In this paper we revisit the efficacy of knowledge distillation as a fun...
Semantic segmentation from aerial views is a vital task for autonomous d...
While monocular depth estimation (MDE) is an important problem in comput...
Humans exhibit incredibly high levels of multi-modal understanding -
com...
Monocular depth estimation (MDE) aims to transform an RGB image of a sce...
In the light of recent analyses on privacy-concerning scene revelation f...
In this paper, we address the problem of estimating scale factors betwee...
Despite the empirical success of knowledge distillation, there still lac...
We present an efficient alternative to the convolutional layer through
u...
Automatically detecting graspable regions from a single depth image is a...
In this paper, we address the problem of camera pose estimation in outdo...
State-of-the-art performance for many emerging edge applications is achi...
Accurate real depth annotations are difficult to acquire, needing the us...
In this paper, we propose an approach for filter-level pruning with
hier...
Depth completion aims to predict a dense depth map from a sparse depth i...
We study the image retrieval problem at the wireless edge, where an edge...
Recent works show that local descriptor learning benefits from the use o...
In this paper, we present a novel approach that exploits the information...
Local feature extraction remains an active research area due to the adva...
In this paper we present an approach and a benchmark for visual reasonin...
Person re-identification (re-ID) is a very active area of research in
co...
We propose a joint transmission-recognition scheme for efficient inferen...
Recent works in deep-learning have shown that utilising second-order
inf...
Deep neural networks have demonstrated state-of-the-art performance for
...
We propose a domain adaptation approach for object detection. We introdu...
Motivated by surveillance applications with wireless cameras or drones, ...
We introduce a novel approach for keypoint detection task that combines
...
Inspired by the effectiveness of adversarial training in the area of
Gen...
Partial person re-identification involves matching pedestrian frames whe...
In interventional radiology, short video sequences of vein structure in
...
In this paper we propose a new approach to person re-identification usin...
Building upon recent Deep Neural Network architectures, current approach...
In this paper we propose a new approach for learning local descriptors f...