Maria Elena Meza-de-Luna, Juan Ramon Terven Salinas, Bogdan Raducanu, & Joaquin Salas. (2019). A Social-Aware Assistant to support individuals with visual impairments during social interaction: A systematic requirements analysis. IJHC - International Journal of Human-Computer Studies, 122, 50–60.
Abstract: Visual impairment affects the normal course of activities in everyday life including mobility, education, employment, and social interaction. Most of the existing technical solutions devoted to empowering the visually impaired people are in the areas of navigation (obstacle avoidance), access to printed information and object recognition. Less effort has been dedicated so far in developing solutions to support social interactions. In this paper, we introduce a Social-Aware Assistant (SAA) that provides visually impaired people with cues to enhance their face-to-face conversations. The system consists of a perceptive component (represented by smartglasses with an embedded video camera) and a feedback component (represented by a haptic belt). When the vision system detects a head nodding, the belt vibrates, thus suggesting the user to replicate (mirror) the gesture. In our experiments, sighted persons interacted with blind people wearing the SAA. We instructed the former to mirror the noddings according to the vibratory signal, while the latter interacted naturally. After the face-to-face conversation, the participants had an interview to express their experience regarding the use of this new technological assistant. With the data collected during the experiment, we have assessed quantitatively and qualitatively the device usefulness and user satisfaction.
|
Marc Bolaños, Mariella Dimiccoli, & Petia Radeva. (2017). Towards Storytelling from Visual Lifelogging: An Overview. THMS - IEEE Transactions on Human-Machine Systems, 47(1), 77–90.
Abstract: Visual lifelogging consists of acquiring images that capture the daily experiences of the user by wearing a camera over a long period of time. The pictures taken offer considerable potential for knowledge mining concerning how people live their lives, hence, they open up new opportunities for many potential applications in fields including healthcare, security, leisure and
the quantified self. However, automatically building a story from a huge collection of unstructured egocentric data presents major challenges. This paper provides a thorough review of advances made so far in egocentric data analysis, and in view of the current state of the art, indicates new lines of research to move us towards storytelling from visual lifelogging.
|
R. de Nijs, Sebastian Ramos, Gemma Roig, Xavier Boix, Luc Van Gool, & K. Kühnlenz. (2012). On-line Semantic Perception Using Uncertainty. In International Conference on Intelligent Robots and Systems (pp. 4185–4191).
Abstract: Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not beaccurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental requirement for proper high level decision making in a robotic system. Yet, the uncertainty measure is often sacrificed to account for dependencies between object/region classifiers. This is the case of Conditional Random Fields (CRFs), the success of which stems from their ability to infer the most likely world configuration, but they do not directly allow to estimate the uncertainty of the solution. In this paper, we consider the setting of assigning semantic labels to the pixels of an image sequence. Instead of using a CRF, we employ a Perturb-and-MAP Random Field, a recently introduced probabilistic model that allows performing fast approximate sampling from its probability density function. This allows to effectively compute the uncertainty of the solution, indicating the reliability of the most likely labeling in each region of the image. We report results on the CamVid dataset, a standard benchmark for semantic labeling of urban image sequences. In our experiments, we show the benefits of exploiting the uncertainty by putting more computational effort on the regions of the image that are less reliable, and use more efficient techniques for other regions, showing little decrease of performance
Keywords: Semantic Segmentation
|
Ruben Perez Tito. (2023). Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents (Ernest Valveny, Ed.). Ph.D. thesis, IMPRIMA, .
Abstract: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.
|
Ivet Rafegas. (2017). Color in Visual Recognition: from flat to deep representations and some biological parallelisms (Maria Vanrell, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Visual recognition is one of the main problems in computer vision that attempts to solve image understanding by deciding what objects are in images. This problem can be computationally solved by using relevant sets of visual features, such as edges, corners, color or more complex object parts. This thesis contributes to how color features have to be represented for recognition tasks.
