Irregular-shaped texts bring challenges to Scene Text Detection (STD).
A...
To pursue comprehensive performance, recent text detectors improve detec...
Randomized experiments, or "A/B" tests, remain the gold standard for
eva...
Unlabeled data learning has attracted considerable attention recently.
H...
This paper aims to caption daily life –i.e., to create a textual descrip...
Crowd analysis via computer vision techniques is an important topic in t...
Cross-domain crowd counting (CDCC) is a hot topic due to its importance ...
Person Re-Identification (ReID) aims to recognize a person-of-interest a...
For pixel-level crowd understanding, it is time-consuming and laborious ...
Recently, crowd counting using supervised learning achieves a remarkable...
With the development of deep neural networks, the performance of crowd
c...
The article considers strategies of coalitions that are based on intelli...
Recently, crowd counting is a hot topic in crowd analysis. Many CNN-base...
Pay-it-forward reciprocity encourages the spread of prosocial behavior.
...
In this work, we investigate black-box optimization from the perspective...
In weakly-supervised temporal action localization, previous works have f...
In this paper, we present iDVO (inertia-embedded deep visual odometry), ...
Although traffic sign detection has been studied for years and great pro...
Road detection from the perspective of moving vehicles is a challenging ...
Street scene understanding is an essential task for autonomous driving. ...
Action Prediction is aimed to determine what action is occurring in a vi...
Human actions captured in video sequences contain two crucial factors fo...
Anomaly detection from a driver's perspective when driving is important ...
Processing and fusing information among multi-modal is a very useful
tec...
Forward Vehicle Collision Warning (FCW) is one of the most important
fun...
Video-based vehicle detection and tracking is one of the most important
...
Recently, counting the number of people for crowd scenes is a hot topic
...
Developing targeted therapies based on patients' baseline characteristic...
Predicting keywords performance, such as number of impressions, click-th...
We consider the single image super-resolution problem in a more general ...
To obtain effective pedestrian detection results in surveillance video, ...
Recent empirical studies show that the performance of GenProg is not
sat...
Gift giving is a ubiquitous social phenomenon, and red packets have been...
In this paper, we investigate a weakly-supervised object detection frame...
In this report, we suggest nine test problems for multi-task multi-objec...