One Shot Similarity Metric Learning for Action Recognition
By Orit Kliper-Gross, Tal Hassner, Lior Wolf. 2011
44 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
- Lior Wolf
- Tal Hassner
- Yu Qiao
- Juan Carlos Niebles
- Orit Kliper-Gross
- Ranjay Krishna
- Li Fei-Fei
- Xiaojiang Peng
In Computer Vision and Pattern Recognition
- Yu Qiao
- Luc Van Gool
- Andrew Zisserman
- Dacheng Tao
- Li Fei-Fei
- Xiaogang Wang
- Trevor Darrell
- Cordelia Schmid
Citations in the corpus
- Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (2019, methodology): “OSS and TARN propose a measurement of similarity or distance measure between video pairs [7, 39], CMN encodes uses a multi-saliency algorithm to encode videos [90], and ProtoGAN creates a prototype vector for each class [18].”
- Few-Shot Video Classification via Temporal Alignment (2019, background): “OSS-Metric Learning [19] proposes a novel OSS-Metric Learning to measure the similarity of video pairs to enable one-shot video classification.”
- Large Margin Dimensionality Reduction for Action Similarity Labeling (2014, methodology): “For video representation, most of the methods in the ASLAN task followed those in the action recognition [8], [9], [10], [11], such as the popular bag-of-words (BoW) [12] representation with Space–Time Interest Points (STIPs) [1] and dense trajectories [4].”
- Temporal Tessellation: A Unified Approach for Video Analysis (2016, background): “Early work on video action recognition relied on hand crafted space-time features [24, 25, 30, 65].”
- Violent flows: Real-time detection of violent crowd behavior (2012, methodology): “, [1]) and intensive processing [15], instead following the example of methods for dynamic texture recognition, such as [13], in collecting statistics of densely sampled, low-level features.”
- A Critical Review of Action Recognition Benchmarks (2013, methodology): “In [11] a metric learning approach was designed for the One Shot Similarity of [42].”