Hyperbolic space is becoming a popular choice for representing data due ...
This paper investigates the problem of scene graph generation in videos ...
Deep learning in hyperbolic space is quickly gaining traction in the fie...
This work considers supervised learning to count from images and their
c...
Mixup is a widely adopted strategy for training deep networks, where
add...
Deep representation learning is a ubiquitous part of modern computer vis...
This paper introduces an end-to-end residual network that operates entir...
Graph neural networks have shown to learn effective node representations...
This paper introduces the task of visual named entity discovery in video...
Maximizing the separation between classes constitutes a well-known induc...
The goal of this paper is to bypass the need for labelled examples in
fe...
For image segmentation, the current standard is to perform pixel-level
o...
This work addresses the problem of recognizing action categories in vide...
This paper investigates the problem of zero-shot action recognition, in ...
Video relation detection forms a new and challenging problem in computer...
This paper strives to classify and detect the relationship between objec...
This paper strives to generate a synthetic computed tomography (CT) imag...
The deep image prior has demonstrated the remarkable ability that untrai...
Hyperbolic space has become a popular choice of manifold for representat...
The goal of this paper is guided image filtering, which emphasizes the
i...
This work strives for the classification and localization of human actio...
This paper introduces the task of few-shot common action localization in...
This work proposes a metric learning approach for self-supervised scene ...
This paper introduces data augmentation for point clouds by interpolatio...
This paper strives to localize the temporal extent of an action in a lon...
This paper introduces open cross-domain visual search, where categories ...
The shift operation was recently introduced as an alternative to spatial...
This paper aims to count arbitrary objects in images. The leading counti...
This paper introduces hyperspherical prototype networks, which unify
reg...
The goal of this paper is spatio-temporal localization of human actions ...
This paper strives for spatio-temporal localization of human actions in
...
We aim for zero-shot localization and classification of human actions in...
The goal of this paper is to determine the spatio-temporal location of
a...
We strive for spatio-temporal localization of actions in videos. The
sta...
This paper strives for video event detection using a representation lear...
This work aims for image categorization using a representation of distin...