|
|
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.
|
|
|
|
Benjia Zhou, Zhigang Chen, Albert Clapes, Jun Wan, Yanyan Liang, Sergio Escalera, et al. (2023). Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining. In IEEE/CVF International Conference on Computer Vision (ICCV) Workshops.
Abstract: Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a two-stage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training (CLIP) with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (>+5) and the CSL-Daily dataset (>+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods.
|
|
|
|
Raquel Justo, Leila Ben Letaifa, Cristina Palmero, Eduardo Gonzalez-Fraile, Anna Torp Johansen, Alain Vazquez, et al. (2020). Analysis of the Interaction between Elderly People and a Simulated Virtual Coach, Journal of Ambient Intelligence and Humanized Computing. AIHC - Journal of Ambient Intelligence and Humanized Computing, 11(12), 6125–6140.
Abstract: The EMPATHIC project develops and validates new interaction paradigms for personalized virtual coaches (VC) to promote healthy and independent aging. To this end, the work presented in this paper is aimed to analyze the interaction between the EMPATHIC-VC and the users. One of the goals of the project is to ensure an end-user driven design, involving senior users from the beginning and during each phase of the project. Thus, the paper focuses on some sessions where the seniors carried out interactions with a Wizard of Oz driven, simulated system. A coaching strategy based on the GROW model was used throughout these sessions so as to guide interactions and engage the elderly with the goals of the project. In this interaction framework, both the human and the system behavior were analyzed. The way the wizard implements the GROW coaching strategy is a key aspect of the system behavior during the interaction. The language used by the virtual agent as well as his or her physical aspect are also important cues that were analyzed. Regarding the user behavior, the vocal communication provides information about the speaker’s emotional status, that is closely related to human behavior and which can be extracted from the speech and language analysis. In the same way, the analysis of the facial expression, gazes and gestures can provide information on the non verbal human communication even when the user is not talking. In addition, in order to engage senior users, their preferences and likes had to be considered. To this end, the effect of the VC on the users was gathered by means of direct questionnaires. These analyses have shown a positive and calm behavior of users when interacting with the simulated virtual coach as well as some difficulties of the system to develop the proposed coaching strategy.
|
|
|
|
Albert Clapes, Miguel Reyes, & Sergio Escalera. (2013). Multi-modal User Identification and Object Recognition Surveillance System. PRL - Pattern Recognition Letters, 34(7), 799–808.
Abstract: We propose an automatic surveillance system for user identification and object recognition based on multi-modal RGB-Depth data analysis. We model a RGBD environment learning a pixel-based background Gaussian distribution. Then, user and object candidate regions are detected and recognized using robust statistical approaches. The system robustly recognizes users and updates the system in an online way, identifying and detecting new actors in the scene. Moreover, segmented objects are described, matched, recognized, and updated online using view-point 3D descriptions, being robust to partial occlusions and local 3D viewpoint rotations. Finally, the system saves the historic of user–object assignments, being specially useful for surveillance scenarios. The system has been evaluated on a novel data set containing different indoor/outdoor scenarios, objects, and users, showing accurate recognition and better performance than standard state-of-the-art approaches.
Keywords: Multi-modal RGB-Depth data analysis; User identification; Object recognition; Intelligent surveillance; Visual features; Statistical learning
|
|
|
|
S.Grau, Ana Puig, Sergio Escalera, & Maria Salamo. (2013). Intelligent Interactive Volume Classification. In Pacific Graphics (Vol. 32, pp. 23–28).
Abstract: This paper defines an intelligent and interactive framework to classify multiple regions of interest from the original data on demand, without requiring any preprocessing or previous segmentation. The proposed intelligent and interactive approach is divided in three stages: visualize, training and testing. First, users visualize and label some samples directly on slices of the volume. Training and testing are based on a framework of Error Correcting Output Codes and Adaboost classifiers that learn to classify each region the user has painted. Later, at the testing stage, each classifier is directly applied on the rest of samples and combined to perform multi-class labeling, being used in the final rendering. We also parallelized the training stage using a GPU-based implementation for
obtaining a rapid interaction and classification.
|
|
|
|
S.Grau, Anna Puig, Sergio Escalera, Maria Salamo, & Oscar Amoros. (2013). Efficient complementary viewpoint selection in volume rendering. In 21st WSCG Conference on Computer Graphics,.
