Conditional random fields for activity recognition

By Douglas L. Vail, Manuela M. Veloso, John D. Lafferty. 2007

400 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

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 Signal Processing

Citations in the corpus

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.”
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification (2015, methodology): “employed the CRF for activity recognition in [41].”
Gesture Modeling by Hanklet-Based Hidden Markov Model (2014, methodology): “Another model often used for action recognition is Conditional Random Fields (CRF)[16],[17],[18], which is a discriminative approach and has proven to be successful for recognition task.”
Text Classification Algorithms: A Survey (2019, background): “CRFs can incorporate complex features into an observation sequence without violating the independence assumption by modeling the conditional probability of the label sequence rather than the joint probability P(X, Y) [174,175].”
Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy (2010, background): “, 2001), vision (Kumar & Hebert, 2006), and activities (Liao et al., 2007a; Vail et al., 2007).”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “, velocity thresholds in [106]) to explore the influence on both models.”
Learning latent structure for activity recognition (2014, background): “Linear-chain CRFs are efficient models because the exact inference is tractable.”
Sensor-Based Activity Recognition (2012, methodology): “CRFs are applied to the problem of activity recognition in [155] where they are compared with HMMs, but only in a simple simulated domain.”
A Survey on Ambient Intelligence in Health Care (2013, neutral): “Discriminative approaches, including support vector machines [58] and conditional random fields [52], [76]–[78]”
Predicting future locations with hidden Markov models (2012, background): “State-space models attempt to capture the variation in spatial sequences through sequence models such as generative Hidden Markov Models (HMMs) [17], discriminative Conditional Random Fields (CRFs) [21, 19], or extensions of these two well-known approaches [4, 15].”
Cross-domain activity recognition (2009, background): “Activity recognition aims to infer a user’s behaviors from the observations such as sensor data, and has various applications including medical care [19], logistics service [13], robot soccer [25], plan recognition [12], etc.”