Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold

By Xikang Zhang, Yin Wang, Mengran Gou, Mario Sznaier, Octavia I. Camps. 2016

95 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

How researchers see this paper

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

In Biomedical Engineering

1. Guillermo Garcia-Hernando
2. Tae-Kyun Kim
3. Vittorio Murino
4. Pietro Morerio
5. Jacopo Cavazza
6. Yui Man Lui

In Computer Vision and Pattern Recognition

1. Guillermo Garcia-Hernando
2. Pietro Morerio
3. Jacopo Cavazza
4. Tae-Kyun Kim
5. Vittorio Murino
6. Xiaogang Wang
7. Dacheng Tao
8. Yi Yang

In Human-Computer Interaction

1. Guillermo Garcia-Hernando
2. Tae-Kyun Kim
3. Vittorio Murino
4. Pietro Morerio
5. Jacopo Cavazza
6. Yui Man Lui

Citations in the corpus

• When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “Alternatively, Hankel matrices [22, 43] have been attested to be extremely effective in the field of action recognition from skeletal data, either being paired with Hidden Markov Models [22] or with a prototype-based nearest neighbor classification on the Riemannian manifold [43].”
• Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection (2016, methodology): “0%, but inferior to the offline approach of Gram matrix [37], 94.”