One-Shot Action Localization by Learning Sequence Matching Network

By Hongtao Yang, Xuming He, Fatih Murat Porikli. 2018

49 citations recorded by the source corpus.

Learning based temporal action localization methods require vast amounts of training data. However, such large-scale video datasets, which are expected to capture the dynamics of every action category, are not only very expensive to acquire but are also not practical simply because there exists an uncountable number of action classes. This poses a critical restriction to the current methods when the training samples are few and rare (e.g. when the target action classes are not present in the current publicly available datasets). To address this challenge, we conceptualize a new example-based action detection problem where only a few examples are provided, and the goal is to find the occurrences of these examples in an untrimmed video sequence. Towards this objective, we introduce a novel one-shot action localization method that alleviates the need for large amounts of training samples. Our solution adopts the one-shot learning technique of Matching Network and utilizes correlations to mine and localize actions of previously unseen classes. We evaluate our one-shot action localization method on the THUMOS14 and ActivityNet datasets, of which we modified the configuration to fit our one-shot problem setup.

Subfields: Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, background): “Plenty of advanced techniques, such as metric learning [84] and meta learning [85], [86], have been introduced for one-shot object recognition and image classiﬁcation [87], [88], [89].”
Generalizing from a Few Examples (2019, methodology): “FSL has also been successfully used in video applications, including motion prediction [50], video classification [164], action localization [152], person re-identification [148], event detection [151], and object segmentation [21].”
Small Sample Learning in Big Data Era (2018, background): “, 2018) and one-shot action localization (Yang et al., 2018).”
ProtoGAN: Towards Few Shot Learning for Action Recognition (2019, methodology): “A method for action localization in FSL setting is explored in [27].”