Humans can easily perceive the direction of sound sources in a visual sc...
Active learning has been utilized as an efficient tool in building anoma...
Most deep anomaly detection models are based on learning normality from
...
In recent years, monitoring the world wide area with satellite images ha...
We address a weakly-supervised low-shot instance segmentation, an
annota...
One-class classification has been a prevailing method in building deep
a...
Open compound domain adaptation (OCDA) considers the target domain as th...
Human brain is continuously inundated with the multisensory information ...
The objective of this work is to localize the sound sources in visual sc...
In this paper, we propose Normality-Calibrated Autoencoder (NCAE), which...
Recently, vehicle re-identification methods based on deep learning const...
We propose a novel framework to generate clean video frames from a singl...
In most of computer vision applications, motion blur is regarded as an
u...
Abrupt motion of camera or objects in a scene result in a blurry video, ...
ResNet or DenseNet? Nowadays, most deep learning based approaches are
im...
Visual events are usually accompanied by sounds in our daily lives. Howe...
Dashboard cameras capture a tremendous amount of driving scene video eac...
In daily life, graphic symbols, such as traffic signs and brand logos, a...
Visual events are usually accompanied by sounds in our daily lives. We p...
Recent advances in visual recognition show overarching success by virtue...
In this paper, we propose a unified end-to-end trainable multi-task netw...