The main goal of this course is to provide the students with the theoretical and methodological knowledge about algorithms and methods for multimedia information indexing and retrieval. At the end of the course the students are expected to have acquired (or progress in the acquisition -for transversal competences-) the following competences: 1. TRANSVERSAL/GENERAL COMPETENCES: 1.1 Personal work abilities. 1.2 Analysis and Synthesis abilities. 1.3 Abilities for applying theoretical concepts to practical uses. 1.4 Abilities related to team work and collaboration. 1.5 Abilities related to oral and written presentations. 2. SPECIFIC COMPETENCES: 2.1 To understand the fundamentals of audio-visual data analytics and its applications. 2.2 To understand the basics of speech, audio, image and video description and representation. 2.3 To understand audio-visual analytics methods and technologies. 2.4 To understand, design and implement multimedia indexing, retrieval, filtering and recommendation. CB1, CB2 CG3, CG11 ETEGITT9, ETEGITT3

The modern information overload problem caused by the availability of enormous amounts of information through internet makes it necessary to design systems that allow us to find the information we search and filter or personalize the information according to our needs. For that matter it is fundamental to be able to automatically index not only textual contents but also audio (music, speech, etc.) image or video, using methods based on the content or even collaborative tagging as the one taking place in social networks. Examples of these multimedia management systems are Google search (and all its variants as Google Image, Google Goggles, etc.), recommender systems and user profilers like those available in Amazon. 0. Overview of audio & visual analytics. 1. Speech, audio, image & video descriptors 2. Methods for audio & visual analytics 3. Multimedia Information Retrieval and Recommendation

Several types of learning activities are proposed: theoretical and practical lessons, lab assignments and final project. Several methodologies will be adopted: theoretical lessons and problem-based learning (with different levels of supervision and guidance). THEORETICAL LESSONS (2.5 ECTS) Theoretical lessons provide an overview of the main theoretical and mathematical concepts together with explanations about the analytical tools employed for analysis of audio, imagen and video. GUIDED LAB ASSIGNMENTS (1.75 ECTS) Several guided lab assignments have been designed with the purpose of allowing the students to put into practice the mathematical tools explained in the theoretical lessons. The students will learn to use different audio and image analysis methods, such as audio clustering, face recognition and textual indexing, and learn to make sense of the results obtained. FINAL PROJECT (1.75 ECTS) The students will develop a simple image or audio (their choice) analysis system.