks29
This work addresses two problems related to large-scale aerial monitoring of district heating networks by proposing a classification scheme to reduce the number of false alarms among automatically detaining heating networks.
- 27
- 26
- 26
- Active Contours in Three Dimensions26
To find a shape in an image, a technique called snakes or active contours can be used, which moves towards the sought-for shape in a way controlled by internal forces.
- 24
- 23
- Faces Everywhere: Towards Ubiquitous Production and Delivery of Face Animation18
The goal is to offer a framework of tools interconnected by standard formats and protocols and capable of supporting any imaginable application involving face animation with the desired level of animation quality, automatic production wherever it is possible, and delivery on a wide range of platforms.
- An Experiment on 3D Face Model Adaptation using the Active Appearance Algorithm17
This report describes the first implementation and experiment on adapting a 3D wirefrane model to a face in an input image using the Active Appearance Algorithm and concludes that this track should be continued in the task to create a real-time model-based coder.
- A thermal infrared dataset for evaluation of short-term tracking methods16
A thermal infrared dataset for evaluation of short-term tracking methods that consists of 20 sequences which have been collected from multiple sources and the data format used is in accordance with the Visual Object Tracking (VOT) Challenge.
- 15
- 15
- 15
- 14
- Online Learning of Correspondences between Images13
A novel method for iterative learning of point correspondences between image sequences that optimizes the mapping based on Neyman's chi-square divergence between the densities representing the uncertainties of the estimated and the actual locations.
- A feature based face tracker using extended Kalman filtering13
This report is based on the work of a real time feature based face tracker that tracks feature points using motion between frames and a textured face model (Candide), and uses an extended Kalman filter to estimate the parameters from the tracked feature points.
- An information system for target recognition13
The aim is to cover the complete process for automatic target recognition, from sensor data to the user interface, based on a query-based information system, and include tasks like feature extraction from sensorData, data association, data fusion and situation analysis.
- BASE: Probably a Better Approach to Visual Multi-Object Tracking12
BASE (Bayesian Approximation Single-hypothesis Estimator), a simple, performant and easily extendible visual tracker, achieving state-of-the-art (SOTA) on MOT17 and MOT20, without using Re- Id.
- Face Model Adaptation for Tracking and Active Appearance Model Training12
Two adaptation methods for adapting a 3D deformable face model to video sequences are proposed and it is shown that the proposed methods can outperform the adaptation based on a directed continuous search.
- Representing and compressing facial animation parameters using facial action basis functions12
This work seeks to utilize this spatial correlation between FAPs and interframe delay to achieve efficient compression in facial animation parameters specified in MPEG-4, and is suitable for interactive applications, e.g., videophone and interactive video, where low delay is a vital issue.
- Unsupervised Adversarial Learning of Anomaly Detection in the Wild11
This work evaluates the effects of anomaly contaminations in the training data on state-of-the-art GAN-based anomaly detection methods and proposes to add an additional encoder network already at training time and shows that joint generator-encoder training stratifies the latent space, mitigating the problem with contaminated data.
- Three-dimensional hyperspectral imaging technique11
A configuration has been developed that enables the reconstruction of the hyperspectral three-dimensional environment and the camera is described, based on a linear variable filter and a high frame rate, high resolution camera enabling point-to-point matching and 3D reconstruction.
- Fast Localization of Facial Landmark Points11
A method that can accurately estimate the positions of relevant facial landmarks in real-time even on hardware with limited processing power, such as mobile devices is described.
- 11
- 11
- Facial Feature Extraction using Deformable Graphs and Statistical Pattern Matching11
In model-based coding of image sequences containing human faces, the detection and location of the face as well as the extraction of facial features from the images are crucial and there are different approaches to reduce the computational complexity.
- Fast Rendering of Image Mosaics and ASCII Art10
This work proposes an algorithm able to reproduce the quality of existing non‐photorealistic rendering techniques, in particular ASCII art and image mosaics, obtaining large performance speed‐ups.
- Effective evaluation of privacy protection techniques in visible and thermal imagery9
An annotation-free evaluation method that is neither subjective nor assumes a specific target type in image data and use target detection and recognition accuracies to assess privacy protection is proposed and demonstrated effectiveness by evaluating six image-based privacy protection techniques and also shows comparisons of the proposed method over existing methods.
- 8
- 8
- Picking out the bad apples: unsupervised biometric data filtering for refined age estimation7
The unsupervised facial biometric data filtering method presented in this work greatly reduces label noise levels in web-scraped facial biometry data and enables considerable performance gains for all tested age estimation methods and age estimation tasks.
- An Overview of the Thermal Infrared Visual Object Tracking VOT-TIR2015 Challenge7
The Thermal Infrared Visual Object Tracking (VOT-TIR2015) Challenge was organized in conjunction with ICCV2015 and was the first benchmark on short-term, single-target tracking in thermal infrared.
