Drone-based vehicle detection aims at detecting vehicle locations and categories in aerial
images. It empowers smart city traffic management and disaster relief. Researchers have …

Multispectral pedestrian detection has received great attention in recent years as
multispectral modalities (ie color and thermal) can provide complementary visual …

Although the visual appearances of small-scale objects are not well observed, humans can
recognize them by associating the visual cues of small objects from their memorized …

Multispectral pedestrian detection is an important task due to its critical role in a wide
spectrum of applications. Basically, the complementary information from color and thermal …

Conventional object detectors often encounter remarkable performance drops due to the
domain shift caused by environmental changes. However, labeling sufficient training data …

Multispectral pedestrian detection is attractive for around-the-clock applications due to the
complementary information between RGB and thermal modalities. However, current models …

With the ease of accessing large unlabeled datasets, studies on semi-supervised learning
for object detection (SSOD) have become increasingly popular. Among these SSOD studies …

Class imbalance occurs in the datasets with a disproportionate ratio of observations. The
class imbalance problem drives the detection and classification systems to be more biased …

The one-stage object detector has recently attracted extensive interest due to its high
detection efficiency and simple framework. However, one-stage detectors suffer much from …

The parallel branches with independent optimized classification and localization capabilities
are widely used in single-stage object detection. Defects such as feature conflicts, low level …