Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval. (arXiv:2104.00650v2 [cs.CV] UPDATED)

Our objective in this work is video-text retrieval - in particular a joint
embedding that enables efficient text-to-video retrieval. The challenges in
this area include the design of the visual architecture and the nature of the
training data, in that the available large scale video-text training datasets,
such as HowTo100M, are noisy and hence competitive performance is achieved only
at scale through large amounts of compute. We address both these challenges in
this paper. We propose an end-to-end trainable model …

arxiv cv encoder image retrieval time video