We present a holistic data-driven approach to image description generation, exploiting the vast amount of (noisy) parallel image data and associated natural language descriptions ...
Polina Kuznetsova, Vicente Ordonez, Alexander C. B...
In order to understand similarity between images, recent research has focused on adaptable searches [9] and fuzzy queries [4]. However, one of the best means for determining simil...
Gregory D. Speegle, Allen M. Gao, Shaowen Hu, Le G...
This paper presents a strategy for shape-based image retrieval in which moment invariants form a feature vector to describe the shape of an object. Fuzzy k-means clustering is use...
In this paper, we present a method to retrieve natural images by sketch query. To measure the similarity between the sketch and an image, relevant regions are first located in th...
Jinyi Yao, Mingjing Li, Zhiwei Li, Lei Zhang, Wei-...
The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...