Modeling video evolution for action recognition

By Basura Fernando, Efstratios Gavves, José Oramas, Amir Ghodrati, Tinne Tuytelaars. 2015

556 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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 Control and Systems Engineering

Citations in the corpus

Joint Discovery of Object States and Manipulation Actions (2017, methodology): “This observation has been used to design action models in [16, 17, 45].”
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (2017, background): “…in attempts to capture this relationship, for example by learning frame ranking functions for action classes and using these as a representation [9], by making analogies between actions and transformations [33], or by creating 2D visual snapshots of frame sequences [2] – this idea is related to…”
UvA-DARE (Digital Academic Repository) Self-Supervised Video Representation Learning With Odd-One-Out Networks (neutral): “There has also been unsupervised temporal feature encoding methods to capture the structure of videos for action classification [13, 14, 15, 29, 36].”
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (2016, background): “Fer-nando [18] modeled the temporal evolution of BoVW representations for action recognition.”
Video Representation Learning Using Discriminative Pooling (2018, methodology): “For comparison, we plot the running times for some of the recent pooling schemes such as rank pooling [2, 14] and the Fisher vectors [51].”
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, methodology): “As shown in Table 8, our method surpasses the state-ofthe-art methods [39], [91], [92], [93], [94], [95], which demonstrates the effectiveness of our method in dealing with skeleton-based action recognition problem.”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “As done in the literature [9, 12], we report the precision, recall and F1-score measures on the validation set.”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, background): “ this paper, we focus on skeleton-based 3D action recognition. To recognize a video action, the temporal information of the sequence needs to be exploited to understand the dynamics of human postures [29, 9, 44, 8, 20]. For skeleton data, the spatial structure of the human skeleton is also an import”
Actions ~ Transformations (2015, background): “Fernando et al. [6] learned ranking functions for each video and tried to capture video-wide temporal information for action recognition.”
Action Recognition using Visual Attention (2015, neutral): “ft attention model (Our model) 41.3 43.9 Composite LSTM Model (Srivastava et al., 2015) 44.0 - DL-SFA (Sun et al., 2014) - 48.1 Two-stream ConvNet (Simonyan & Zisserman, 2014) 59.4 - VideoDarwin (Fernando et al., 2015) 63.7 73.7 Multi-skIp Feature Stacking (Lan et al., 2014) 65.1 68.0 Traditiona”
Long-Term Temporal Convolutions for Action Recognition (2016, neutral): “Explicit representations of the temporal structure of actions have rarely beed used with some exceptions such as the recent work [20].”
Learning and Using the Arrow of Time (2018, background): “Others have used the temporal ordering of frames as a supervisory signal for learning an embedding [15], for self-supervision training of a ConvNet [6, 13], and for construction of a representation for action recognition [7].”
Connectionist Temporal Modeling for Weakly Supervised Action Labeling (2016, background): “Our goal of understanding the temporal structure of video is related to [10,31,34,37,39,40].”
VideoLSTM convolves, attends and flows for action recognition (2016, neutral): “, Wang and Schmid (2013), Jain et al. (2013), Sadanand and Corso (2012), Peng et al. (2016); 2014),Fernando et al.”
Temporal Segment Networks for Action Recognition in Videos (2017, background): “been proven crucial for understanding the dynamics in traditional methods [19], [20], [21], [22], [23], it has not been consid-”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Capturing the whole information of the video in terms of temporal evolution of the video stream has been the focus of some recent approaches [51, 6, 12, 35, 49, 30].”
Learnable pooling with Context Gating for video classification (2017, background): “The remaining question is: how to aggregate video features over the entire and potentially long video? One way to achieve this is to employ recurrent neural networks, such as long short-term memory (LSTM) [16] or gated recurrent unit (GRU) [17]), on top of the extracted frame-level features to captu”
Structured Images for RGB-D Action Recognition (2017, methodology): “Inspired by the promising performance of recently introduced rank pooling machine [10, 2, 9] on RGB video, this paper proposes to adopt rank pooling method to encode depth map sequences into dynamic images.”
Spatially and Temporally Structured Global to Local Aggregation of Dynamic Depth Information for Action Recognition (2018, background): “[30], [34] is restricted to exploit long term dynamics.”