Flourishing multimedia content analysis technologies have pushed multimedia information retrieval and various multidisciplinary studies towards realistic paradigms that significantly impact our daily life. For example, Google Image Search allows users to retrieve web images relevant to provided keywords or uploaded images. Google Goggles APP enables object and scene recognition on smart phones (in limited domains). The influence of multimedia content analysis on our life in both the real world and the cyberspace is not only apparent but also deep. However, related researches are impeded by the notorious semantic gap problem, i.e., the gap between human perception/cognition and computational features derived from signals. Recently, in addition to machine learning, pattern recognition, and computer vision techniques that have been widely employed in analyzing large-scale multimedia content, many researchers turn to seek out human knowledge by analyzing social media with/without geographical information, capturing multi-view videos or RGB videos with depth information, or getting insights from crowdsourcing mechanisms.
Campus France and MOST: Ministry of Science and Technology of Taiwan are funding the organisation of the France - Taiwan Multimedia Workshop which will take place in EURECOM, Sophia-Antipolis, France.
We are welcoming interested researchers, academics and industrial to attend the talks given at the workshop. Registration is free but as space is limited, please register in order to be allowed to enter the amphitheater. Register early to avoid disappointment.
