Abstract: This paper presents a system capable of recognizing six head gestures: nodding, shaking, turning right, turning left, looking up, and looking down. The main difference of our system compared to other methods is that the Hidden Markov Models presented in this paper, are fully connected and consider all possible states in any given order, providing the following advantages to the system: (1) allows unconstrained movement of the head and (2) it can be easily integrated into a wearable device (e.g. glasses, neck-hung devices), in which case it can robustly recognize gestures in the presence of ego-motion. Experimental results show that this approach outperforms common methods that use restricted HMMs for each gesture.

Abstract: Human-robot interaction is a hot topic nowadays in the social robotics community. One crucial aspect is represented by the affective communication which comes encoded through the facial expressions. In this paper, we propose a novel approach for facial expression recognition, which exploits an efficient and adaptive graph-based label propagation (semi-supervised mode) in a multi-observation framework. The facial features are extracted using an appearance-based 3D face tracker, view- and texture independent. Our method has been extensively tested on the CMU dataset, and has been conveniently compared with other methods for graph construction. With the proposed approach, we developed an application for an AIBO robot, in which it mirrors the recognized facial
expression.

Abstract: Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition applications, such as image classification, detection and segmentation. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected
informative and/or representative samples. In this thesis we study several aspects of active learning including video object detection for autonomous driving systems, image classification on balanced and imbalanced datasets and the incorporation of self-supervised learning in active learning. We briefly describe our approach in each of these areas to reduce the labeling effort.
In chapter two we introduce a novel active learning approach for object detection in videos by exploiting temporal coherence. Our criterion is based on the estimated number of errors in terms of false positives and false negatives. Additionally, we introduce a synthetic video dataset, called SYNTHIA-AL, specially designed to evaluate active
learning for video object detection in road scenes. Finally, we show that our
approach outperforms active learning baselines tested on two outdoor datasets.
In the next chapter we address the well-known problem of over confidence in the neural networks. As an alternative to network confidence, we propose a new informativeness-based active learning method that captures the learning dynamics of neural network with a metric called label-dispersion. This metric is low when the network consistently assigns the same label to the sample during the course of training and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
In chapter four, we tackle the problem of sampling bias in active learning methods on imbalanced datasets. Active learning is generally studied on balanced datasets where an equal amount of images per class is available. However, real-world datasets suffer from severe imbalanced classes, the so called longtail distribution. We argue that this further complicates the active learning process, since the imbalanced data pool can result in suboptimal classifiers. To address this problem in the context of active learning, we propose a general optimization framework that explicitly takes class-balancing into account. Results on three datasets show that the method is general (it can be combined with most existing active learning algorithms) and can be effectively applied to boost the performance of both informative and representative-based active learning methods. In addition, we show that also on balanced datasets our method generally results in a performance gain.
Another paradigm to reduce the annotation effort is self-training that learns from a large amount of unlabeled data in an unsupervised way and fine-tunes on few labeled samples. Recent advancements in self-training have achieved very impressive results rivaling supervised learning on some datasets. In the last chapter we focus on whether active learning and self supervised learning can benefit from each other.
We study object recognition datasets with several labeling budgets for the evaluations. Our experiments reveal that self-training is remarkably more efficient than active learning at reducing the labeling effort, that for a low labeling budget, active learning offers no benefit to self-training, and finally that the combination of active learning and self-training is fruitful when the labeling budget is high.

Abstract: Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.

Abstract: Ensembles are a popular way to improve results of discriminative CNNs. The
combination of several networks trained starting from different initializations
improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways to construct ensembles. The first one is based on the fact that in the minimax game which is played to optimize the GAN objective the generator network keeps on changing even after the network can be considered optimal. As such ensembles of GANs can be constructed based on the same network initialization but just taking models which have different amount of iterations. These so-called self ensembles are much faster to train than traditional ensembles. The second method, called cascade GANs, redirects part of the training data which is badly modeled by the first GAN to another GAN. In experiments on the CIFAR10 dataset we show that ensembles of GANs obtain model probability distributions which better model the data distribution. In addition, we show that these improved results can be obtained at little additional computational cost.

Abstract: Mirroring occurs when one person tends to mimic the non-verbal communication of their counterparts. Even though mirroring is a complex phenomenon, in this study, we focus on the detection of head-nodding as a simple non-verbal communication cue due to its significance as a gesture displayed during social interactions. This paper introduces a computer vision-based method to detect mirroring through the analysis of head gestures using wearable cameras (smart glasses). In addition, we study how such a method can be used to explore perceived competence. The proposed method has been evaluated and the experiments demonstrate how static and wearable cameras seem to be equally effective to gather the information required for the analysis.

Abstract: Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.

Abstract: Describing persons and their actions is a challenging problem due to variations in pose, scale and viewpoint in real-world images. Recently, semantic pyramids approach [1] for pose normalization has shown to provide excellent results for gender and action recognition. The performance of semantic pyramids approach relies on robust image description and is therefore limited due to the use of shallow local features. In the context of object recognition [2] and object detection [3], convolutional neural networks (CNNs) or deep features have shown to improve the performance over the conventional shallow features.
We propose deep semantic pyramids for human attributes and action recognition. The method works by constructing spatial pyramids based on CNNs of different part locations. These pyramids are then combined to obtain a single semantic representation. We validate our approach on the Berkeley and 27 Human Attributes datasets for attributes classification. For action recognition, we perform experiments on two challenging datasets: Willow and PASCAL VOC 2010. The proposed deep semantic pyramids provide a significant gain of 17.2%, 13.9%, 24.3% and 22.6% compared to the standard shallow semantic pyramids on Berkeley, 27 Human Attributes, Willow and PASCAL VOC 2010 datasets respectively. Our results also show that deep semantic pyramids outperform conventional CNNs based on the full bounding box of the person. Finally, we compare our approach with state-of-the-art methods and show a gain in performance compared to best methods in literature.