Antonio Clavelli. (2014). A computational model of eye guidance, searching for text in real scene images (Dimosthenis Karatzas, Giuseppe Boccignone, & Josep Llados, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Searching for text objects in real scene images is an open problem and a very active computer vision research area. A large number of methods have been proposed tackling the text search as extension of the ones from the document analysis field or inspired by general purpose object detection methods. However the general problem of object search in real scene images remains an extremely challenging problem due to the huge variability in object appearance. This thesis builds on top of the most recent findings in the visual attention literature presenting a novel computational model of eye guidance aiming to better describe text object search in real scene images.
First are presented the relevant state-of-the-art results from the visual attention literature regarding eye movements and visual search. Relevant models of attention are discussed and integrated with recent observations on the role of top-down constraints and the emerging need for a layered model of attention in which saliency is not the only factor guiding attention. Visual attention is then explained by the interaction of several modulating factors, such as objects, value, plans and saliency. Then we introduce our probabilistic formulation of attention deployment in real scene. The model is based on the rationale that oculomotor control depends on two interacting but distinct processes: an attentional process that assigns value to the sources of information and motor process that flexibly links information with action.
In such framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the reward of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects.
In the experimental section the model is tested in laboratory condition, comparing model simulations with data from eye tracking experiments. The comparison is qualitative in terms of observable scan paths and quantitative in terms of statistical similarity of gaze shift amplitude. Experiments are performed using eye tracking data from both a publicly available dataset of face and text and from newly performed eye-tracking experiments on a dataset of street view pictures containing text. The last part of this thesis is dedicated to study the extent to which the proposed model can account for human eye movements in a low constrained setting. We used a mobile eye tracking device and an ad-hoc developed methodology to compare model simulated eye data with the human eye data from mobile eye tracking recordings. Such setting allow to test the model in an incomplete visual information condition, reproducing a close to real-life search task.
|
Albert Clapes. (2019). Learning to recognize human actions: from hand-crafted to deep-learning based visual representations (Sergio Escalera, Ed.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Action recognition is a very challenging and important problem in computer vision. Researchers working on this field aspire to provide computers with the abil ity to visually perceive human actions – that is, to observe, interpret, and under stand human-related events that occur in the physical environment merely from visual data. The applications of this technology are numerous: human-machine interaction, e-health, monitoring/surveillance, and content-based video retrieval, among others. Hand-crafted methods dominated the field until the apparition of the first successful deep learning-based action recognition works. Although ear lier deep-based methods underperformed with respect to hand-crafted approaches, these slowly but steadily improved to become state-of-the-art, eventually achieving better results than hand-crafted ones. Still, hand-crafted approaches can be advan tageous in certain scenarios, specially when not enough data is available to train very large deep models or simply to be combined with deep-based methods to fur ther boost the performance. Hence, showing how hand-crafted features can provide extra knowledge the deep networks are notable to easily learn about human actions.
This Thesis concurs in time with this change of paradigm and, hence, reflects it into two distinguished parts. In the first part, we focus on improving current suc cessful hand-crafted approaches for action recognition and we do so from three dif ferent perspectives. Using the dense trajectories framework as a backbone: first, we explore the use of multi-modal and multi-view input
data to enrich the trajectory de scriptors. Second, we focus on the classification part of action recognition pipelines and propose an ensemble learning approach, where each classifier leams from a different set of local spatiotemporal features to then combine their outputs following an strategy based on the Dempster-Shaffer Theory. And third, we propose a novel hand-crafted feature extraction method that constructs a rnid-level feature descrip tion to better modellong-term spatiotemporal dynarnics within action videos. Moving to the second part of the Thesis, we start with a comprehensive study of the current deep-learning based action recognition methods. We review both fun damental and cutting edge methodologies reported during the last few years and introduce a taxonomy of deep-leaming methods dedicated to action recognition. In particular, we analyze and discuss how these handle
the temporal dimension of data. Last but not least, we propose a residual recurrent network for action recogni tion that naturally integrates all our previous findings in a powerful and prornising framework.
|
Esteve Cervantes, Long Long Yu, Andrew Bagdanov, Marc Masana, & Joost Van de Weijer. (2016). Hierarchical Part Detection with Deep Neural Networks. In 23rd IEEE International Conference on Image Processing.
Abstract: Part detection is an important aspect of object recognition. Most approaches apply object proposals to generate hundreds of possible part bounding box candidates which are then evaluated by part classifiers. Recently several methods have investigated directly regressing to a limited set of bounding boxes from deep neural network representation. However, for object parts such methods may be unfeasible due to their relatively small size with respect to the image. We propose a hierarchical method for object and part detection. In a single network we first detect the object and then regress to part location proposals based only on the feature representation inside the object. Experiments show that our hierarchical approach outperforms a network which directly regresses the part locations. We also show that our approach obtains part detection accuracy comparable or better than state-of-the-art on the CUB-200 bird and Fashionista clothing item datasets with only a fraction of the number of part proposals.