Abstract: A major goal of visualization is to appropriately express knowledge of scientific data. Generally, gathering visual information contained in the volume data often requires a lot of expertise from the final user to setup the parameters of the visualization. One way of alleviating this problem is to provide the position of inner structures with different viewpoint locations to enhance the perception and construction of the mental image. To this end, traditional illustrations use two or three different views of the regions of interest. Similarly, with the aim of assisting the users to easily place a good viewpoint location, this paper proposes an automatic and interactive method that locates different complementary viewpoints from a reference camera in volume datasets. Specifically, the proposed method combines the quantity of information each camera provides for each structure and the shape similarity of the projections of the remaining viewpoints based on Dynamic Time Warping. The selected complementary viewpoints allow a better understanding of the focused structure in several applications. Thus, the user interactively receives feedback based on several viewpoints that helps him to understand the visual information. A live-user evaluation on different data sets show a good convergence to useful complementary viewpoints.
Keywords: Dual camera; Visualization; Interactive Interfaces; Dynamic Time Warping.
|
|
|
|
Meysam Madadi, Sergio Escalera, Alex Carruesco Llorens, Carlos Andujar, Xavier Baro, & Jordi Gonzalez. (2018). Top-down model fitting for hand pose recovery in sequences of depth images. IMAVIS - Image and Vision Computing, 79, 63–75.
Abstract: State-of-the-art approaches on hand pose estimation from depth images have reported promising results under quite controlled considerations. In this paper we propose a two-step pipeline for recovering the hand pose from a sequence of depth images. The pipeline has been designed to deal with images taken from any viewpoint and exhibiting a high degree of finger occlusion. In a first step we initialize the hand pose using a part-based model, fitting a set of hand components in the depth images. In a second step we consider temporal data and estimate the parameters of a trained bilinear model consisting of shape and trajectory bases. We evaluate our approach on a new created synthetic hand dataset along with NYU and MSRA real datasets. Results demonstrate that the proposed method outperforms the most recent pose recovering approaches, including those based on CNNs.
|
|
|
|
Yagmur Gucluturk, Umut Guclu, Marc Perez, Hugo Jair Escalante, Xavier Baro, Isabelle Guyon, et al. (2017). Visualizing Apparent Personality Analysis with Deep Residual Networks. In Chalearn Workshop on Action, Gesture, and Emotion Recognition: Large Scale Multimodal Gesture Recognition and Real versus Fake expressed emotions at ICCV (pp. 3101–3109).
Abstract: Automatic prediction of personality traits is a subjective task that has recently received much attention. Specifically, automatic apparent personality trait prediction from multimodal data has emerged as a hot topic within the filed of computer vision and, more particularly, the so called “looking
at people” sub-field. Considering “apparent” personality traits as opposed to real ones considerably reduces the subjectivity of the task. The real world applications are encountered in a wide range of domains, including entertainment, health, human computer interaction, recruitment and security. Predictive models of personality traits are useful for individuals in many scenarios (e.g., preparing for job interviews, preparing for public speaking). However, these predictions in and of themselves might be deemed to be untrustworthy without human understandable supportive evidence. Through a series of experiments on a recently released benchmark dataset for automatic apparent personality trait prediction, this paper characterizes the audio and
visual information that is used by a state-of-the-art model while making its predictions, so as to provide such supportive evidence by explaining predictions made. Additionally, the paper describes a new web application, which gives feedback on apparent personality traits of its users by combining
model predictions with their explanations.
|
|
|
|
Mohammad N. S. Jahromi, Morten Bojesen Bonderup, Maryam Asadi-Aghbolaghi, Egils Avots, Kamal Nasrollahi, Sergio Escalera, et al. (2018). Automatic Access Control Based on Face and Hand Biometrics in a Non-cooperative Context. In IEEE Winter Applications of Computer Vision Workshops (pp. 28–36).
Abstract: Automatic access control systems (ACS) based on the human biometrics or physical tokens are widely employed in public and private areas. Yet these systems, in their conventional forms, are restricted to active interaction from the users. In scenarios where users are not cooperating with the system, these systems are challenged. Failure in cooperation with the biometric systems might be intentional or because the users are incapable of handling the interaction procedure with the biometric system or simply forget to cooperate with it, due to for example, illness like dementia. This work introduces a challenging bimodal database, including face and hand information of the users when they approach a door to open it by its handle in a noncooperative context. We have defined two (an easy and a challenging) protocols on how to use the database. We have reported results on many baseline methods, including deep learning techniques as well as conventional methods on the database. The obtained results show the merit of the proposed database and the challenging nature of access control with non-cooperative users.
Keywords: IEEE Winter Applications of Computer Vision Workshops
|
|
|
|
Jelena Gorbova, Egils Avots, Iiris Lusi, Mark Fishel, Sergio Escalera, & Gholamreza Anbarjafari. (2018). Integrating Vision and Language for First Impression Personality Analysis. MULTIMEDIA - IEEE Multimedia, 25(2), 24–33.
