Unsupervised Learning of Visual Sense Models for Polysemous Words
By Kate Saenko, Trevor Darrell. 2008
71 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Li Fei-Fei
- Dacheng Tao
- Xiaogang Wang
- Andrew Zisserman
- Jitendra Malik
- Abhinav Kumar Gupta
In Representation & Self-Supervised Learning
- Trevor Darrell
- Kristen Grauman
- Andrew Zisserman
- Abhinav Kumar Gupta
- Andrea Vedaldi
- Ali Farhadi
- Mathieu Salzmann
- Xinlei Chen
Citations in the corpus
- Webly Supervised Learning of Convolutional Networks (2015, background): “In fact, they are so clean that they are biased towards iconic images where a single object is centered with a clean background in a canonical viewpoint [31, 40, 3, 30].”
- Sense discovery via co-clustering on images and text (2015, methodology): “[37, 38] presented a model for learning visual senses using images clustered using text, but rely on WordNet’s sense inventory.”
- Deep Classifiers from Image Tags in the Wild (2015, background): “Some tags have multiple distinct meanings [26], e.”
- Harvesting Image Databases from the Web (2007, background): “Recent work [26] addresses the polysemy problem directly and a combination with our work would be interesting.”
- BabyTalk: Understanding and Generating Simple Image Descriptions (2013, background): “Saenko and Darrell [36] learn visual sense models for polysemous words (e.g., " jaguar " ) from textual descriptions on Wikipedia.”
- Baby talk: Understanding and generating simple image descriptions (2011, background): “Saenko and Darrell [36] learn visual sense models for polysemous words (e.”
- Discovering Attribute Shades of Meaning with the Crowd (2015, background): “Some work bridging text and visual analysis aims to cluster Web images according to distinct senses (Barnard et al. 2006; Loeff et al. 2006; Saenko and Darrell 2008; Berg and Forsyth 2006).”
- Learning to Recognize Objects from Unseen Modalities (2010, methodology): “In [4, 5] latent Dirichlet allocation (LDA) was used to perform visual sense disambiguation using unsupervised text and images.”