Keywords: Object Recognition; Part Detection; Convolutional Neural Networks
|
Felipe Codevilla, Antonio Lopez, Vladlen Koltun, & Alexey Dosovitskiy. (2018). On Offline Evaluation of Vision-based Driving Models. In 15th European Conference on Computer Vision (Vol. 11219, pp. 246–262). LNCS.
Abstract: Autonomous driving models should ideally be evaluated by deploying
them on a fleet of physical vehicles in the real world. Unfortunately, this approach is not practical for the vast majority of researchers. An attractive alternative is to evaluate models offline, on a pre-collected validation dataset with ground truth annotation. In this paper, we investigate the relation between various online and offline metrics for evaluation of autonomous driving models. We find that offline prediction error is not necessarily correlated with driving quality, and two models with identical prediction error can differ dramatically in their driving performance. We show that the correlation of offline evaluation with driving quality can be significantly improved by selecting an appropriate validation dataset and
suitable offline metrics.
Keywords: Autonomous driving; deep learning
|
Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, & Mariella Dimiccoli. (2019). How Much Does Audio Matter to Recognize Egocentric Object Interactions?.
Abstract: CoRR abs/1906.00634
Sounds are an important source of information on our daily interactions with objects. For instance, a significant amount of people can discern the temperature of water that it is being poured just by using the sense of hearing. However, only a few works have explored the use of audio for the classification of object interactions in conjunction with vision or as single modality. In this preliminary work, we propose an audio model for egocentric action recognition and explore its usefulness on the parts of the problem (noun, verb, and action classification). Our model achieves a competitive result in terms of verb classification (34.26% accuracy) on a standard benchmark with respect to vision-based state of the art systems, using a comparatively lighter architecture.
|
Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, & Mariella Dimiccoli. (2019). Seeing and Hearing Egocentric Actions: How Much Can We Learn? In IEEE International Conference on Computer Vision Workshops (pp. 4470–4480).
Abstract: Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have considered to integrate the visual and audio modalities for this purpose. In this work, we propose a multimodal approach for egocentric action recognition in a kitchen environment that relies on audio and visual information. Our model combines a sparse temporal sampling strategy with a late fusion of audio, spatial, and temporal streams. Experimental results on the EPIC-Kitchens dataset show that multimodal integration leads to better performance than unimodal approaches. In particular, we achieved a 5.18% improvement over the state of the art on verb classification.
|
Chee-Kheng Chng, Yuliang Liu, Yipeng Sun, Chun Chet Ng, Canjie Luo, Zihan Ni, et al. (2019). ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT. In 15th International Conference on Document Analysis and Recognition (pp. 1571–1576).
Abstract: This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT that consists of three major challenges: i) scene text detection, ii) scene text recognition, and iii) scene text spotting. A total of 78 submissions from 46 unique teams/individuals were received for this competition. The top performing score of each challenge is as follows: i) T1 – 82.65%, ii) T2.1 – 74.3%, iii) T2.2 – 85.32%, iv) T3.1 – 53.86%, and v) T3.2 – 54.91%. Apart from the results, this paper also details the ArT dataset, tasks description, evaluation metrics and participants' methods. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.
|
Ciprian Corneanu, Meysam Madadi, & Sergio Escalera. (2018). Deep Structure Inference Network for Facial Action Unit Recognition. In 15th European Conference on Computer Vision (Vol. 11216, pp. 309–324). LNCS.
Abstract: Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Recently, efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between AUs. We propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
Keywords: Computer Vision; Machine Learning; Deep Learning; Facial Expression Analysis; Facial Action Units; Structure Inference
|
Ciprian Corneanu, Meysam Madadi, Sergio Escalera, & Aleix M. Martinez. (2019). What does it mean to learn in deep networks? And, how does one detect adversarial attacks? In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 4752–4761).
Abstract: The flexibility and high-accuracy of Deep Neural Networks (DNNs) has transformed computer vision. But, the fact that we do not know when a specific DNN will work and when it will fail has resulted in a lack of trust. A clear example is self-driving cars; people are uncomfortable sitting in a car driven by algorithms that may fail under some unknown, unpredictable conditions. Interpretability and explainability approaches attempt to address this by uncovering what a DNN models, i.e., what each node (cell) in the network represents and what images are most likely to activate it. This can be used to generate, for example, adversarial attacks. But these approaches do not generally allow us to determine where a DNN will succeed or fail and why. i.e., does this learned representation generalize to unseen samples? Here, we derive a novel approach to define what it means to learn in deep networks, and how to use this knowledge to detect adversarial attacks. We show how this defines the ability of a network to generalize to unseen testing samples and, most importantly, why this is the case.
|
Ciprian Corneanu, Meysam Madadi, Sergio Escalera, & Aleix Martinez. (2020). Explainable Early Stopping for Action Unit Recognition. In Faces and Gestures in E-health and welfare workshop (pp. 693–699).
