About MICO

 MICO is a EU-funded research project (no. 610480) to develop an integrated platform for cross-media analysis, metadata publishing, querying and recommendation

  • Motivation

    Abundance of A/V material requires automatic annotation –  automatic annotators typically operate in isolation and do not consider the context of a media resource – insufficient annotation quality for many tasks – available technologies are complex to use and difficult to combine: expensive, especially for SME approach – integration and orchestration of extractors for various media types, capable of reusing their results – providing all necessary technologies for distributed cross-media extraction, metadata publishing, querying and recommendations – core software provided under business-friendly OSS licenses (building on OSS projects such as Apache Marmotta), allowing inclusion of OSS and closed- source extractors.

  • Key Challenges

    The main challenges for MICO are cross-media extraction: container tag extraction, language detection, scene detection, face detection, speech-music discrimination, ASR and NER – context-specific, dynamic orchestration and parametrization: config of the analysis graph and extractor parameters depend on the context – bridge the gap between high-level user queries and context-specific low-level queries – metadata model, query language and reco for media fragments, e.g. find similar topics based on key word cooccurrence in different video fragment transcriptions

  • News Media Showcase

    InsideOut10, Italian SME with extensive experience on web publishing and media delivery platforms brings a number of challenging business cases to MICO such as – “Shoof”: citizen journalism; challenges: automatic QA of user-created videos, ASR, tampering detection, etc.- “Greenpeace News”: digital magazine; challanges: metadata enrichment for “cross-issue” reco and discovery paths, etc. includes e.g. queries: “point me to scenes within videos where a specific person is talking about a topic, and show me similar content on related topics” with

  • Snapshot Serengeti Showcase

    Zooniverse, home to some of the largest and most successful citizen-science projects in the world brings the challenges of the Snapshot Serengeti project to MICO, such as animal detection and classification – visual analysis: blank image detection, pre-classification – tactual analysis of posts and discussions, and recommendation: identify user interest, emerging species, enrich species information, detect controversial topics, identity user communities (e.g. via vocabulary expertise), targeted education of users, harness user expertise