Sorry, you need to enable JavaScript to visit this website.

In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, this is the first example of a deep learning architecture for illuminant estimation that is trained without ground truth illuminants. We evaluate our solution on standard datasets for color constancy, and compare it with state of the art methods.

Action quality assessment is crucial in areas of sports, surgery and assembly line where action skills can be evaluated. In this paper, we propose the Segment-based P3D-fused network S3D built-upon ED-TCN and push the performance on the UNLV-Dive dataset by a significant margin. We verify that segment-aware training performs better than full-video training which turns out to focus on the water spray. We show that temporal segmentation can be embedded with few efforts.

One of the most important factors in training object recognition networks using convolutional neural networks (CNN) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset.

In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a visually interpretable local structure in conjunction with other filters. The significance of learning these interpretable filter sets is demonstrated on two contrasting applications. The first application is image recognition under progressive decolorization, in which recognition algorithms should be color-insensitive to achieve a robust performance.

The task of rain detection, or wet-dry classification
using measurements from commercial microwave links (CMLs)
is a subject that been studied in depth. However, these studies
are based on direct measurement of the signal level, which
is known to be attenuated by rain. In this paper we present,
for the first time an empirical study on rain classification using
records of transmissions errors in the CMLs. Based on a dataset
of measurements taken from operational cellular backhaul
networks and meteorological measurements, and using long

In multi-antenna systems, it is preferred to activate only a subset of the available transmit antennas in order to save hardware and energy resources, without seriously degrading the system performance. However, antenna selection often poses very hard optimization problems. Joint multicast beamforming and antenna selection is one particular example, which is often approached by Semi-Definite Relaxation (SDR) type approximations. The drawback is that SDR lifts the problem to a much higher dimension, leading to considerably high memory and computational complexities.

We apply convolutional neural networks (CNN) for monitoring the
operation of photovoltaic panels. In particular, we predict the daily
electrical power curve of a photovoltaic panel based on the power
curves of neighboring panels. An exceptionally large deviation between
predicted and actual (observed) power curve indicates a malfunctioning
panel. The problem is challenging because the power
curve depends on many factors such as weather conditions and the
surrounding objects causing shadows with a regular time pattern. We

Convolutional neural networks (CNNs) are being applied to an increasing number of problems and fields due to their superior performance in classification and regression tasks. Since two of the key operations that CNNs implement are convolution and pooling, this type of networks is implicitly designed to act on data described by regular structures such as images. Motivated by the recent interest in processing signals defined in irregular domains, we advocate a CNN architecture that operates on signals supported on graphs.