Deep Multimodal Distance Metric Learning Using Click Constraints for Image Ranking

By Jun Yu, Xiaokang Yang, Fei Gao, Dacheng Tao. IEEE Transactions on Cybernetics, 2017

352 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3b913a704754465b268f86f82bfebc993b9bae25

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. Gan Sun
2. Xiaowei Xu
3. Jian Cheng
4. Ming-Hsuan Yang
5. Paul L. Rosin
6. Stylianos Asteriadis
7. Jufeng Yang
8. Maria Brbic

In Computer Vision and Pattern Recognition

1. Jian Cheng
2. Shiv Ram Dubey
3. Jufeng Yang
4. Ji Liu
5. Gan Sun
6. Xiangyu He
7. Peisong Wang
8. Qiang Chen

Citations in the corpus

• Multi-view low-rank sparse subspace clustering (2017, methodology): “The method in [38] relies on learning a linear projection matrix for each view separately.”
• SpatialFlow: Bridging All Tasks for Panoptic Segmentation (2019, background): “These methods have dramatically improved the state-of-the-art in many vision tasks, including image recognition[23], [25], [26], [27], [28], [29], [30], image retrieval [31], [32], metric learning [33], [34], [35], object detection [36], [37], [19], image segmentation [38], [39], [4], human pose est”
• Lifelong Metric Learning (2017, background): “To the best of our knowledge, seeking a better distance metric through learning with a training dataset is at the key issue of of most state-of-the-art single metric learning models [13], [14], [15].”
• Multimodal and Temporal Perception of Audio-visual Cues for Emotion Recognition (2019, background): “correlation-based models [22] and distance and similarity-based models [23]) and multi-view representation fusion (e.”
• A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, background): “learning for image search [92], distance metric learning for image ranking [93] and deep structure-preserving embeddings with visual attention [94].”
• Deep Metric Learning: A Survey (2019, background): “However, these approaches are not successful enough to reveal nonlinear knowledge of the data [21].”
• Dynamic Match Kernel With Deep Convolutional Features for Image Retrieval (2018, methodology): “In recent years, several methods have exploited deep CNNs for image retrieval [37]–[40], thanks to their excellent property”