Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services. While many solutions have been proposed for this task, the majority of them are too computatio
nally expensive to run on portable devices with limited hardware resources. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a real-time performance on mobile GPUs. The participants were provided with the REDS dataset and trained their models to do an efficient 4X video upscaling. The runtime of all models was evaluated on the OPPO Find X2 smartphone with the Snapdragon 865 SoC capable of accelerating floating-point networks on its Adreno GPU. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent. In this work, we propose UVIT, a novel unsupervised video-to-video
translation model. Our model decomposes the style and the content, uses the specialized encoder-decoder structure and propagates the inter-frame information through bidirectional recurrent neural network (RNN) units. The style-content decomposition mechanism enables us to achieve style consistent video translation results as well as provides us with a good interface for modality flexible translation. In addition, by changing the input frames and style codes incorporated in our translation, we propose a video interpolation loss, which captures temporal information within the sequence to train our building blocks in a self-supervised manner. Our model can produce photo-realistic, spatio-temporal consistent translated videos in a multimodal way. Subjective and objective experimental results validate the superiority of our model over existing methods. More details can be found on our project website: https://uvit.netlify.com
High-energy astrophysical neutrinos, recently discovered by IceCube up to energies of several PeV, opened a new window to the high-energy Universe. Yet much remains to be known. IceCube has excellent muon flavor identification, but tau flavor identif
ication is challenging. This limits its ability to probe neutrino physics and astrophysics. To address this limitation, we present a concept for a large-scale observatory of astrophysical tau neutrinos in the 1-100 PeV range, where a flux is guaranteed to exist. Its detection would allow us to characterize the neutrino sources observed by IceCube, to discover new ones, and test neutrino physics at high energies. The deep-valley air-shower array concept that we present provides highly background-suppressed neutrino detection with pointing resolution <1 degree, allowing us to begin the era of high-energy tau-neutrino astronomy.
A successful ground array Radio Frequency (RF)-only self-trigger on 10 high-energy cosmic ray events is demonstrated with 256 dual-polarization antennas of the Owens Valley Radio Observatory Long Wavelength Array (OVRO-LWA). This RF-only capability i
s predicated on novel techniques for Radio Frequency Interference (RFI) identification and mitigation with an analysis efficiency of 45% for shower-driven events with a Signal-to-noise ratio $gtrsim$ 5 against the galactic background noise power of individual antennas. This technique enables more efficient detection of cosmic rays over a wider range of zenith angles than possible via triggers from in-situ particle detectors and can be easily adapted by neutrino experiments relying on RF-only detection. This paper discusses the system design, RFI characterization and mitigation techniques, and initial results from 10 cosmic ray events identified within a 40-hour observing window. A design for a future optimized commensal cosmic-ray detector for the OVRO-LWA is presented, as well as recommendations for developing a similar capability for other experiments -- these designs either reduce data-rate or increase sensitivity by an order of magnitude for many configurations of radio instruments.
These proceedings address a recent publication by the ANITA collaboration of four upward- pointing cosmic-ray-like events observed in the first flight of ANITA. Three of these events were consistent with stratospheric cosmic-ray air showers where the
axis of propagation does not inter- sect the surface of the Earth. The fourth event was consistent with a primary particle that emerges from the surface of the ice suggesting a possible {tau}-lepton decay as the origin of this event. These proceedings follow-up on the modeling and testing of the hypothesis that this event was of {tau} neutrino origin.