- 7
- 7
- 6
- The Detection of Concealed Targets in Woodland Areas using Hyperspectral Imagery5
This work presents the assessment of the imager L4 from Glana Sensors to detect concealed targets in woodland areas and evaluates the potential and limitations of this new imaging device in the context of difficult target detection in forested area.
- 5
- 5
- Classifying district heating network leakages in aerial thermal imagery5
The results show that this postprocessing step significantly improves the usefulness of the system and proposes to address the issue by machine learning techniques and provide extensive experimental analysis on real-world data.
- 5
- 5
- 5
- A sensor management framework for autonomous UAV surveillance5
A framework inspired by optimal control and information theory is presented for concurrent path and sensor planning and a method for visual landmark selection and recognition is presented, intended to be used within a SLAM (Simultaneous Localization and Mapping) architecture for visual navigation.
- 4
- 4
- High-performance face tracking4
This extended abstract briefly describes the implementation of a high-performance multi-platform face and facial feature tracking system that is robust, resistant to rapid changes in pose and facial expressions, does not suffer from drifting and is modestly computationally expensive.
- WinCandide 1.3 User’s Manual4
WinCandide is a piece of software for handling, visualizing, and synhtesizing wireframe face models that could be used with other face models as well.
- Detection-Guided Attention for Selective Target Classification Using Radar Micro-Doppler Spectrograms3
This work proposes to inform the classifier which targets to classify by encoding the detected target position as a separate channel, which enables the model to classify individual objects in multitarget spectrograms, paving the way for higher classification performance in complex environments.
- BASE: Probably a Better Approach to Multi-Object Tracking3
BASE (Bayesian Approximation Single-hypothesis Estimator), a simple, performant and easily extendible visual tracker, achieving state-of-the-art (SOTA) on MOT17 and MOT20, without using Re-Id is presented.
- Simultaneous sensing, readout, and classification on an intensity‐ranking image sensor3
This paper describes techniques for classification and proposes a particular variant (groves) that fits the IRIS architecture well as it can work on the intensity rankings only and concludes that the simultaneous sensing and classification obtainable with theIRIS sensor yields both fast and processing‐efficient classification.
- Facial Feature Extraction using Eigenspaces and Deformable Graphs3
In model-based coding of image sequences containing human faces, eg videophone sequences, the detection and location of the face as well as the extraction of facial features from the images are crucial, and there are different approaches to reduce the high computational complexity.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Ground Target Recognition in a Query-Based Multi-Sensor Information System2
A system covering the complete process for automatic ground target recognition, from sensor data to the user interface, i.e., from low level image processing to high level situation anal recognition, is presented.
- ACTIVE APPEARANCE MODEL SEARCH WITH MOTION COMPENSATION FOR 3D FACE TRACKING2
Two different feature-based schemes for global motion compensation have been proposed and integrated into the search algorithm for face and facial feature tracking and the robustness and stability can be considerably improved with the inclusion of the proposed motion compensation schemes.
- 2
- Visual Spectrum Image Generation fromThermal Infrared1
This work addresses short-term, single-object tracking, a topic that is currently seeing fast progress for visual video, for the case of thermal infrared (TIR) imagery.
- 1
- Object Tracking in Thermal Infrared Imagery based on Channel Coded Distribution Fields1
This work addresses short-term, single-object tracking, a topic that is currently seeing fast progress for visual video, for the case of thermal infrared (TIR) imagery.
- 1
- An information measure of sensor performance and its relation to the ROC curve1
This work relates the proposed information theoretic method for measuring sensor performance to the ROC curve, shows that it is equivalent to selecting a certain point on the R OC curve, and that this point is easily determined, and studies hyperspectral data, studying discrimination between single pixels.
- 1
- A new hyperspectral dataset and some challenges1
A new hyperspectral data set that FOI will keep publicly available is presented, primarily in anomaly detection of man-made objects placed in nature where no such objects are expected.
- Surveillance Systems for Urban Crisis Management1
This work presents a concept for combing 3D models and multiple heterogeneous sensors into a surveillance system enabling superior situation awareness and has many military as well as civilian app users.
- Face and Facial Feature Tracking1
It is concluded that a real-time model-based coder running on consumer hardware is possible to implement this approach to tracking a face and its facial features in an input video sequence using the Active Appearance Algorithm.
- Let Me Take a Better Look: Towards Video-Based Age Estimation–
A video-specific age estimation method that leverages pseudo-labeling and semi-supervised learning and outperforms image-based baselines on both offline and online benchmark protocols, while the online estimation stability is improved by more than 50%.
- –
- –
- Visualization Techniques for Surveillance: Visualizing What Cannot Be Seen and Hiding What Should Not Be Seen–
An introduction to some of the problems of modern camera surveillance, and how these problems are, or can be, addressed using visualization techniques.
- –
- Facial Action Tracking–
This chapter explains the basics of parametric face models used for face and facial action tracking as well as fundamental strategies and methodologies for tracking.
- –
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 2026-10-15. 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.