Abstract: Following the completion of the AutoDL challenge (the final challenge in the ChaLearn
AutoDL challenge series 2019), we investigate winning solutions and challenge results to
answer an important motivational question: how far are we from achieving true AutoML?
On one hand, the winning solutions achieve good (accurate and fast) classification performance on unseen datasets. On the other hand, all winning solutions still contain a
considerable amount of hard-coded knowledge on the domain (or modality) such as image,
video, text, speech and tabular. This form of ad-hoc meta-learning could be replaced by
more automated forms of meta-learning in the future. Organizing a meta-learning challenge could help forging AutoML solutions that generalize to new unseen domains (e.g.
new types of sensor data) as well as gaining insights on the AutoML problem from a more
fundamental point of view. The datasets of the AutoDL challenge are a resource that can
be used for further benchmarks and the code of the winners has been outsourced, which is
a big step towards “democratizing” Deep Learning.

Abstract: This paper describes an approach to human action recognition based on a probabilistic optimization model of body parts using hidden Markov model (HMM). Our method is able to distinguish between similar actions by only considering the body parts having major contribution to the actions, for example, legs for walking, jogging and running; arms for boxing, waving and clapping. We apply HMMs to model the stochastic movement of the body parts for action recognition. The HMM construction uses an ensemble of body-part detectors, followed by grouping of part detections, to perform human identification. Three example-based body-part detectors are trained to detect three components of the human body: the head, legs and arms. These detectors cope with viewpoint changes and self-occlusions through the use of ten sub-classifiers that detect body parts over a specific range of viewpoints. Each sub-classifier is a support vector machine trained on features selected for the discriminative power for each particular part/viewpoint combination. Grouping of these detections is performed using a simple geometric constraint model that yields a viewpoint-invariant human detector. We test our approach on three publicly available action datasets: the KTH dataset, Weizmann dataset and HumanEva dataset. Our results illustrate that with a simple and compact representation we can achieve robust recognition of human actions comparable to the most complex, state-of-the-art methods.

Abstract: Activity Recognition is an emerging field of research, born from the larger fields of ubiquitous computing, context-aware computing and multimedia. Recently, recognizing everyday life activities becomes one of the challenges for pervasive computing. In our work, we developed a novel wearable system easy to use and comfortable to bring. Our wearable system is based on a new set of 20 computationally efficient features and the Random Forest classifier. We obtain very encouraging results with classification accuracy of human activities recognition of up to 94%.

Abstract: Pose Recovery (PR) and Human Behavior Analysis (HBA) have been a main focus of interest from the beginnings of Computer Vision and Machine Learning. PR and HBA were originally addressed by the analysis of still images and image sequences. More recent strategies consisted of Motion Capture technology (MOCAP), based on the synchronization of multiple cameras in controlled environments; and the analysis of depth maps from Time-of-Flight (ToF) technology, based on range image recording from distance sensor measurements. Recently, with the appearance of the multi-modal RGBD information provided by the low cost Kinect \textsfTM sensor (from RGB and Depth, respectively), classical methods for PR and HBA have been redefined, and new strategies have been proposed. In this paper, the recent contributions and future trends of multi-modal RGBD data analysis for PR and HBA are reviewed and discussed.

Abstract: This chapter tackles the challenging problem of human pose estimation in multi-view environments to handle scenes with self-occlusions. The proposed approach starts by first estimating the camera pose—extrinsic parameters—in multi-view scenarios; due to few real image datasets, different virtual scenes are generated by using a special simulator, for training and testing the proposed convolutional neural network based approaches. Then, these extrinsic parameters are used to establish the relation between different cameras into the multi-view scheme, which captures the pose of the person from different points of view at the same time. The proposed multi-view scheme allows to robustly estimate human body joints’ position even in situations where they are occluded. This would help to avoid possible false alarms in behavioral analysis systems of smart cities, as well as applications for physical therapy, safe moving assistance for the elderly among other. The chapter concludes by presenting experimental results in real scenes by using state-of-the-art and the proposed multi-view approaches.

Abstract: Psychological evidence has emphasized the importance of affective behaviour understanding due to its high impact in nowadays interaction humans and computers. All
type of affective and behavioural patterns such as gestures, emotions and mental
states are highly displayed through the face, head and body. Therefore, this thesis is
focused to analyse affective behaviours on head and face. To this end, head and facial
movements are encoded by using appearance based tracking methods. Specifically,
a wise combination of deformable models captures rigid and non-rigid movements of
different kinematics; 3D head pose, eyebrows, mouth, eyelids and irises are taken into
account as basis for extracting features from databases of video sequences. This approach combines the strengths of adaptive appearance models, optimization methods
and backtracking techniques.
For about thirty years, computer sciences have addressed the investigation on
human emotions to the automatic recognition of six prototypic emotions suggested
by Darwin and systematized by Paul Ekman in the seventies. The Facial Action
Coding System (FACS) which uses discrete movements of the face (called Action
units or AUs) to code the six facial emotions named anger, disgust, fear, happy-Joy,
sadness and surprise. However, human emotions are much complex patterns that
have not received the same attention from computer scientists.
Simon Baron-Cohen proposed a new taxonomy of emotions and mental states
without a system coding of the facial actions. These 426 affective behaviours are
more challenging for the understanding of human emotions. Beyond of classically
classifying the six basic facial expressions, more subtle gestures, facial actions and
spontaneous emotions are considered here. By assessing confidence on the recognition
results, exploring spatial and temporal relationships of the features, some methods are
combined and enhanced for developing new taxonomy of expressions and emotions.
The objective of this dissertation is to develop a computer vision system, including both facial feature extraction, expression recognition and emotion understanding
by building a bottom-up reasoning process. Building a detailed taxonomy of human
affective behaviours is an interesting challenge for head-face-based image analysis
methods. In this paper, we exploit the strengths of Canonical Correlation Analysis
(CCA) to enhance an on-line head-face tracker. A relationship between head pose and
local facial movements is studied according to their cognitive interpretation on affective expressions and emotions. Active Shape Models are synthesized for AAMs based
on CCA-regression. Head pose and facial actions are fused into a maximally correlated space in order to assess expressiveness, confidence and classification in a CBR system. The CBR solutions are also correlated to the cognitive features, which allow
avoiding exhaustive search when recognizing new head-face features. Subsequently,
Support Vector Machines (SVMs) and Bayesian Networks are applied for learning the
spatial relationships of facial expressions. Similarly, the temporal evolution of facial
expressions, emotion and mental states are analysed based on Factorized Dynamic
Bayesian Networks (FaDBN).
As results, the bottom-up system recognizes six facial expressions, six basic emotions and six mental states, plus enhancing this categorization with confidence assessment at each level, intensity of expressions and a complete taxonomy

Abstract: We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.