Learn More
The Placing Task is a yearly challenge offered by the MediaEval Multimedia Benchmarking Initiative that requires participants to develop algorithms that automatically predict the geo-location of social media videos and images. We introduce a recent development of a new standardized web-scale geo-tagged dataset for Placing Task 2014, which contains 5.5(More)
We report on a search for particle dark matter with the XENON100 experiment, operated at the Laboratori Nazionali del Gran Sasso for 13 months during 2011 and 2012. XENON100 features an ultralow electromagnetic background of (5.3 ± 0.6) × 10(-3) events/(keV(ee) × kg × day) in the energy region of interest. A blind analysis of 224.6 live days × 34 kg(More)
Multimedia event detection (MED) on user-generated content is the task of finding an event, e.g., a Flash mob or Attempting a bike trick, using its content characteristics. Recent research has focused on approaches that use semantically defined " concepts " trained with annotated audio clips. Using audio concepts allows us to show semantic evidence of their(More)
Audio-based multimedia retrieval tasks may identify semantic information in audio streams, i.e., audio concepts (such as music, laughter , or a revving engine). Conventional Gaussian-Mixture-Models have had some success in classifying a reduced set of audio concepts. However, multi-class classification can benefit from context window analysis and the(More)
We present a work-in-progress snapshot of learning with a 15 billion parameter deep learning network on HPC architectures applied to the largest publicly available natural image and video dataset released to-date. Recent advancements in unsupervised deep neural networks suggest that scaling up such networks in both model and training dataset size can yield(More)
The publication of the Yahoo Flickr Creative Commons 100 Million dataset (YFCC100M)--to date the largest open-access collection of photos and videos--has provided a unique opportunity to stimulate new research in multimedia analysis and retrieval. To make the YFCC100M even more valuable, we have started working towards supplementing it with a comprehensive(More)
We consider the visual sentiment task of mapping an image to an adjective noun pair (ANP) such as " cute baby ". To capture the two-factor structure of our ANP semantics as well as to overcome annotation noise and ambiguity, we propose a novel factorized CNN model which learns separate representations for adjectives and nouns but optimizes the(More)