Image features can be extracted following two different approaches. A first approach is defining handcrafted descriptors of images which is then followed by a learning scheme to classify the content (named flat schemes in Kruger et al. (2013). In this approach, perceptual considerations are habitually used to define efficient color features. Here we propose a new flat color descriptor based on the extension of color channels to boost the representation of spatio-chromatic contrast that surpasses state-of-the-art approaches. However, flat schemes present a lack of generality far away from the capabilities of biological systems. A second approach proposes evolving these flat schemes into a hierarchical process, like in the visual cortex. This includes an automatic process to learn optimal features. These deep schemes, and more specifically Convolutional Neural Networks (CNNs), have shown an impressive performance to solve various vision problems. However, there is a lack of understanding about the internal representation obtained, as a result of automatic learning. In this thesis we propose a new methodology to explore the internal representation of trained CNNs by defining the Neuron Feature as a visualization of the intrinsic features encoded in each individual neuron. Additionally, and inspired by physiological techniques, we propose to compute different neuron selectivity indexes (e.g., color, class, orientation or symmetry, amongst others) to label and classify the full CNN neuron population to understand learned representations.
Finally, using the proposed methodology, we show an in-depth study on how color is represented on a specific CNN, trained for object recognition, that competes with primate representational abilities (Cadieu et al (2014)). We found several parallelisms with biological visual systems: (a) a significant number of color selectivity neurons throughout all the layers; (b) an opponent and low frequency representation of color oriented edges and a higher sampling of frequency selectivity in brightness than in color in 1st layer like in V1; (c) a higher sampling of color hue in the second layer aligned to observed hue maps in V2; (d) a strong color and shape entanglement in all layers from basic features in shallower layers (V1 and V2) to object and background shapes in deeper layers (V4 and IT); and (e) a strong correlation between neuron color selectivities and color dataset bias.
|
M. Danelljan, Fahad Shahbaz Khan, Michael Felsberg, & Joost Van de Weijer. (2014). Adaptive color attributes for real-time visual tracking. In 27th IEEE Conference on Computer Vision and Pattern Recognition (pp. 1090–1097).
Abstract: Visual tracking is a challenging problem in computer vision. Most state-of-the-art visual trackers either rely on luminance information or use simple color representations for image description. Contrary to visual tracking, for object
recognition and detection, sophisticated color features when combined with luminance have shown to provide excellent performance. Due to the complexity of the tracking problem, the desired color feature should be computationally
efficient, and possess a certain amount of photometric invariance while maintaining high discriminative power.
This paper investigates the contribution of color in a tracking-by-detection framework. Our results suggest that color attributes provides superior performance for visual tracking. We further propose an adaptive low-dimensional
variant of color attributes. Both quantitative and attributebased evaluations are performed on 41 challenging benchmark color sequences. The proposed approach improves the baseline intensity-based tracker by 24% in median distance precision. Furthermore, we show that our approach outperforms
state-of-the-art tracking methods while running at more than 100 frames per second.
|
Jose Seabra, Francesco Ciompi, Oriol Pujol, J. Mauri, Petia Radeva, & Joao Sanchez. (2011). Rayleigh Mixture Model for Plaque Characterization in Intravascular Ultrasound. TBME - IEEE Transactions on Biomedical Engineering, 58(5), 1314–1324.
Abstract: Vulnerable plaques are the major cause of carotid and coronary vascular problems, such as heart attack or stroke. A correct modeling of plaque echomorphology and composition can help the identification of such lesions. The Rayleigh distribution is widely used to describe (nearly) homogeneous areas in ultrasound images. Since plaques may contain tissues with heterogeneous regions, more complex distributions depending on multiple parameters are usually needed, such as Rice, K or Nakagami distributions. In such cases, the problem formulation becomes more complex, and the optimization procedure to estimate the plaque echomorphology is more difficult. Here, we propose to model the tissue echomorphology by means of a mixture of Rayleigh distributions, known as the Rayleigh mixture model (RMM). The problem formulation is still simple, but its ability to describe complex textural patterns is very powerful. In this paper, we present a method for the automatic estimation of the RMM mixture parameters by means of the expectation maximization algorithm, which aims at characterizing tissue echomorphology in ultrasound (US). The performance of the proposed model is evaluated with a database of in vitro intravascular US cases. We show that the mixture coefficients and Rayleigh parameters explicitly derived from the mixture model are able to accurately describe different plaque types and to significantly improve the characterization performance of an already existing methodology.
