Attention estimation and annotation are tasks aimed at revealing which parts of some content are likely to draw the users’ interest. Previous approaches have tackled these incredibly challenging tasks using a variety of behavioral signals, from dwell-time to clickthrough data, and computational models of visual correspondence to these behavioral signals. Today, these signals are leveraged by a myriad of online services to personalize social media, search engine results, recommender systems, and even in supporting critical decision making, such as financial or medical data. However, the signals that all these services are based on are rough estimations of the real underlying attention and affective preferences of the users. Indeed, users may attend to some content simply because it is salient, but not because it is really interesting, or simply because it is outrageous. In contrast, project BANANA will use brain-computer interfaces (BCIs) to infer users’ preferences and their attentional correlates towards visual content, as measured directly from the human brain. We aim for a scientific breakthrough by proposing the first-of-its-kind affective visual attention annotation via brainsourcing, i.e. crowdsourced BCI signal acquisition. First, our approach will allow accurate estimation of user preferences, attention allocation, and --critically-- the affective component of attention, directly measured from the natural and implicit brain potentials evoked in response to users experiencing digital contents. Then, we will utilize the resulting data in a crowdsourcing setting to reveal how multiple users react to different stimuli and how their attention and affective responses are distributed. These collective responses will produce unified, consistent measures as a result. Our technology will be used in several downstream tasks such as segmentation of users' attention while looking at images, identification of key events, and video summarisation. We will pilot BANANA with different user groups to test and prove its effectiveness, using objective benchmarks and evaluation strategies.

The TRADEGREEN project examines public policies aiming at reconciling international trade with our environment: the carbon border adjustment mechanism (CBAM), subsidies on decarbonated technologies, and environmental provisions in trade agreements. The first two policies reduce carbon leakage. The CBAM can be combined with free emission allowances, with export rebates, or with public investment in technological change. The impact and efficiency of these instruments are investigated in an economic model in which international trade and firms' investment in decarbonated technologies are endogenous. The model is calibrated on European data to obtain estimates. The environmental provisions of trade agreements are analyzed in a framework with asymmetric information about the signatory countries' willingness to protect the environment. Our goal is to come up with environmental provisions that mitigate the harmful impacts of trade on ecosystems, for instance by making the reduction of tariffs contingent on the adoption of more stringent environmental standards. The theoretical analysis is complemented with two empirical evaluations. The first investigates the relationship between the signatory countries' environmental values and policies with the environmental provisions of the trade agreements in various issues such as biodiversity, climate change, GMOs, pesticides, or air quality. The second study focuses on the agreement between the European Union and the Mercosur. Using administrative, economic, and satellite data, we calibrate the theoretical model to estimate tariff cuts on agricultural products contingent on measurable targets on deforestation reduction in the Brazilian Amazone. TRADEGREEN aims at improving our understanding of environmental and trade policies, and quantifying their impact on economics, trade, and our planet.

INTOMED develops novel, effective and sustainable tools that utilize (a) interactions between plants and soil-borne beneficial microbes and (b) natural key plant (metabolites and peptides) and bacterially-expressed RNA molecules to enhance the resistance of economically important Mediterranean crops, i.e. tomato, olive and citrus, to major agricultural arthropod pests and pathogens. Soil-borne beneficial microbes have long been recognized for their ability to improve plant growth and nutrition and prime the plant immune system against pathogens and herbivores in plants. We thus aim to first, assess the potential of selected marketed and laboratory-owned strains of beneficial microbes, including endophytes, for their ability to improve crop resistance to arthropods and pathogens and second, study the molecular mechanisms involved in promising microbe-plant-pest combinations with the aim to also identify plant secondary metabolites and peptides that mediate enhanced resistance and technically support future commercial biocontrol products. INTOMED also exploits the development of a GMO-free and effective pest control tool i.e. exogenous delivery of RNA molecules having the potential to trigger RNA interference (RNAi) against targeted pathogens/pests in both vegetables and fruit trees. Pilot demonstration trials, targeting end-users (farmers, SMEs) will assess promising beneficial microbes and plant molecules. In addition, INTOMED will increase public awareness of the nature of the proposed tools and analyse the impact of their acceptance. Our consortium includes 9 academic and industrial partners from Greece, Spain, France, Morocco, Portugal and Tunisia. INTOMED will generate new knowledge on plant-microbe-pest interactions and develop novel sustainable tools to prevent outbreaks of economically important pests and pathogens in the Mediterranean.