7cce53cf90577442771720a370c3c723-Reviews.html

Paper 1048 proposes a system for large-scale zero-shot visual recognition. It consists of the following steps: (1) Learn an embedding of a large number of words in a Euclidean space. The 1,000 categories are a subset of the'large number of words' of step (1). Replace it by the word embeddings and add a layer to map the core visual model output to the word embeddings. On the positive side: The paper is well written and reads easily.