Image Retrieval using Scene Graphs
Deep Visual-Semantic Alignments for Generating Image Descriptions
Best of both worlds: human-machine collaboration for dense object annotation
Deep Fragment Embeddings for Bidirectional Image-Sentence Mapping
Video Event Understanding using Natural Language Descriptions
===========
Ref:
http://vision.stanford.edu/publications.html
Deep Visual-Semantic Alignments for Generating Image Descriptions
Best of both worlds: human-machine collaboration for dense object annotation
Deep Fragment Embeddings for Bidirectional Image-Sentence Mapping
Video Event Understanding using Natural Language Descriptions
===========
Ref:
http://vision.stanford.edu/publications.html