Unsupervised Visual Representation Learning by Graph-Based Consistent Constraints
By Dong Li, Wei-Chih Hung, Jia-Bin Huang, Shengjin Wang, Narendra Ahuja, Ming-Hsuan Yang. 2016
62 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Yingli Tian
- Xiaodong Yang
- Longlong Jing
- Hsin-Ying Lee
- Xiangyuan Lan
- Jia-Bin Huang
- Ming-Hsuan Yang
- Pong Chi Yuen
In Computer Vision and Pattern Recognition
- Ming-Hsuan Yang
- Luc Van Gool
- Dacheng Tao
- Andrew Zisserman
- Yi Yang
- Andrea Vedaldi
- Cordelia Schmid
- Xiaogang Wang
Citations in the corpus
- Unsupervised Embedding Learning via Invariant and Spreading Instance Feature (2019, neutral): “9 Unsupervised Learning Cyclic [25] 40.”
- Unsupervised Representation Learning by Sorting Sequences (2017, methodology): “In addition to using only individual images, several recent directions have been explored by grouping visual entities using co-occurrence in space and time [13], using graph-based constraints [22], and crossmodal supervision from sounds [29].”
- Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction. (2018, methodology): “Li et al. propose to mine the positive and negative image pairs with graph constraints in the feature space and the mined pairs are used to train the network to learn visual features [27].”
- Self-supervised Spatiotemporal Feature Learning by Video Geometric Transformations (2018, methodology): “proposed to mine the positive and negative image pairs with graph constraints in the feature space and the mined pairs are used to train the network to learn visual features [21].”
- Mining on Manifolds: Metric Learning Without Labels (2018, methodology): “All methods expect for ours and cyclic match [30] use ground-truth labels during training.”
- Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild (2018, background): “Other approaches utilize the graph theory to exploit the relationship among different samples [3, 20].”
- Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey (2019, methodology): “Then a ConvNet is trained to recognize the cluster assignment [34], [44] or to recognize whether two imaged are from same cluster [43].”