Search results with tag "By deep"

MSR-VTT: A Large Video Description Dataset for Bridging ...

rived from the image to model the embedding between text and image [13]. Hao et al. propose a three-step approach to image captioning including word detection by multiple instance learning, sentence generation by language model-s, and sentence reranking by deep embedding [8]. Similar works have started to adopt RNNs for generating image de-

  Image, Learning, Deep, By deep