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
|
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.
|
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.
|
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.
|
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
|
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
|
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.
|
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.
|
Antonio Clavelli, Dimosthenis Karatzas, Josep Llados, Mario Ferraro, & Giuseppe Boccignone. (2014). Modelling task-dependent eye guidance to objects in pictures. CoCom - Cognitive Computation, 6(3), 558–584.
Abstract: 5Y Impact Factor: 1.14 / 3rd (Computer Science, Artificial Intelligence)
We introduce a model of attentional eye guidance based on the rationale that the deployment of gaze is to be considered in the context of a general action-perception loop relying on two strictly intertwined processes: sensory processing, depending on current gaze position, identifies sources of information that are most valuable under the given task; motor processing links such information with the oculomotor act by sampling the next gaze position and thus performing the gaze shift. In such a 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 payoff of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. The different levels of the action-perception loop are represented in probabilistic form and eventually give rise to a stochastic process that generates the gaze sequence. This way the model also accounts for statistical properties of gaze shifts such as individual scan path variability. Results of the simulations are compared either with experimental data derived from publicly available datasets and from our own experiments.
Keywords: Visual attention; Gaze guidance; Value; Payoff; Stochastic fixation prediction
|
Antonio Clavelli, Dimosthenis Karatzas, Josep Llados, Mario Ferraro, & Giuseppe Boccignone. (2013). Towards Modelling an Attention-Based Text Localization Process. In 6th Iberian Conference on Pattern Recognition and Image Analysis (Vol. 7887, pp. 296–303). LNCS. Springer Berlin Heidelberg.
Abstract: This note introduces a visual attention model of text localization in real-world scenes. The core of the model built upon the proto-object concept is discussed. It is shown how such dynamic mid-level representation of the scene can be derived in the framework of an action-perception loop engaging salience, text information value computation, and eye guidance mechanisms.
Preliminary results that compare model generated scanpaths with those eye-tracked from human subjects are presented.
Keywords: text localization; visual attention; eye guidance
|
Albert Clapes, Julio C. S. Jacques Junior, Carla Morral, & Sergio Escalera. (2020). ChaLearn LAP 2020 Challenge on Identity-preserved Human Detection: Dataset and Results. In 15th IEEE International Conference on Automatic Face and Gesture Recognition (pp. 801–808).
Abstract: This paper summarizes the ChaLearn Looking at People 2020 Challenge on Identity-preserved Human Detection (IPHD). For the purpose, we released a large novel dataset containing more than 112K pairs of spatiotemporally aligned depth and thermal frames (and 175K instances of humans) sampled from 780 sequences. The sequences contain hundreds of non-identifiable people appearing in a mix of in-the-wild and scripted scenarios recorded in public and private places. The competition was divided into three tracks depending on the modalities exploited for the detection: (1) depth, (2) thermal, and (3) depth-thermal fusion. Color was also captured but only used to facilitate the groundtruth annotation. Still the temporal synchronization of three sensory devices is challenging, so bad temporal matches across modalities can occur. Hence, the labels provided should considered “weak”, although test frames were carefully selected to minimize this effect and ensure the fairest comparison of the participants’ results. Despite this added difficulty, the results got by the participants demonstrate current fully-supervised methods can deal with that and achieve outstanding detection performance when measured in terms of AP@0.50.
|
Nuria Cirera. (2012). Recognition of Handwritten Historical Documents (Vol. 174). Master's thesis, , .
|
Francesco Ciompi. (2012). Multi-Class Learning for Vessel Characterization in Intravascular Ultrasound (Petia Radeva, & Oriol Pujol, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: In this thesis we tackle the problem of automatic characterization of human coronary vessel in Intravascular Ultrasound (IVUS) image modality. The basis for the whole characterization process is machine learning applied to multi-class problems. In all the presented approaches, the Error-Correcting Output Codes (ECOC) framework is used as central element for the design of multi-class classifiers.
Two main topics are tackled in this thesis. First, the automatic detection of the vessel borders is presented. For this purpose, a novel context-aware classifier for multi-class classification of the vessel morphology is presented, namely ECOC-DRF. Based on ECOC-DRF, the lumen border and the media-adventitia border in IVUS are robustly detected by means of a novel holistic approach, achieving an error comparable with inter-observer variability and with state of the art methods.
The two vessel borders define the atheroma area of the vessel. In this area, tissue characterization is required. For this purpose, we present a framework for automatic plaque characterization by processing both texture in IVUS images and spectral information in raw Radio Frequency data. Furthermore, a novel method for fusing in-vivo and in-vitro IVUS data for plaque characterization is presented, namely pSFFS. The method demonstrates to effectively fuse data generating a classifier that improves the tissue characterization in both in-vitro and in-vivo datasets.
A novel method for automatic video summarization in IVUS sequences is also presented. The method aims to detect the key frames of the sequence, i.e., the frames representative of morphological changes. This novel method represents the basis for video summarization in IVUS as well as the markers for the partition of the vessel into morphological and clinically interesting events.
Finally, multi-class learning based on ECOC is applied to lung tissue characterization in Computed Tomography. The novel proposed approach, based on supervised and unsupervised learning, achieves accurate tissue classification on a large and heterogeneous dataset.
|
Francesco Ciompi. (2008). ECOC-based Plaque Classification using In-vivo and Exvivo Intravascular Ultrasound Data.
|
Bhaskar Chakraborty, Michael Holte, Thomas B. Moeslund, & Jordi Gonzalez. (2012). Selective Spatio-Temporal Interest Points. CVIU - Computer Vision and Image Understanding, 116(3), 396–410.
Abstract: Recent progress in the field of human action recognition points towards the use of Spatio-TemporalInterestPoints (STIPs) for local descriptor-based recognition strategies. In this paper, we present a novel approach for robust and selective STIP detection, by applying surround suppression combined with local and temporal constraints. This new method is significantly different from existing STIP detection techniques and improves the performance by detecting more repeatable, stable and distinctive STIPs for human actors, while suppressing unwanted background STIPs. For action representation we use a bag-of-video words (BoV) model of local N-jet features to build a vocabulary of visual-words. To this end, we introduce a novel vocabulary building strategy by combining spatial pyramid and vocabulary compression techniques, resulting in improved performance and efficiency. Action class specific Support Vector Machine (SVM) classifiers are trained for categorization of human actions. A comprehensive set of experiments on popular benchmark datasets (KTH and Weizmann), more challenging datasets of complex scenes with background clutter and camera motion (CVC and CMU), movie and YouTube video clips (Hollywood 2 and YouTube), and complex scenes with multiple actors (MSR I and Multi-KTH), validates our approach and show state-of-the-art performance. Due to the unavailability of ground truth action annotation data for the Multi-KTH dataset, we introduce an actor specific spatio-temporal clustering of STIPs to address the problem of automatic action annotation of multiple simultaneous actors. Additionally, we perform cross-data action recognition by training on source datasets (KTH and Weizmann) and testing on completely different and more challenging target datasets (CVC, CMU, MSR I and Multi-KTH). This documents the robustness of our proposed approach in the realistic scenario, using separate training and test datasets, which in general has been a shortcoming in the performance evaluation of human action recognition techniques.
|