What Are the Current Approaches for Utilizing Temporal Information in Object Detection?

Hello everyone, I'm currently working on a project that involves object detection in video sequences. I've noticed that many state-of-the-art object detection algorithms primarily focus on individual frames and do not incorporate temporal information between frames for improved accuracy and efficiency. Are there any popular methods or frameworks that take advantage of this kind of temporal information? Additionally, are there any notable papers or resources that delve into this topic? Any recommendations for further reading would be greatly appreciated. Thanks …

accuracy algorithms art computervision current detection efficiency focus frameworks hello information popular project state temporal video