Discovering and Leveraging Visual Structure for Large-Scale Recognation
Explore this paper's citation graph
Summary
This dissertation proposes to discover and harness this structure in large amounts of visual data and incorporate it as constraints in large-scale semi-supervised learning algorithms to improve visual recognition systems.
- Published
- 2017-01-01
- Cited by
- 0
- References
- 325
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:195979170
References
- Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- Learning Dictionaries for Information Extraction by Multi-Level Bootstrapping
- Unsupervised Learning of Visual Representations Using Videos
- R-CNNs for Pose Estimation and Action Detection
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- FlowNet: Learning Optical Flow with Convolutional Networks
- Learning to Segment Object Candidates
- Contextual Action Recognition with R*CNN
- Learning to predict where humans look
- Toward an Architecture for Never-Ending Language Learning
- Building the gist of a scene: the role of global image features in recognition.
- Understanding the difficulty of training deep feedforward neural networks
- Human Pose Estimation with Iterative Error Feedback
- Learning and example selection for object and pattern detection
- Fracking Deep Convolutional Image Descriptors
- The ACRONYM Model-Based Vision System
- Cortical feedback improves discrimination between figure and background by V1, V2 and V3 neurons
- Computational Baby Learning
- Very Deep Convolutional Networks for Large-Scale Image Recognition
Cited by
No citing papers recorded for this paper.
Related papers
No related papers recorded.