|
Lluis Pere de las Heras, David Fernandez, Ernest Valveny, Josep Llados, & Gemma Sanchez. (2013). Unsupervised wall detector in architectural floor plan. In 12th International Conference on Document Analysis and Recognition (pp. 1245–1249).
Abstract: Wall detection in floor plans is a crucial step in a complete floor plan recognition system. Walls define the main structure of buildings and convey essential information for the detection of other structural elements. Nevertheless, wall segmentation is a difficult task, mainly because of the lack of a standard graphical notation. The existing approaches are restricted to small group of similar notations or require the existence of pre-annotated corpus of input images to learn each new notation. In this paper we present an automatic wall segmentation system, with the ability to handle completely different notations without the need of any annotated dataset. It only takes advantage of the general knowledge that walls are a repetitive element, naturally distributed within the plan and commonly modeled by straight parallel lines. The method has been tested on four datasets of real floor plans with different notations, and compared with the state-of-the-art. The results show its suitability for different graphical notations, achieving higher recall rates than the rest of the methods while keeping a high average precision.
|
Baiyu Chen, Sergio Escalera, Isabelle Guyon, Victor Ponce, N. Shah, & Marc Oliu. (2016). Overcoming Calibration Problems in Pattern Labeling with Pairwise Ratings: Application to Personality Traits. In 14th European Conference on Computer Vision Workshops.
Abstract: We address the problem of calibration of workers whose task is to label patterns with continuous variables, which arises for instance in labeling images of videos of humans with continuous traits. Worker bias is particularly dicult to evaluate and correct when many workers contribute just a few labels, a situation arising typically when labeling is crowd-sourced. In the scenario of labeling short videos of people facing a camera with personality traits, we evaluate the feasibility of the pairwise ranking method to alleviate bias problems. Workers are exposed to pairs of videos at a time and must order by preference. The variable levels are reconstructed by fitting a Bradley-Terry-Luce model with maximum likelihood. This method may at first sight, seem prohibitively expensive because for N videos, p = N (N-1)/2 pairs must be potentially processed by workers rather that N videos. However, by performing extensive simulations, we determine an empirical law for the scaling of the number of pairs needed as a function of the number of videos in order to achieve a given accuracy of score reconstruction and show that the pairwise method is a ordable. We apply the method to the labeling of a large scale dataset of 10,000 videos used in the ChaLearn Apparent Personality Trait challenge.
Keywords: Calibration of labels; Label bias; Ordinal labeling; Variance Models; Bradley-Terry-Luce model; Continuous labels; Regression; Personality traits; Crowd-sourced labels
|
Adria Ruiz, Joost Van de Weijer, & Xavier Binefa. (2014). Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization. In 25th British Machine Vision Conference.
Abstract: We address the problem of estimating high-level semantic labels for videos of recorded people by means of analysing their facial expressions. This problem, to which we refer as facial behavior categorization, is a weakly-supervised learning problem where we do not have access to frame-by-frame facial gesture annotations but only weak-labels at the video level are available. Therefore, the goal is to learn a set of discriminative expressions and how they determine the video weak-labels. Facial behavior categorization can be posed as a Multi-Instance-Learning (MIL) problem and we propose a novel MIL method called Regularized Multi-Concept MIL to solve it. In contrast to previous approaches applied in facial behavior analysis, RMC-MIL follows a Multi-Concept assumption which allows different facial expressions (concepts) to contribute differently to the video-label. Moreover, to handle with the high-dimensional nature of facial-descriptors, RMC-MIL uses a discriminative approach to model the concepts and structured sparsity regularization to discard non-informative features. RMC-MIL is posed as a convex-constrained optimization problem where all the parameters are jointly learned using the Projected-Quasi-Newton method. In our experiments, we use two public data-sets to show the advantages of the Regularized Multi-Concept approach and its improvement compared to existing MIL methods. RMC-MIL outperforms state-of-the-art results in the UNBC data-set for pain detection.
|
Yaxing Wang, Joost Van de Weijer, & Luis Herranz. (2018). Mix and match networks: encoder-decoder alignment for zero-pair image translation. In 31st IEEE Conference on Computer Vision and Pattern Recognition (pp. 5467–5476).
