Transformers have rapidly gained popularity in computer vision, especial...
We propose a new method for producing color images from sketches. Curren...
Object detectors are conventionally trained by a weighted sum of
classif...
The prevalent approach in self-supervised image generation is to operate...
We present StreamDEQ, a method that infers frame-wise representations on...
Ground-truth depth, when combined with color data, helps improve object
...
This paper presents Mask-aware Intersection-over-Union (maIoU) for assig...
We propose Rank Sort (RS) Loss, as a ranking-based loss function to ...
In this paper, we present a new bottom-up one-stage method for whole-bod...
This paper presents HoughNet, a one-stage, anchor-free, voting-based,
bo...
In this study, we introduce a measure for machine perception, inspired b...
We introduce a new method for generating color images from sketches or e...
Convolutional neural networks (CNNs) are able to attain better visual
re...
Despite being widely used as a performance measure for visual detection
...
We propose average Localization-Recall-Precision (aLRP), a unified, boun...
Current anchor-free object detectors label all the features that spatial...
This paper presents HoughNet, a one-stage, anchor-free, voting-based,
bo...
In this paper, we explore illustrations in children's books as a new dom...
Two-stage deep object detectors generate a set of regions-of-interest (R...
In this paper, we present a comprehensive review of the imbalance proble...
Training accurate 3D human pose estimators requires large amount of 3D
g...
In this paper, we present MultiPoseNet, a novel bottom-up multi-person p...
Average precision (AP), the area under the recall-precision (RP) curve, ...
This paper is aimed at creating extremely small and fast convolutional n...
We present a foveated object detector (FOD) as a biologically-inspired
a...
In this paper, we present a new multiple instance learning (MIL) method,...