Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification

By Juan Carlos Niebles, Chih-Wei Chen, Li Fei-Fei. 2010

826 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

Unsupervised Learning from Narrated Instruction Videos (2015, background): “Methods in [22, 25] learn in an unsupervised manner the temporal structure of actions from video but do not discover textual expressions for actions as we do in this work.”
Dense-Captioning Events in Videos (2017, neutral): “Early work in activity recognition involved using hidden Markov models to learn latent action states [58], followed by discriminative SVM models that used key poses and action grammars [31, 48, 35].”
HMDB: A large video database for human motion recognition (2011, methodology): “We use this database to evaluate the performance of two representative computer vision systems for action recognition and explore the robustness of these methods under various conditions such as camera motion, viewpoint, video quality and occlusion.”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, background): “Significant progress towards action recognition in realistic video settings has been achieved in the past few years [22, 24, 26, 30, 35].”
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (2016, methodology): “Many research works have been devoted to modeling the temporal structure for action recognition [15,16,17,29,30,18].”
A New Representation of Skeleton Sequences for 3D Action Recognition (2017, background): “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].”
Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition (2014, methodology): “We use standard splits with 649 training clips and 134 test clips and report mAP as in [20] for comparison purposes.”
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “Discriminative models include those based on latent SVMs over key poses and action grammars (Niebles et al. 2010; Vahdat et al. 2011; Pirsiavash and Ramanan 2014).”
Unsupervised Semantic Parsing of Video Collections (2015, background): “Also, a large body of action recognition methods are intended for trimmed videos clips or remain limited to detecting very short actions [30, 56, 42, 33, 11, 51].”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
Temporal Segment Networks for Action Recognition in Videos (2017, methodology): “Many research works have been devoted to modeling the temporal structure of video for action recognition [19], [20], [21], [22], [56], [57].”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “This includes both discriminative [1], [13], [14], [15] and generative models [16], [17].”
CliqueCNN: Deep Unsupervised Exemplar Learning (2016, methodology): “In this section we present qualitative retrieval results for Olympic Sports in Fig.”
Temporal Localization of Actions with Actoms (2013, neutral): “We describe the process used to acquire training actom annotations in Section 3.3.”
Learning Maximum Margin Temporal Warping for Action Recognition (2013, methodology): “One approach to handle the the temporal structure is based on statistical generative models, such as HMM [12], dynamic Bayes nets [29], stochastic grammar [17] and CRFs [15].”
Representing Videos Using Mid-level Discriminative Patches (2013, background): “The key idea is that instead of using semantic parts/constituents, videos are represented in terms of discriminative spatio-temporal patches that can establish correspondences across videos.”
Modeling Complex Temporal Composition of Actionlets for Activity Prediction (2012, methodology): “To model temporal structure of decomposable activities, [10, 11] extend the classic bag-of-words model by including segmentation and dynamic matching.”