Viterbi Algorithm

By Ralph Grishman. 2010

2,989 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Pichao Wang
2. Wanqing Li
3. Jun Liu
4. Dacheng Tao
5. Chunhua Shen
6. Michael J. Black
7. Luc Van Gool
8. Wanli Ouyang

Citations in the corpus

• Towards Open Intent Discovery for Conversational Text (2019, methodology): “The Viterbi algorithm [8] used for decoding the CRF layer only considers interactions between sequentially adjacent tag labels.”
• Large-scale Continuous Gesture Recognition Using Convolutional Neural Networks (2016, methodology): “The distance between two feature vectors is defined as the negative Euclidean distance and a matrix containing DTW distances (measuring similarity between two temporal sequences) between the two sequences is then calculated and analysed by Viterbi algorithm [23] to segment the gestures.”
• Standardization of Automated Analyses of Oculomotor Fixation and Saccadic Behaviors (2010, background): “The second stage is defined by the Viterbi sampler [32], where each eye”
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (2020, methodology): “After the model is trained, we employ Viterbi algorithm (Forney, 1973) to find the best label sequence for each input.”
• Neural Network Detection of Data Sequences in Communication Systems (2018, methodology): “Using these transition probabilities and setting the L(V0,0) = 0 and L(V0,u ) = −∞, for u = 0, the most likely sequence x̂k , 1 ≤ k ≤ K, can be estimated using the Viterbi algorithm [60].”
• AMASS: Archive of Motion Capture As Surface Shapes (2019, methodology): “They generate multiple hypotheses per frame and then connect them using the Viterbi algorithm [13].”
• A batch algorithm using iterative application of the Viterbi algorithm to track cells and construct cell lineages (2012, unknown): “The Markov property, along with the trellis structure of the state space diagram, allows a dynamic programming algorithm – known as the Viterbi algorithm [8] in the communication literature – to find the optimal way of adding a cell, with a complexity that is linear in T , as opposed to trying all p”
• On orchestrating virtual network functions (2015, methodology): “The heuristic runs in two steps: (i) we model the VNF-OP as a multi-stage directed graph with associated costs, (ii) we find a near-optimal solution from the multi-stage graph by running the Viterbi algorithm [14].”
• A Review of Computer Vision Techniques for the Analysis of Urban Traffic (2011, methodology): “uses the Viterbi algorithm [40], [146] to find the optimal vehicle constellation over several frames.”
• Robust Scheme for Iris Presentation Attack Detection Using Multiscale Binarized Statistical Image Features (2015, methodology): “1 performs the iris segmentation based on tracing the optimal path of the contours using the Viterbi search algorithm [21].”
• A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection (2016, background): “[111] G. D. Forney, “The Viterbi algorithm,” Proc.”
• Interactive Facial Feature Localization (2012, methodology): “We can find the globally optimal such sequence in O(NM(2)) time using dynamic programming (the Viterbi algorithm [18]).”
• Human gesture recognition through a Kinect sensor (2012, unknown): “We apply the Viterbi algorithm [21] to solve this problem.”
• Orchestrating Virtualized Network Functions (2015, methodology): “Then we find a near-optimal VNF placement from the multi-stage graph by running the Viterbi algorithm [20].”