Abstract: Multi-modal and cross-modal retrieval has garnered increasing attention from researchers recently, owing to its potential to transcend the limitations imposed by traditional retrieval ...

Finally, the code for the web UI client used in the Moshi demo is provided in the client/ directory. If you want to fine tune Moshi, head out to kyutai-labs/moshi ...

Abstract: Text-to-image person search is challenging due to the cross-scale correspondences and information inequality between modalities. Specifically, images and text are complexly linked at ...