Large-scale labeled data are generally required to train deep neural networks in order to
obtain better performance in visual feature learning from images or videos for computer …

Due to its capacity to gather vast, high-level data about human activity from wearable or
stationary sensors, human activity recognition substantially impacts people's day-to-day …

The success of deep neural networks generally requires a vast amount of training data to be
labeled, which is expensive and unfeasible in scale, especially for video collections. To …

There are many deep learning algorithms currently used in ship supervision, but they
generally have the problems of insufficient target detection speed and accurate identification …

The underlining task for fine-grained image recognition captures both the inter-class and
intra-class discriminate features. Existing methods generally use auxiliary data to guide the …

Most approaches to automatic facial action unit (AU) detection consider only spatial
information and ignore AU dynamics. For humans, dynamics improves AU perception. Is …

Modeling and reasoning of the interactions between multiple entities (actors and objects)
are beneficial for the action recognition task. In this paper, we propose a 3D Deformable …

In this paper, we propose a 3D Convolutional Neural Network (3DCNN) based multi-stream
framework to recognize American Sign Language (ASL) manual signs (consisting of …

Underwater object detection involves the activity of multiple object identification within a
dynamic and noisy environment. Such task is challenging due to the inconsistency of …

In recent years, vehicle type detection has had an important role in traffic management. A
lightweight detection network based on multiscale ghost convolution called G‐YOLOX is …