Online Multi-modal Person Search in Videos
This work addresses the need for real-time person search in applications like video organization and editing, offering a novel online approach that overcomes the limitations of offline methods.
The paper tackles the problem of searching for people in videos in real-time by proposing an online person search framework that uses a multimodal memory bank updated via reinforcement learning, achieving significant improvements over both online and offline methods on a large movie dataset.
The task of searching certain people in videos has seen increasing potential in real-world applications, such as video organization and editing. Most existing approaches are devised to work in an offline manner, where identities can only be inferred after an entire video is examined. This working manner precludes such methods from being applied to online services or those applications that require real-time responses. In this paper, we propose an online person search framework, which can recognize people in a video on the fly. This framework maintains a multimodal memory bank at its heart as the basis for person recognition, and updates it dynamically with a policy obtained by reinforcement learning. Our experiments on a large movie dataset show that the proposed method is effective, not only achieving remarkable improvements over online schemes but also outperforming offline methods.