Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied detection. However, these perform poorly for blurry low-contrast videos. Additionally, they fail account contextual relationships between frame-level results. To address challenges, we propose mo...

• A type of shallow modules are proposed to directly predict the feature flow for alignment in a single network. Self-supervision learning is introduced further improve quality predicted flow. new state-of-the-art performance shown by comparing with other methods, while fast inference speed maintained. Optical flow, which expresses pixel displacement, widely used many computer vision tasks prov...

We present an approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation. The approach extracts temporally consistent object tubes based on an off-the-shelf detector. Besides the class label for each tube, this provides a location prior that is independent of motion. For the final video segmentation, we combin...

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial frame-level variability, even in videos that appear smooth to the eye. Additionally, video datasets tend to have sparsely annotated frames. We present a new f...

The purpose of our work is to detect the target human concerned in video. For security considerations, event detection in video has potential economic and social needs. Human concerned object detecting is very helpful for event detection. In some emergency or special events, people will focus on specific object. We need locate human body and face, detect the sight direction, and determine the o...