clip 5 deep-learning 4 retrieval 2 pytorch 2 multimodal 1 faiss 1 docker 1 django 1 universal-embedding 1 multimodel-large-language-model 1 large-language-models 1 information-retrieval 1 image-search 1 image-retrieval 1 composed-image-retrieval 1 zero-shot-classification 1 multi-modal 1 linear-classification 1 image-generation 1 retrieval-augmented-generation 1 tf-idf 1 yolo 1 bert 1 fewshot-learning 1 knowledge-distillation 1 knowledge-pretraining 1 machine-learning 1 nlp 1 pretrained-models 1 text-classification 1 text-to-image-synthesis 1 transfer-learning 1 transformers 1 cross-modal-retrieval 1 fine-grained-classification 1 diffusion-models 1 instance-segmentation 1 open-vocabulary 1 open-vocabulary-segmentation 1 open-vocabulary-semantic-segmentation 1 open-world-classification 1 open-world-object-detection 1 panoptic-segmentation 1 semantic-segmentation 1 zero-shot-learning 1 graph-neural-networks 1 fastapi 1 open-ai 1 reactjs 1 search-engine 1 remote-sensing 1 semantic-localization 1 efficient-deep-learning 1 framework 1 image-captioning 1 image-text-retrieval 1 model-acceleration 1 multimodal-learning 1 token-ensemble 1 token-matching 1 transformer 1 vision-language-transformer 1 visual-question-answering 1 visual-reasoning 1 flickr30k 1 flickr8k 1