2nd International ACM Workshop on Crowdsourcing for Multimedia

Date: 
21 Oct 2013 to 25 Oct 2013
Location: 
Barcelona, Spain

Overview Crowdsourcing--leveraging a large number of human contributors and the capabilities of human computation--has enormous potential to address key challenges in the area of multimedia research. Applications of crowdsourcing range from the exploitation of unsolicited user contributions, such as using tags to aid image understanding, to utilizing crowdsourcing platforms and marketplaces to micro-outsource tasks such as semantic video annotation. Further, crowdsourcing offers a time- and resource-efficient method for collecting large volumes of input for system design or evaluation, making it possible to optimize multimedia systems more rapidly and to address human factors more effectively. At present, crowdsourcing remains notoriously difficult to exploit effectively in multimedia settings, due to the high sensitivity of the users or workers to changes in the form and the parameterization of their activities. For example, on a crowdsourcing platform, workers are known to react differently depending on the way in which a multimedia annotation task is presented or explained and in the manner in which they are incentivized (e.g., compensation, appeal of the task). A thorough understanding of crowdsourcing for multimedia will be crucial in enabling the field to effectively address these challenges. This workshop encourages theoretical, experimental, and methodological developments advancing state-of-the-art knowledge of crowdsourcing techniques for multimedia research and novel applications using crowdsourcing to solve traditional challenges in multimedia research. Topics include, but are not limited to the use of crowds, wisdom of crowds, or human computation in multimedia, in the following areas of research: - Creation: content synthesis, authoring, editing, and collaboration, summarization and storytelling - Evaluation: evaluation of multimedia signal processing algorithms, multimedia analysis and retrieval algorithms, or multimedia systems and applications - Retrieval: analysis of user multimedia queries, evaluating multimedia search algorithms and interactive multimedia retrieval - Annotation: generating semantic annotations for multimedia content, collecting large-scale input on user affective reactions - Human factors: designing or evaluating user interfaces for multimedia systems, usability study, multi-modal environment, human recognition and perceptions - Novel applications (e.g., human as an element in the loop of computation) - Effective Learning from crowd-annotated or crowd-augmented datasets - Quality assurance and cheat detection - Economics and incentive structures - Programming languages, tools, and platforms providing enhanced support - Inherent biases, limitations, and trade-offs of crowd-centered approaches