Object detectors are conventionally trained by a weighted sum of
classif...
The rise of simulation environments has enabled learning-based approache...
Logo retrieval is a challenging problem since the definition of similari...
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 ...
Despite being widely used as a performance measure for visual detection
...
Most state-of-the-art approaches for Facial Action Unit (AU) detection r...
Deep neural network approaches have demonstrated high performance in obj...
We propose average Localization-Recall-Precision (aLRP), a unified, boun...
In this work, we combine 3D convolution with late temporal modeling for
...
To date, endowing robots with an ability to assess social appropriatenes...
Recognition of expressions of emotions and affect from facial images is ...
Robots collaborating with humans in realistic environments will need to ...
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...
Humans frequently use referring (identifying) expressions to refer to
ob...
Referring to objects in a natural and unambiguous manner is crucial for
...
Average precision (AP), the area under the recall-precision (RP) curve, ...
Scene modeling is very crucial for robots that need to perceive, reason ...
Scene models allow robots to reason about what is in the scene, what els...
There have been several attempts at modeling context in robots. However,...
Context is an essential capability for robots that are to be as adaptive...
Drone detection is the problem of finding the smallest rectangle that
en...
Trademark retrieval (TR) has become an important yet challenging problem...