Learning a Multi-Concept Video Retrieval Model with Multiple Latent Variables
ACM TOMM 2018Amir Mazaheri, Boqing Gong, Mubarak Shah
Multi-Concept Video Retrieval
2016 – 2017
A latent-variable model for retrieving videos by multiple concepts supplied directly by users or inferred from queries.
video-retrievallatent-variable-models
Provides a foundational model for computing the ranking scores of a video in response to one or more concepts, where the concepts may be supplied directly by users or inferred by the system from user queries. Uses multiple latent variables to capture the diverse visual manifestations of each concept.