User Conditional Hashtag Prediction for Images

By Emily L. Denton, Jason Aaron Edward Weston, Manohar Paluri, Lubomir D. Bourdev, Rob Fergus. 2015

89 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

1. Jason Aaron Edward Weston
2. Quoc V. Le
3. Mohit Bansal
4. Jianfeng Gao
5. Armand Joulin
6. Abhinav Kumar Gupta
7. Yoshua Bengio
8. Caiming Xiong

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Trevor Darrell
4. Abhinav Kumar Gupta
5. Cordelia Schmid
6. Xiaogang Wang
7. Jitendra Malik
8. Andrew Zisserman

In Natural Language Processing

1. Jason Aaron Edward Weston
2. Kurt Shuster
3. Antoine Bordes
4. Y-Lan Boureau
5. Sebastian Riedel
6. Mohit Bansal
7. Luke S. Zettlemoyer
8. Douwe Kiela

Citations in the corpus

• Exploring the Limits of Weakly Supervised Pretraining (2018, background): “Other studies on hashtag prediction [42] do not train convolutional networks from scratch, but train linear classifiers to predict relevant hashtags from pre-defined image features.”
• Learning Visual Features from Large Weakly Supervised Data (2015, background): “Denton et al. [8] learn (user-conditional) embeddings of images and hashtags on a large collection of Instagram photos and hashtags.”
• Deep Joint Entity Disambiguation with Local Neural Attention (2017, methodology): “We therefore use a neural network with two fully connected layers of 100 hidden units and ReLU non-linearities, which we regularize as suggested in (Denton et al., 2015) by constraining the sum of squares of all weights in the linear layer.”
• Engaging Image Captioning via Personality (2018, methodology): “by using user level features such as location and age [10] or knowledge of the reader’s active vocabulary [42].”
• Separating Self-Expression and Visual Content in Hashtag Supervision (2017, methodology): “The most closely related to our study is [5], which studies hashtag prediction conditioned on image and user features.”
• ClusterFit: Improving Generalization of Visual Representations (2019, methodology): “Weakly Supervised Learning: Training ConvNets on very large, weakly supervised images by defining the proxy tasks using the associated meta-data [11, 20, 24, 31, 36, 38, 48, 51–53 , 56] has shown By contrast, our approach does not adhere to a particular target task and leverages all the data, since,…”
• Attend to You: Personalized Image Captioning with Context Sequence Memory Networks (2017, background): “[2] develop a CNN model that predicts hashtags from image content and user information.”