1 Introduction.- 2 Developing mobile applications for environmental and biodiversity citizen science: considerations and recommendations.- 3 A toolbox for understanding and implementing a citizens' observatory on air monitoring.- 4 A Real-Time Streaming and Detection System for Bio-acoustic Ecological Studies after the Fukushima Accident.- 5 Towards improved air quality monitoring using publicly available sky images.- 6 Traits: Structuring species information for discoverability, navigation and identification.- 7 Unsupervised Bioacoustic Segmentation by Hierarchical Dirichlet Process Hidden Markov Model.- 8 Plant Identification: Experts vs. Machines in the Era of Deep Learning.- 9 Automated identification of herbarium specimens at different taxonomic levels.- 10 A deep learning approach to species distribution modelling.- A Existing Data and Metadata Standards and Schemas related to Citizen Science.- B Creative Commons (CC) and Open Data Commons (ODC) Licenses.- C List of Apps, Platforms and their Functionalities in Citizen Science Projects.- D Examples of Symbolic and Non-symbolic Rewards in Citizen Science Projects.- E List of Apps for Sonic Environment and Noise Pollution Monitoring.

Demonstrates how multimedia research and technological innovation impact the wide range of environmental and biodiversity studies Provides an introduction to the leading content analysis and machine learning techniques in an easily accessible expression, based on various and concrete examples of implementations Illustrates the increasing capabilities of multimedia tools & applications for the characterization of living organisms