See all by looking at a few: Sparse modeling for finding representative objects

By Ehsan Elhamifar, Guillermo Sapiro, René Vidal. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

405 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/e1415b6d848bdb6ff8e4cb7f0ebf948870b71183

How researchers see this paper

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

In Computational Mechanics

1. René Vidal
2. Ehsan Elhamifar
3. Julien Mairal
4. Zaïd Harchaoui
5. Nicolas Gillis
6. Ishan Misra
7. Kaiyang Zhou
8. Yu Qiao

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Jitendra Malik
3. Yu Qiao
4. Dacheng Tao
5. Cordelia Schmid
6. Ming-Hsuan Yang
7. Andrea Vedaldi
8. Trevor Darrell

In Media Technology

1. Nicolas Gillis
2. Yu Qiao
3. Julien Mairal
4. Qiang Zhou
5. Qi Zhao
6. Kaiyang Zhou
7. Ehsan Elhamifar
8. Martial Hebert

Citations in the corpus

• Fast and Robust Archetypal Analysis for Representation Learning (2014, background): “Data visualization has now become an important topic, especially regarding image databases from the Internet [6], or videos [8].”
• Flexible Clustered Multi-Task Learning by Learning Representative Tasks (2016, methodology): “Motivated by representatives/exemplars used in dictionary learning and data clustering [18], [19], this work proposes a new approach for clustered multi-task learning.”
• Sparse Subspace Clustering: Algorithm, Theory, and Applications (2012, background): “Hence, minimizing (28) corresponds to minimizing the number of nonzero rows of C [61], [62], [63], i.”
• Generating Diverse Image Datasets with Limited Labeling (2016, methodology): “, l2,1 regularizer is to induce row level sparsity in representative selection [8, 11], whereas the second constraint tries to select images that are less correlated with images in current dataset.”
• Data-driven exemplar model selection (2014, methodology): “Pruning baselines: We use sparse modeling [9] on HOG features [6].”
• Sparse Subspace Clustering: Algorithm, Theory, and Applications (2013, background): “Hence, minimizing (28) corresponds to minimizing the number of nonzero rows of C [61], [62], [63], i.”
• Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “To compare with other approaches, we implement Uniform sampling, K-medoids and Dictionary selection (Elhamifar, Sapiro, and Vidal 2012) by ourselves.”
• The Why and How of Nonnegative Matrix Factorization (2014, methodology): “Separability has also been used successfully in blind source separation [95, 22], video summarization and image classification [40], and foreground-background separation in computer vision [76].”
• Viewpoint-Aware Video Summarization (2018, methodology): “To investigate the effectiveness of the proposed method, we compared it with other baseline methods as follows: Sparse Modeling Representative Selection (SMRS) [7]: SMRS computes a representation of video clips such that a small number of clips can represent an entire video by group sparse regulariz”