Corpus ID: 588692

Sherlock: Scalable Fact Learning in Images

@inproceedings{Elhoseiny2017SherlockSF,
  title={Sherlock: Scalable Fact Learning in Images},
  author={Mohamed Elhoseiny and S. Cohen and W. Chang and Brian L. Price and A. Elgammal},
  booktitle={AAAI},
  year={2017}
}
We study scalable and uniform understanding of facts in images. Existing visual recognition systems are typically modeled differently for each fact type such as objects, actions, and interactions. We propose a setting where all these facts can be modeled simultaneously with a capacity to understand unbounded number of facts in a structured way. The training data comes as structured facts in images, including (1) objects (e.g., $ $), (2) attributes (e.g., $ $), (3) actions (e.g., $ $), and (4… Expand
17 Citations
Relationship Proposal Networks
  • 60
  • PDF
Learning to detect visual relations
  • Highly Influenced
  • PDF
Weakly-Supervised Learning of Visual Relations
  • 119
  • PDF
Exploring the Challenges towards Lifelong Fact Learning
  • 10
  • PDF
Detecting Visual Relationships with Deep Relational Networks
  • Bo Dai, Yuqi Zhang, D. Lin
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
  • 274
  • PDF
Language guided visual perception
Continual learning in cross-modal retrieval
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 76 REFERENCES
Automatic Annotation of Structured Facts in Images
  • 7
  • PDF
Zero-Shot Learning via Visual Abstraction
  • 69
  • PDF
DeViSE: A Deep Visual-Semantic Embedding Model
  • 1,585
  • PDF
Learning Everything about Anything: Webly-Supervised Visual Concept Learning
  • 268
  • PDF
Grouplet: A structured image representation for recognizing human and object interactions
  • B. Yao, Li Fei-Fei
  • Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
  • 322
  • Highly Influential
  • PDF
Zero-Shot Learning by Convex Combination of Semantic Embeddings
  • 646
  • PDF
Zero-Shot Learning Through Cross-Modal Transfer
  • 1,006
  • PDF
Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images
  • 485
  • PDF
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions
  • 295
  • PDF
Show and tell: A neural image caption generator
  • 3,813
  • PDF
...
1
2
3
4
5
...