Abstract: We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform unseen image translation tasks between domains or modalities for which explicit paired samples were not seen during training. We study the impact of autoencoders, side information and losses in improving the alignment and transferability of trained pairwise translation models to unseen translations. We show our approach is scalable and can perform colorization and style transfer between unseen combinations of domains. We evaluate our system in a challenging cross-modal setting where semantic segmentation is estimated from depth images, without explicit access to any depth-semantic segmentation training pairs. Our model outperforms baselines based on pix2pix and CycleGAN models.
|
Shiqi Yang, Yaxing Wang, Luis Herranz, Shangling Jui, & Joost Van de Weijer. (2023). Casting a BAIT for offline and online source-free domain adaptation. CVIU - Computer Vision and Image Understanding, 234, 103747.
Abstract: We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be visited multiple times (epochs) to arrive at a prediction for each target sample, and the online setting where the target data needs to be directly classified upon arrival. Inspired by diverse classifier based domain adaptation methods, in this paper we introduce a second classifier, but with another classifier head fixed. When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features. Next, when updating the feature extractor, those features will be pushed towards the right side of the source decision boundary, thus achieving source-free domain adaptation. Experimental results show that the proposed method achieves competitive results for offline SFDA on several benchmark datasets compared with existing DA and SFDA methods, and our method surpasses by a large margin other SFDA methods under online source-free domain adaptation setting.
|
Jürgen Brauer, Wenjuan Gong, Jordi Gonzalez, & Michael Arens. (2011). On the Effect of Temporal Information on Monocular 3D Human Pose Estimation. In 2nd IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (pp. 906–913).
Abstract: We address the task of estimating 3D human poses from monocular camera sequences. Many works make use of multiple consecutive frames for the estimation of a 3D pose in a frame. Although such an approach should ease the pose estimation task substantially since multiple consecutive frames allow to solve for 2D projection ambiguities in principle, it has not yet been investigated systematically how much we can improve the 3D pose estimates when using multiple consecutive frames opposed to single frame information. In this paper we analyze the difference in quality of 3D pose estimates based on different numbers of consecutive frames from which 2D pose estimates are available. We validate the use of temporal information on two major different approaches for human pose estimation – modeling and learning approaches. The results of our experiments show that both learning and modeling approaches benefit from using multiple frames opposed to single frame input but that the benefit is small when the 2D pose estimates show a high quality in terms of precision.
|
Carlo Gatta, & Francesco Ciompi. (2014). Stacked Sequential Scale-Space Taylor Context. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1694–1700.
Abstract: We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 data sets.
|
Onur Ferhat, & Fernando Vilariño. (2013). A Cheap Portable Eye-Tracker Solution for Common Setups. In 17th European Conference on Eye Movements.
Abstract: We analyze the feasibility of a cheap eye-tracker where the hardware consists of a single webcam and a Raspberry Pi device. Our aim is to discover the limits of such a system and to see whether it provides an acceptable performance. We base our work on the open source Opengazer (Zielinski, 2013) and we propose several improvements to create a robust, real-time system. After assessing the accuracy of our eye-tracker in elaborated experiments involving 18 subjects under 4 different system setups, we developed a simple game to see how it performs in practice and we also installed it on a Raspberry Pi to create a portable stand-alone eye-tracker which achieves 1.62° horizontal accuracy with 3 fps refresh rate for a building cost of 70 Euros.
Keywords: Low cost; eye-tracker; software; webcam; Raspberry Pi
|