Abstract: A common technique to avoid overfitting when training deep neural networks (DNN) is to monitor the performance in a dedicated validation data partition and to stop
training as soon as it saturates. This only focuses on what the model does, while completely ignoring what happens inside it.
In this work, we open the “black-box” of DNN in order to perform early stopping. We propose to use a novel theoretical framework that analyses meso-scale patterns in the topology of the functional graph of a network while it trains. Based on it,
we decide when it transitions from learning towards overfitting in a more explainable way. We exemplify the benefits of this approach on a state-of-the art custom DNN that jointly learns local representations and label structure employing an ensemble of dedicated subnetworks. We show that it is practically equivalent in performance to early stopping with patience, the standard early stopping algorithm in the literature. This proves beneficial for AU recognition performance and provides new insights into how learning of AUs occurs in DNNs.
|
Victor M. Campello, Carlos Martin-Isla, Cristian Izquierdo, Andrea Guala, Jose F. Rodriguez Palomares, David Vilades, et al. (2022). Minimising multi-centre radiomics variability through image normalisation: a pilot study. ScR - Scientific Reports, 12(1), 12532.
Abstract: Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise for deeper phenotyping of cardiovascular disease. Thus far, the technique has been mostly applied in single-centre studies. However, one of the main difficulties in multi-centre imaging studies is the inherent variability of image characteristics due to centre differences. In this paper, a comprehensive analysis of radiomics variability under several image- and feature-based normalisation techniques was conducted using a multi-centre cardiovascular magnetic resonance dataset. 218 subjects divided into healthy (n = 112) and hypertrophic cardiomyopathy (n = 106, HCM) groups from five different centres were considered. First and second order texture radiomic features were extracted from three regions of interest, namely the left and right ventricular cavities and the left ventricular myocardium. Two methods were used to assess features’ variability. First, feature distributions were compared across centres to obtain a distribution similarity index. Second, two classification tasks were proposed to assess: (1) the amount of centre-related information encoded in normalised features (centre identification) and (2) the generalisation ability for a classification model when trained on these features (healthy versus HCM classification). The results showed that the feature-based harmonisation technique ComBat is able to remove the variability introduced by centre information from radiomic features, at the expense of slightly degrading classification performance. Piecewise linear histogram matching normalisation gave features with greater generalisation ability for classification ( balanced accuracy in between 0.78 ± 0.08 and 0.79 ± 0.09). Models trained with features from images without normalisation showed the worst performance overall ( balanced accuracy in between 0.45 ± 0.28 and 0.60 ± 0.22). In conclusion, centre-related information removal did not imply good generalisation ability for classification.
|
Felipe Codevilla, Matthias Muller, Antonio Lopez, Vladlen Koltun, & Alexey Dosovitskiy. (2018). End-to-end Driving via Conditional Imitation Learning. In IEEE International Conference on Robotics and Automation (pp. 4693–4700).
Abstract: Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands. The supplementary video can be viewed at this https URL
|
|
R. Clariso, David Masip, & A. Rius. (2014). Student projects empowering mobile learning in higher education. RUSC - Revista de Universidad y Sociedad del Conocimiento, 192–207.
|
Alejandro Cartas, Juan Marin, Petia Radeva, & Mariella Dimiccoli. (2018). Batch-based activity recognition from egocentric photo-streams revisited. PAA - Pattern Analysis and Applications, 21(4), 953–965.
Abstract: Wearable cameras can gather large amounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health applications that could be enabled by the automatic recognition of daily activities, such as lifestyle characterization for habit improvement, context-aware personal assistance and tele-rehabilitation services, we propose a system to classify 21 daily activities from photo-streams acquired by a wearable photo-camera. Our approach combines the advantages of a late fusion ensemble strategy relying on convolutional neural networks at image level with the ability of recurrent neural networks to account for the temporal evolution of high-level features in photo-streams without relying on event boundaries. The proposed batch-based approach achieved an overall accuracy of 89.85%, outperforming state-of-the-art end-to-end methodologies. These results were achieved on a dataset consists of 44,902 egocentric pictures from three persons captured during 26 days in average.
Keywords: Egocentric vision; Lifelogging; Activity recognition; Deep learning; Recurrent neural networks
|
Manuel Carbonell, Joan Mas, Mauricio Villegas, Alicia Fornes, & Josep Llados. (2019). End-to-End Handwritten Text Detection and Transcription in Full Pages. In 2nd International Workshop on Machine Learning (Vol. 5, pp. 29–34).
Abstract: When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect
the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume
segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
Keywords: Handwritten Text Recognition; Layout Analysis; Text segmentation; Deep Neural Networks; Multi-task learning
|
