Optical flow is an indispensable building block for various important computer vision tasks,
including motion estimation, object tracking, and disparity measurement. In this work, we …

Video object detection needs to solve feature degradation situations that rarely happen in
the image domain. One solution is to use the temporal information and fuse the features from …

Remote sensing (RS) spatiotemporal prediction aims to infer future trends from historical
spatiotemporal data, eg, videos and time-series images, which has a broad application …

Transformers have rapidly gained popularity in computer vision, especially in the field of
object recognition and detection. Upon examining the outcomes of state-of-the-art object …

深度学习框架Transformer 具有强大的建模能力和并行计算能力, 目前基于Transformer
的目标检测算法已经成为研究的热点. 为了进一步探索目标检测的新思路, 新方向 …

Streaming perception is a fundamental task in autonomous driving that requires a careful
balance between the latency and accuracy of the autopilot system. However, current …

Video object detection needs to solve feature degradation situations that rarely happen in
the image domain. One solution is to use the temporal information and fuse the features from …

Due to the ever-changing shape and scale of ships, as well as the complex sea background,
accurately detecting multi-scale ships on the sea while considering real-time requirements …

Abstract Objects in videos are typically characterized by continuous smooth motion. We
exploit continuous smooth motion in three ways. 1) Improved accuracy by using object …

When deploying pre-trained video object detectors in real-world scenarios the domain gap
between training and testing data caused by adverse image conditions often leads to …