The target representation learned by convolutional neural networks plays...
GANs largely increases the potential impact of generative models. Theref...
In the last few years, unpaired image-to-image translation has witnessed...
One of the attractive characteristics of deep neural networks is their
a...
Recurrent neural networks (RNN) are popular for many computer vision tas...
The cost of drawing object bounding boxes (i.e. labeling) for millions o...
Autonomous driving systems require huge amounts of data to train. Manual...
We propose an end-to-end tracking framework for fusing the RGB and TIR
m...
Recently, image-to-image translation research has witnessed remarkable
p...
Siamese approaches address the visual tracking problem by extracting an
...
The task of unpaired image-to-image translation is highly challenging du...
This paper investigates the role of saliency to improve the classificati...
The usage of both off-the-shelf and end-to-end trained deep networks hav...
Deep image translation methods have recently shown excellent results,
ou...
Transferring the knowledge of pretrained networks to new domains by mean...
We present a semantic part detection approach that effectively leverages...
Semantic object parts can be useful for several visual recognition tasks...
Object class detectors typically apply a window classifier to all the wi...