Modeling and Learning Distributed Word Representation with Metadata for Question Retrieval

Weakly Supervised Fine-Grained Categorization with Part-Based Image Representation Abstract In this paper, we propose a fine-grained image categorization system with easy deployment. We do not use any object/part annotation (weakly supervised) in the training or in the testing stage, but only class labels for training images. Fine-grained image categorization aims to classify objects with only subtle distinctions (e.g., two breeds of dogs that look alike). Most […]