Baselines for Image Annotation

217 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (2013, methodology): “…images with tags or keywords, methods which annotate unseen images with the tags of their nearest neighbors among training images are known to achieve competitive performance (Makadia et al., 2010), and similar methods have recently been proposed for image description (Ordonez et al., 2011).”
Choosing Linguistics over Vision to Describe Images (2012, neutral): “Phrase Annotation Another interesting application of our approach is phrase annotation ; i.e., we can annotate images with phrase(s) instead of just keywords (Makadia, Pavlovic, and Kumar 2010; Guillaumin et al. 2009).”
Content-based visual search learned from social media (2012, methodology): “Instead of feature concatenation, another method is to combine visual similarities of the individual features [41, 80, 128].”
Automatic Caption Generation for News Images (2013, background): “Approaches to image annotation are too numerous to describe exhaustively; see [18] for an overview.”
KDGAN: Knowledge Distillation with Generative Adversarial Networks (2018, methodology): “First, we compareC in KDGAN with KNN [32], TPROP [19], TFEAT [11], and REXMP [28].”