Sense discovery via co-clustering on images and text

By Xinlei Chen, Alan Ritter, Abhinav Kumar Gupta, Tom Michael Mitchell. 2015

28 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal 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

1. Abhinav Kumar Gupta
2. Luc Van Gool
3. Xinlei Chen
4. Trevor Darrell
5. Dacheng Tao
6. Jitendra Malik
7. Xiaogang Wang
8. Alan L. Yuille

In Multimodal Learning

1. Xinlei Chen
2. Abhinav Kumar Gupta
3. Frank Keller
4. Mirella Lapata
5. Spandana Gella
6. Devi Parikh
7. Yansong Feng
8. C. Lawrence Zitnick

Citations in the corpus

• Webly Supervised Learning of Convolutional Networks (2015, background): “ we did observe some interesting semantic drift between PASCAL categories and Google categories. For example, bicycle can also mean motorcycle on Google. Sense disambiguation for this polysemous word [45, 9] is needed here. Also note that our person detector is confused with cars, we suspect it is b”
• Unsupervised Visual Sense Disambiguation for Verbs using Multimodal Embeddings (2016, methodology): “VSD for nouns is helped by resources such as ImageNet (Deng et al., 2009), a large image database containing 1.4 million images for 21,841 noun synsets and organized according to the WordNet hierarchy.”