Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

By Javen Qinfeng Shi, Li Cheng, Li Wang, Alex Smola. 2011

148 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning human activities and object affordances from RGB-D videos (2012, methodology): “…work on human activity detection from images (Yang et al., 2010; Yao et al., 2011) and from videos (Laptev et al., 2008; Liu et al., 2009; Hoai et al., 2011; Shi et al., 2011; Matikainen et al., 2012; Pirsiavash and Ramanan, 2012; Rohrbach et al., 2012; Sadanand and Corso, 2012; Tang et al., 2012).”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2015, background): “Examples include human activity recognition and segmentation from videos [50, 47, 62, 60, 8, 25, 37, 36], context-rich human-object interactions [39, 33, 29, 20, 30], modeling human motion [14, 57, 56] etc.”
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos (2015, background): “Shi et al. [28] proposes a semi-Markov model to segment a sequence temporally and label segments with an action class.”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “Works on semi-Markov models (Sarawagi & Cohen, 2004; Shi et al., 2011) are quite related to our work as they address the problem of finding the segmentation along with labeling.”
Predictive-Corrective Networks for Action Detection (2017, methodology): “These models generally rely on chain structured models that admit efficient inference, such as HMMs [33, 12] and CRFs [52].”
Harnessing Lab Knowledge for Real-World Action Recognition (2014, methodology): “Following Wang et al. (2009), we use the Harris3D + HOG/HOF to process the above three datasets.”
Parsing Videos of Actions with Segmental Grammars (2014, background): “Most related to our work are [25, 6], who use a semi-Markov model to segment video streams into actions.”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, unknown): “Another line of work captures temporal evolutions of appearance or pose using sequential state models [11,23,20,19].”
Manifold Warp Segmentation of Human Action (2018, methodology): “Besides, statistical algorithms [16], Markov models [16], and biological modelbased algorithms [17] are also applied in realizing human”
Pose Adaptive Motion Feature Pooling for Human Action Analysis (2014, methodology): “Shi et al. (2011) proposed a discriminative action segmentation and recognition method using semi-Markov models.”
Temporal Localization of Actions with Actoms (2013, unknown): “Inspired by speech recognition, sequential probabilistic models [13– 21] use dynamic probabilistic graphical models — e.g. Hidden Markov Models (HMM) [22] — to learn temporal transitions between hidden states.”
Structured Label Inference for Visual Understanding (2018, background): “puter vision rely on hidden Markov models for obtaining representations in order to recognize action classes considering evolution of actions or even multiple view-points [44], [45], [46].”
Part-Activated Deep Reinforcement Learning for Action Prediction (2018, unknown): “Different from action recognition [4, 5, 34, 35, 41, 42, 46, 47],”
Human Action Recognition and Prediction: A Survey (2018, methodology): “The action representation component basically converts an action video into a feature vector [11], [80], [81], [82] or a series of vectors [21], [54], [83], and the action classification component infers an action label from the vector [53], [84], [85].”
Watch-n-patch: Unsupervised understanding of actions and relations (2015, background): “Among them, the linear models [34] [12] [32] [3] are the most popular, which focus on modeling the action transitions in the activities.”