The twenty-first century is undergoing a fundamental transition in the way things are created
and services are provided. The digitalization of services has resulted in a compelling, major …

Current object detectors are limited in vocabulary size due to the small scale of detection
datasets. Image classifiers, on the other hand, reason about much larger vocabularies, as …

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …

Despite the recent success of long-tailed object detection, almost all long-tailed object
detectors are developed based on the two-stage paradigm. In practice, one-stage detectors …

One-stage long-tailed recognition methods improve the overall performance in a" seesaw"
manner, ie, either sacrifice the head's accuracy for better tail classification or elevate the …

Can our video understanding systems perceive objects when a heavy occlusion exists in a
scene? To answer this question, we collect a large-scale dataset called OVIS for occluded …

Recently proposed decoupled training methods emerge as a dominant paradigm for long-
tailed object detection. But they require an extra fine-tuning stage, and the disjointed …

Deep learning-based dense object detectors have achieved great success in the past few
years and have been applied to numerous multimedia applications such as video …