Efficient Large-Scale Structured Learning

By Steve Branson, Oscar Beijbom, Serge J. Belongie. 2013

48 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Optimization & Training

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. Jiashi Feng
2. Shuicheng Yan
3. Serge J. Belongie
4. Simon Lacoste-Julien
5. Jean-Baptiste Alayrac
6. Pietro Perona
7. Li Fei-Fei
8. Grant Van Horn

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jiashi Feng
3. Dacheng Tao
4. Cordelia Schmid
5. Shuicheng Yan
6. Yi Yang
7. Trevor Darrell
8. Ming-Hsuan Yang

In Optimization & Training

1. Jean-Baptiste Alayrac
2. Simon Lacoste-Julien
3. Jiashi Feng
4. Anton Osokin
5. Shuicheng Yan
6. Puneet Kumar Dokania
7. Isabella Lukasewitz
8. Pietro Perona

Citations in the corpus

• Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “Caching the oracle calls was shown do deliver significant speed-ups when the oracle is expensive, e.g., in the case of 1Independently, Branson et al. (2013) proposed their SVM-IS algorithm which is equivalent to BCFW in some scenarios. ar X iv :1 60 5.”
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “Implementation Details: We used the DPM implementation from [11], which outputs predicted 2D locations and visibility of 13 semantic part keypoints.”
• A survey on deep learning-based fine-grained object classification and semantic segmentation (2017, methodology): “In training, the pose normalized net uses the DPM [25] to predict 2D locations and the visibility of 13 semantic part keypoints or directly uses the pre-provided object bounding box and part annotations to learn the pose prototypes.”