The composed video retrieval (CoVR) task is a new task, where the goal is to find a video that matches both a query image and a query text. The query image represents a visual concept that the user is interested in, and the query text specifies how the concept should be modified or refined. For example, given an image of a fountain and the text _during show at night_, the CoVR task is to retrieve a video that shows the fountain at night with a show.

RAM adopts RNNs and reinforcement learning (RL) to make the network learn where to pay attention.

Recurrent Models of Visual Attention

CoVR

CoVR: Learning Composed Video Retrieval from Web Video Captions

Multi-heads of both self and cross attentions

Source	CoVR: Learning Composed Video Retrieval from Web Video Captions
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com