Context Driven Optimized Perceptual Video Summarization and Retrieval

Thomas, Sinnu Susan; Gupta, Sumana; Subramanian, V.

doi:10.1109/tcsvt.2018.2873185

Cited by 17 publications

(8 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A perceptionbased approach was explored to achieve the desired design using sensation words [4]. A perceptual video summarization and retrieval was proposed to provide a precise representation of video contents [11]. The interaction modalities and parasocial attractions of ASMR videos was annotated for multi-modal video interactions [5].…”

Section: Related Workmentioning

confidence: 99%

Find Your ASMR: A Perceptual Retrieval Interface for Autonomous Sensory Meridian Response Videos

Zhou¹,

Weng²,

Xie³

2022

Preprint

View full text Add to dashboard Cite

Autonomous sensory meridian response (ASMR) is a type of video contents designed to help people relax and feel comfortable. Users usually retrieve ASMR contents from various video websites using only keywords. However, it is challenging to examine satisfactory contents to reflect users' needs for ASMR videos using keywords or content-based retrieval. To solve this issue, we propose a perceptual video retrieval system for ASMR videos and provide a novel retrieval user interface that allows users to retrieve content according to watching purpose and anticipated expectations, such as excitement, calmness, stress and sadness. An ASMR video perception dataset is constructed with annotations on affective responses after watching the videos. To verify the proposed video retrieval system, a user study is conducted showing that users can retrieve satisfactory ASMR contents easily and efficiently compared to conventional keywords-based retrieval systems. 1

show abstract

Section: Related Workmentioning

confidence: 99%

Find Your ASMR: A Perceptual Retrieval Interface for Autonomous Sensory Meridian Response Videos

Zhou¹,

Weng²,

Xie³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, personalized video summaries with optimal lengths for new long-form videos (e.g., sports matches) are not immediately available. With current approaches [2], [3], generating personalized summaries in real time requires enormous computational resources to process user preference data and video content. Centralized dedicated servers can provide real-time, personalized video summaries.…”

Section: Introductionmentioning

confidence: 99%

LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN

Mujtaba¹,

Malik²,

Ryu³

2022

Preprint

View full text Add to dashboard Cite

This paper proposes a novel lightweight thumbnail container-based summarization (LTC-SUM) framework for full featurelength videos. This framework generates a personalized keyshot summary for concurrent users by using the computational resource of the end-user device. State-of-the-art methods that acquire and process entire video data to generate video summaries are highly computationally intensive. In this regard, the proposed LTC-SUM method uses lightweight thumbnails to handle the complex process of detecting events. This significantly reduces computational complexity and improves communication and storage efficiency by resolving computational and privacy bottlenecks in resource-constrained end-user devices. These improvements were achieved by designing a lightweight 2D CNN model to extract features from thumbnails, which helped select and retrieve only a handful of specific segments.Extensive quantitative experiments on a set of full 18 feature-length videos (approximately 32.9 h in duration) showed that the proposed method is significantly computationally efficient than state-of-the-art methods on the same end-user device configurations. Joint qualitative assessments of the results of 56 participants showed that participants gave higher ratings to the summaries generated using the proposed method. To the best of our knowledge, this is the first attempt in designing a fully client-driven personalized keyshot video summarization framework using thumbnail containers for feature-length videos.

show abstract

“…In salient objection detection (SOD), the main objective is to extract the most predominant objects from a natural scene. It has been an essential function in computer vision since SOD has many useful applications, including image/video compression [18,27], object segmentation and recognition [68,67,44,23], content-based image editing [52,55], informative common object discovery [63,64], and image retrieval [47]. Many SOD methods are based on the assumption that the inputs are RGB images [40,54,57,53,66] or video sequences [56,25].…”

Section: Introductionmentioning

confidence: 99%

AMDFNet: Adaptive multi-level deformable fusion network for RGB-D saliency detection

Zheng

Liu

et al. 2021

Neurocomputing

View full text Add to dashboard Cite

Context Driven Optimized Perceptual Video Summarization and Retrieval

Cited by 17 publications

References 58 publications

Find Your ASMR: A Perceptual Retrieval Interface for Autonomous Sensory Meridian Response Videos

Find Your ASMR: A Perceptual Retrieval Interface for Autonomous Sensory Meridian Response Videos

LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN

AMDFNet: Adaptive multi-level deformable fusion network for RGB-D saliency detection

Contact Info

Product

Resources

About