A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection

By Bharat Singh, Tim K. Marks, Michael J. Jones, Oncel Tuzel, Ming Shao. 2016

493 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

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

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “) [163] and providing a list of related items for the detected action.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “[118] presented a multi-stream bi-directional recurrent neural network for fine-grained action detection.”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, background): “…(RNNs) which can handle the sequential data with variable lengths [10], [11], have shown their strength in language modeling [12], [13], [14], image captioning [15], [16], video analysis [17], [18], [19], [20], [21], [22], [23], [24], [25], and RGB-based activity recognition [26], [27], [28], [29].”
Temporal Convolutional Networks for Action Segmentation and Detection (2016, methodology): “We use MERL Shopping which was designed for action detection, Georgia Tech Egocentric Activities which was designed for action segmentation, and 50 Salads which has been used for both.”
TALL: Temporal Activity Localization via Language Query (2017, methodology): “For traditional temporal action localization, most current approaches [30, 15, 26, 34, 35] apply activity classifiers trained with optical flow-based methods [33, 28] or Convolutional Neural Networks (CNNs) [29, 32] in a sliding window fashion.”
Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment (2018, background): “[17] present a multi-stream bi-directional recurrent neural network for fine-grained action detection task.”
NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning (2018, background): “Most existing work on temporal action segmentation focuses on a fully supervised task [15, 26, 31, 19, 32, 22, 6, 37, 18, 36, 28].”
SST: Single-Stream Temporal Action Proposals (2017, background): “A number of existing methods approach the problem of temporal action localization [19, 22, 26, 27, 31, 32, 35, 40, 24, 30, 38].”
Action Sets: Weakly Supervised Action Segmentation Without Ordering Constraints (2017, background): “In the context of fully supervised action detection, most approaches use a sliding window to efficiently segment a video [21, 27] and rely on CNNs or recurrent networks [39, 31, 29] that can not be used if only weak supervision is available.”
Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction (2016, methodology): “LSTMs are also increasingly being used [56, 3, 37, 57] to address the problem.”
One-Shot Action Localization by Learning Sequence Matching Network (2018, methodology): “[38, 49, 28] use LSTM in addition to CNN to better model the temporal dynamics each proposal.”
Temporal Convolutional Networks: A Unified Approach to Action Segmentation (2016, background): “It has been shown that in practice LSTM only keeps a memory of about 4 seconds on some video-based action segmentation datasets [15].”
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals (2017, background): “[23] extend two-stream [21] framework to multi-stream bi-directional LSTM networks and achieved state-of-the-art performance on MPII-Cooking dataset [19].”