Felzenszwalb-Baum-Welch: Event Detection by Changing Appearance
Explore this paper's citation graph
Summary
A novel training method uses an EM loop to simultaneously learn the temporal structure and object models automatically, without the need to specify either the individual poses to be modeled or the frames in which they occur.
- Type
- preprint
- Published
- 2013-06-19
- Cited by
- 1
- References
- 22
- Access
- Open access
- OpenAlex
- https://openalex.org/W1491719553
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:12280682
Keywords
Hidden Markov model, Computer science, Leverage (statistics), Event (particle physics), Artificial intelligence
References
- An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process
- State-of-the-art on spatio-temporal information-based video retrieval
- Articulated pose estimation with flexible mixtures-of-parts
- Statistical Inference for Probabilistic Functions of Finite State Markov Chains
- The Pascal Visual Object Classes (VOC) Challenge
- Cascade object detection with deformable part models
- Action bank: A high-level representation of activity in video
- Continuously variable duration hidden Markov models for automatic speech recognition
- A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
- Recognizing realistic actions from videos “in the wild”
- HMDB: A large video database for human motion recognition
- Event Detection in Crowded Videos
- Simultaneous Object Detection, Tracking, and Event Recognition
- Learning latent temporal structure for complex event detection
- Histograms of oriented gradients for human detection
- Event recognition with time varying Hidden Markov Model
- Object Detection with Discriminatively Trained Part Based Models
- Recognizing human actions: a local SVM approach
- An HMM-based framework for video semantic analysis
- Video In Sentences Out
Cited by
Related papers
- Research of HMM and I/O HMM used in protein secondary structure prediction
- A mixed autoregressive hidden-markov-chain model applied to people's movements
- Mid-long Term Load Forecasting Using Hidden Markov Model
- The Research of Software Behavior Recognition and Trend Prediction Method Based on GA-HMM
- On modeling context-dependent clustered states: Comparing HMM/GMM, hybrid HMM/ANN and KL-HMM approaches
- Speaker-ensemble hidden Markov modeling for automatic speech recognition
- Music Identification Using Embedded HMM
- Temporal Hidden Markov Models
- Research on Event Detection of Soccer Video Based on Hidden Markov Model