For face naming in TV series or movies, a typical way is using subtitles/script alignment to get the time stamps of the names, and tagging them to the faces. We study the problem of face naming in videos when subtitles are not available. To this end, we divide the problem into two tasks: face clustering which groups the faces depicting a certain person into a cluster, and name assignment which associates a name to each face. Each task is formulated as a structured prediction problem and modeled by a hidden conditional random field (HCRF) model. We argue that the two tasks are correlated problems whose outputs can provide prior knowledge of the target prediction for each other. The two HCRFs are coupled in a unified graphical model called coupled HCRF where the joint dependence of the cluster labels and face name association is naturally embedded in the correlation between the two HCRFs. We provide an effective algorithm to optimize the two HCRFs iteratively and the performance of the two tasks on real-world data set can be both improved.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2016.2601491 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Filtering coupled Wright-Fisher diffusions.
J Math Biol
November 2024
University of Torino and Collegio Carlo Alberto, Turin, Italy.
Coupled Wright-Fisher diffusions have been recently introduced to model the temporal evolution of finitely-many allele frequencies at several loci. These are vectors of multidimensional diffusions whose dynamics are weakly coupled among loci through interaction coefficients, which make the reproductive rates for each allele depend on its frequencies at several loci. Here we consider the problem of filtering a coupled Wright-Fisher diffusion with parent-independent mutation, when this is seen as an unobserved signal in a hidden Markov model.
View Article and Find Full Text PDFDecoding a Cognitive Performance State from Behavioral Data in the Presence of Auditory Stimuli.
IEEE Trans Neural Syst Rehabil Eng
November 2024
Objective: Cognitive performance state is an unobserved state that refers to the overall performance of cognitive functions. Deriving an informative observation vector as well as the adaptive model and decoder would be essential in decoding the hidden performance.
Methods: We decode the performance from behavioral observation data using the Bayesian state-space approach.
Article Synopsis
- Current studies on brain-muscle modulation mainly focus on specific aspects of electrophysiological signals, leading to an incomplete understanding of their interaction.
- This article introduces a cross-modal generative model that translates brain activity (EEG) into muscle responses (EMG) to better understand this relationship.
- The model uses a two-stage process, with contrastive learning to identify shared movement-related information and generative adversarial networks (GANs) to improve EMG generation, showing promising results compared to traditional methods.
Evaluating Medical Entity Recognition in Health Care: Entity Model Quantitative Study.
JMIR Med Inform
October 2024
Department of Medical Data Sharing, Institute of Medical Information & Library, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Background: Named entity recognition (NER) models are essential for extracting structured information from unstructured medical texts by identifying entities such as diseases, treatments, and conditions, enhancing clinical decision-making and research. Innovations in machine learning, particularly those involving Bidirectional Encoder Representations From Transformers (BERT)-based deep learning and large language models, have significantly advanced NER capabilities. However, their performance varies across medical datasets due to the complexity and diversity of medical terminology.
View Article and Find Full Text PDFTransfer learning-enabled outcome prediction for guiding CRRT treatment of the pediatric patients with sepsis.
BMC Med Inform Decis Mak
September 2024
The Graduate School of Fujian Medical University, Fuzhou, Fujian, 35000, China.
Continuous renal replacement therapy (CRRT) is a life-saving procedure for sepsis but the benefit of CRRT varies and prediction of clinical outcomes is valuable in efficient treatment planning. This study aimed to use machine learning (ML) models trained using MIMIC III data for identifying sepsis patients who would benefit from CRRT. We first selected patients with sepsis and CRRT in the ICU setting and their gender, and an array of routine lab results were included as features to train machine learning models using 30-day mortality as the primary outcome.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!