Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks

By Moez Baccouche, Franck Mamalet, Christian Wolf, Christophe Garcia, Atilla Baskurt. 2010

129 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

1. Trevor Darrell
2. Kate Saenko
3. Luc Van Gool
4. Abhinav Kumar Gupta
5. Li Fei-Fei
6. Andrew Zisserman
7. Marcus Rohrbach
8. Yi Yang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Trevor Darrell
3. Dacheng Tao
4. Andrew Zisserman
5. Xiaogang Wang
6. Jitendra Malik
7. Cordelia Schmid
8. Yi Yang

Citations in the corpus

• Long-term recurrent convolutional networks for visual recognition and description (2014, background): “A large body of recent work has proposed deep architectures for activity recognition ([16, 33, 13, 2, 1]).”
• Beyond short snippets: Deep networks for video classification (2015, methodology): “While LSTMs have been applied to action classification in [1], the model is learned on top of SIFT features and a BoW representation.”
• Differential Recurrent Neural Networks for Action Recognition (2015, methodology): “To overcome this limitation, Long Short-Term Memory (LSTM) [14], a variant of RNN, has been designed to learn the long-range dependency between the output label and the input frame, which has achieved competitive performance on action recognition task [2][3].”
• VideoLSTM convolves, attends and flows for action recognition (2016, neutral): “Where early adopters used traditional features as LSTM input [27, 28], more recently both Ng et al.”
• Detecting the Moment of Completion: Temporal Models for Localising Action Completion (2017, background): “In many recent works, LSTMs have achieved promising results for the task of action recognition/detection, such as [26,18,27,28,2,3].”
• Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images (2015, background): “Features activations from fc6 serve as the shared representation for web images and video frames, and allow cross-domain transfer between the two.”
• Long-Term Recurrent Convolutional Networks for Visual Recognition and Description (2017, background): “[2], [52] propose extracting visual and motion features and modeling temporal dependencies with recurrent networks.”
• Robust human action recognition via long short-term memory (2013, background): “LSTM to the action recognition problem [1][2][3][4], yielding accurate discrimination between different action”
• A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “As an initial study for activity recognition, a LSTM network was utilized to classify activities in soccer videos [124].”
• Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition (2016, methodology): “[33] learn temporal dynamics of traditional per-frame SIFT-BOW features using a RNN.”
• Sequential Deep Learning for Human Action Recognition (2011, unknown): “Though, we have shown in our previous work [1] that such information does help discriminating between actions, and is particularly usable by a category of learning machines, adapted to sequential data, namely Long Short-Term Memory recurrent neural networks (LSTM) [6].”
• Deep Learning for Sensor-based Human Activity Recognition (2020, background): “iction. In some common behavior tasks, the activities are usually in a certain order. Therefore, modeling the temporal dependencies across activities is beneficial to predict future predictions.LSTMs [9] are suitable for such tasks. But for long-span activities, LSTMs cannot contain such long depend”