Dans cette dissertation, nous discutons comment utiliser les données du regard humain pour améliorer la performance du modèle d'apprentissage supervisé faible dans la classification des images. Le contexte de ce sujet est à l'ère de la technologie de l'information en pleine croissance. En conséquence, les données à analyser augmentent de façon spectaculaire. Étant donné que la quantité de données pouvant être annotées par l'humain ne peut pas tenir compte de la quantité de données elle-même, les approches d'apprentissage supervisées bien développées actuelles peuvent faire face aux goulets d'étranglement l'avenir. Dans ce contexte, l'utilisation de annotations faibles pour les méthodes d'apprentissage à haute performance est digne d'étude. Plus précisément, nous essayons de résoudre le problème à partir de deux aspects: l'un consiste à proposer une annotation plus longue, un regard de suivi des yeux humains, comme une annotation alternative par rapport à l'annotation traditionnelle longue, par exemple boîte de délimitation. L'autre consiste à intégrer l'annotation du regard dans un système d'apprentissage faiblement supervisé pour la classification de l'image. Ce schéma bénéficie de l'annotation du regard pour inférer les régions contenant l'objet cible. Une propriété utile de notre modèle est qu'elle exploite seulement regardez pour la formation, alors que la phase de test est libre de regard. Cette propriété réduit encore la demande d'annotations. Les deux aspects isolés sont liés ensemble dans nos modèles, ce qui permet d'obtenir des résultats expérimentaux compétitifs. / In this dissertation, we discuss how to use the human gaze data to improve the performance of the weak supervised learning model in image classification. The background of this topic is in the era of rapidly growing information technology. As a consequence, the data to analyze is also growing dramatically. Since the amount of data that can be annotated by the human cannot keep up with the amount of data itself, current well-developed supervised learning approaches may confront bottlenecks in the future. In this context, the use of weak annotations for high-performance learning methods is worthy of study. Specifically, we try to solve the problem from two aspects: One is to propose a more time-saving annotation, human eye-tracking gaze, as an alternative annotation with respect to the traditional time-consuming annotation, e.g. bounding box. The other is to integrate gaze annotation into a weakly supervised learning scheme for image classification. This scheme benefits from the gaze annotation for inferring the regions containing the target object. A useful property of our model is that it only exploits gaze for training, while the test phase is gaze free. This property further reduces the demand of annotations. The two isolated aspects are connected together in our models, which further achieve competitive experimental results.

Over the years, extensive research has been devoted to the study of people's head pose due to its relevance in security, human-computer interaction, advertising as well as cognitive, neuro and behavioural psychology. One of the main goals of this thesis is to estimate people's 3D head orientation as they freely move around in naturalistic settings such as parties, supermarkets etc. Head pose classification from surveillance images acquired with distant, large field-of-view cameras is difficult as faces captured are at low-resolution with a blurred appearance. Also labelling sufficient training data for headpose estimation in such settings is difficult due to the motion of targets and the large possible range of head orientations. Domain adaptation approaches are useful for transferring knowledge from the training source to the test target data having different attributes, minimizing target data labelling efforts in the process. This thesis examines the use of transfer learning for efficient multi-view head pose classification. Relationship between head pose and facial appearance from many labelled examples corresponding to the source data is learned initially. Domain adaptation techniques are then employed to transfer this knowledge to the target data. The following three challenging situations is addressed (I) ranges of head poses in the source and target images is different, (II) where source images capture a stationary person while target images capture a moving person with varying facial appearance due to changing perspective, scale and (III) a combination of (I) and (II). All proposed transfer learning methods are sufficiently tested and benchmarked on a new compiled dataset DPOSE for headpose classification. This thesis also looks at a novel signature representation for describing object sets for covariance descriptors, Covariance Profiles (CPs). CP is well suited for representing a set of similarly related objects. CPs posit that the covariance matrices, pertaining to a specific entity, share the same eigen-structure. Such a representation is not only compact but also eliminates the need to store all the training data. Experiments on images as well as videos for applications such as object-track clustering and headpose estimation is shown using CP. In the second part, Human-gaze for interest point detection for video retargeting is explored. Regions in video streams attracting human interest contribute significantly to human understanding of the video. Being able to predict salient and informative Regions of Interest (ROIs) through a sequence of eye movements is a challenging problem. This thesis proposes an interactive human-in-loop framework to model eye-movements and predicts visual saliency in yet-unseen frames. Eye-tracking and video content is used to model visual attention in a manner that accounts for temporal discontinuities due to sudden eye movements, noise and behavioural artefacts. Gaze buffering, for eye-gaze analysis and its fusion with content based features is proposed. The method uses eye-gaze information along with bottom-up and top-down saliency to boost the importance of image pixels. Our robust visual saliency prediction is instantiated for content aware Video Retargeting.