Proceedings of the Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes 2017
DOI: 10.1145/3132515.3132523
|View full text |Cite
|
Sign up to set email alerts
|

User Group based Viewpoint Recommendation using User Attributes for Multiview Videos

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
3
2

Relationship

1
4

Authors

Journals

citations
Cited by 6 publications
(4 citation statements)
references
References 16 publications
0
4
0
Order By: Relevance
“…Wang et al proposed an automatic camera switching system for soccer. They calculated scores for each camera based on the presence of a ball or player [14], [15], trajectory of viewing target [17], [18] and interest of viewer groups [16]. Tang and Boring developed a video highlighting system [11].…”
Section: Related Workmentioning
confidence: 99%
“…Wang et al proposed an automatic camera switching system for soccer. They calculated scores for each camera based on the presence of a ball or player [14], [15], trajectory of viewing target [17], [18] and interest of viewer groups [16]. Tang and Boring developed a video highlighting system [11].…”
Section: Related Workmentioning
confidence: 99%
“…Moreover, researchers found that the experience quality of an application or a service is related to a user's personality [23]. Some researches have embedded human attributes into model construction for experience assessment and video recommendation, such as personality and user preference [46,56]. From these works, we can infer that user information is useful and critical in user-generated-content related tasks.…”
Section: User-aware Recommendationmentioning
confidence: 99%
“…One way to combat the above limitation is to train the model over a large diverse dataset, but this requires tremendous amount of data with rich statistical diversity [15], which, however, is practically unavailable. Grouping users based on their viewing patterns and training personalized models for each group seems plausible [15] [19], but this necessitates retraining of a new model whenever a new group emerges, leading to prohibitive training cost. Previous work [8] has showcased the potential of ensemble learning (EL) to reduce prediction bias and improve model generalization.…”
Section: Impact Of Viewing Pattern Diversitymentioning
confidence: 99%
“…To tackle the challenge of user diversity, prior studies [10] [15] [19] have attempted to categorize users into dinsinct groups based on their viewing and QoE preferences, and train personalized models for each group. However, this approach necessitates the retraining of a new model whenever a new user group emerges, resulting in prohibitive training cost.…”
Section: Introductionmentioning
confidence: 99%