Abstract: The authors present a novel methodology for analyzing integrated audiovisual signals and language to assess a persons personality. An evaluation of their proposed multimodal method using a job candidate screening system that predicted five personality traits from a short video demonstrates the methods effectiveness.
|
|
|
|
Rain Eric Haamer, Eka Rusadze, Iiris Lusi, Tauseef Ahmed, Sergio Escalera, & Gholamreza Anbarjafari. (2018). Review on Emotion Recognition Databases. In Human-Robot Interaction: Theory and Application.
Abstract: Over the past few decades human-computer interaction has become more important in our daily lives and research has developed in many directions: memory research, depression detection, and behavioural deficiency detection, lie detection, (hidden) emotion recognition etc. Because of that, the number of generic emotion and face databases or those tailored to specific needs have grown immensely large. Thus, a comprehensive yet compact guide is needed to help researchers find the most suitable database and understand what types of databases already exist. In this paper, different elicitation methods are discussed and the databases are primarily organized into neat and informative tables based on the format.
Keywords: emotion; computer vision; databases
|
|
|
|
Julio C. S. Jacques Junior, Xavier Baro, & Sergio Escalera. (2017). Exploiting feature representations through similarity learning and ranking aggregation for person re-identification. In 12th IEEE International Conference on Automatic Face and Gesture Recognition.
Abstract: Person re-identification has received special attentionby the human analysis community in the last few years.To address the challenges in this field, many researchers haveproposed different strategies, which basically exploit eithercross-view invariant features or cross-view robust metrics. Inthis work we propose to combine different feature representationsthrough ranking aggregation. Spatial information, whichpotentially benefits the person matching, is represented usinga 2D body model, from which color and texture informationare extracted and combined. We also consider contextualinformation (background and foreground data), automaticallyextracted via Deep Decompositional Network, and the usage ofConvolutional Neural Network (CNN) features. To describe thematching between images we use the polynomial feature map,also taking into account local and global information. Finally,the Stuart ranking aggregation method is employed to combinecomplementary ranking lists obtained from different featurerepresentations. Experimental results demonstrated that weimprove the state-of-the-art on VIPeR and PRID450s datasets,achieving 58.77% and 71.56% on top-1 rank recognitionrate, respectively, as well as obtaining competitive results onCUHK01 dataset.
|
|
|
|
Sergio Escalera, Xavier Baro, Hugo Jair Escalante, & Isabelle Guyon. (2017). ChaLearn Looking at People: A Review of Events and Resources. In 30th International Joint Conference on Neural Networks.
Abstract: This paper reviews the historic of ChaLearn Looking at People (LAP) events. We started in 2011 (with the release of the first Kinect device) to run challenges related to human action/activity and gesture recognition. Since then we have regularly organized events in a series of competitions covering all aspects of visual analysis of humans. So far we have organized more than 10 international challenges and events in this field. This paper reviews associated events, and introduces the ChaLearn LAP platform where public resources (including code, data and preprints of papers) related to the organized events are available. We also provide a discussion on perspectives of ChaLearn LAP activities.
|
|
|
|
Julio C. S. Jacques Junior, Xavier Baro, & Sergio Escalera. (2018). Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification. IMAVIS - Image and Vision Computing, 79, 76–85.
Abstract: Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset.
|
|
|
|
Fatemeh Noroozi, Marina Marjanovic, Angelina Njegus, Sergio Escalera, & Gholamreza Anbarjafari. (2019). Audio-Visual Emotion Recognition in Video Clips. TAC - IEEE Transactions on Affective Computing, 10(1), 60–75.
Abstract: This paper presents a multimodal emotion recognition system, which is based on the analysis of audio and visual cues. From the audio channel, Mel-Frequency Cepstral Coefficients, Filter Bank Energies and prosodic features are extracted. For the visual part, two strategies are considered. First, facial landmarks’ geometric relations, i.e. distances and angles, are computed. Second, we summarize each emotional video into a reduced set of key-frames, which are taught to visually discriminate between the emotions. In order to do so, a convolutional neural network is applied to key-frames summarizing videos. Finally, confidence outputs of all the classifiers from all the modalities are used to define a new feature space to be learned for final emotion label prediction, in a late fusion/stacking fashion. The experiments conducted on the SAVEE, eNTERFACE’05, and RML databases show significant performance improvements by our proposed system in comparison to current alternatives, defining the current state-of-the-art in all three databases.
|
|
