Entanglement inspired approach for determining the preeminent arrangement of static cameras in a multi-view computer vision system

Kumar, Amit; Ngọc, Nguyễn; Guo, Sen; Han, Lina

doi:10.1007/s00371-022-02497-z

Cited by 7 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-view nature of data refers to situations where information about a particular entity or phenomenon is available from multiple perspectives or sources. In various fields, including data analysis [1], machine learning [2,3], computer vision [4,5], and information retrieval [6], dealing with data from multiple views has become increasingly important. Each view represents a different aspect or set of features related to the underlying data, and combining these views can provide a more comprehensive understanding.…”

Section: Introductionmentioning

confidence: 99%

Spectral Learning of Semantic Units in a Sentence Pair to Evaluate Semantic Textual Similarity

Mehndiratta

Asawa

2020

Big Data Analytics

View full text Add to dashboard Cite

The probabilistic interpretation of Canonical Correlation Analysis (CCA) for learning low-dimensional real vectors, called as latent variables, has been exploited immensely in various fields. This study takes a step further by demonstrating the potential of CCA in discovering a latent state that captures the contextual information within the textual data under a two-view setting. The interpretation of CCA discussed in this study utilizes the multi-view nature of textual data, i.e. the consecutive sentences in a document or turns in a dyadic conversation, and has a strong theoretical foundation. Furthermore, this study proposes a model using CCA to perform the Automatic Short Answer Grading (ASAG) task. The empirical analysis confirms that the proposed model delivers competitive results and can even beat various sophisticated supervised techniques. The model is simple, linear, and adaptable and should be used as the baseline especially when labeled training data is scarce or nonexistent.

show abstract