Image Aesthetics and Content in Selecting Memorable Keyframes from Lifelogs

Hu, Feiyan; Smeaton, Alan F.

doi:10.1007/978-3-319-73603-7_49

Cited by 5 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lifelogging can also include recording the footprints of our online activities on our phones and computers including pages browsed, emails sent/read, documents written or read, even the timing of our keystrokes as we type [13]. We we have shown in some of our previous work, this data, when cleaned, integrated and analysed can be used to indicate shifts in our everyday behaviour [5], as a memory prosthetic for our forgetfulness [12] or to generate a visual summary or reflection on past events in our lifetimes [6].…”

Section: Introductionmentioning

confidence: 88%

Managing Personal Information

Smeaton

2023

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

There is an increasing awareness of the potential that our own self-gathered personal information has for our wellness and our health. This is partly because of our increasing awareness of what others -the major internet companies mainly -have been able to do with the personal information that they gather about us. The biggest hurdle to us using and usefully exploiting our own self-gathered personal data are the applications to support that. In this paper we highlight both the potential and the challenges associated with more widespread use of our own personal data by ourselves and we point at ways in which we believe this might happen. We use the work done in lifelogging and the annual Lifelog Search Challenge as an indicator of what we can do with our own data. We review the small number of existing systems which do allow aggregation of our own personal information and show how the use of large language models could make the management of our personal data more straightforward.

show abstract

Section: Introductionmentioning

confidence: 88%

Managing Personal Information

Smeaton

2023

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Video Memorability (VM) is a natural progression from a related research discipline: image memorability (IM). The work of [21] is regarded as a seminal paper on IM in which it is stated that memorability is an intrinsic property of an image, an abstract concept similar to image aesthetics which can be computed automatically using modern image analysis techniques [20]. The use of deeplearning frameworks has led to results at near human levels of consistency in the task of IM prediction [2,6,15] partly attributed to the development of image datasets with annotated memorability scores [22].…”

Section: Related Work 21 Media Memorabilitymentioning

confidence: 99%

Analysing the Memorability of a Procedural Crime-Drama TV Series, CSI

Cummins,

Sweeney,

Smeaton

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We investigate the memorability of a 5-season span of a popular crime-drama TV series, CSI, through the application of a vision transformer fine-tuned on the task of predicting video memorability. By investigating the popular genre of crime-drama TV through the use of a detailed annotated corpus combined with video memorability scores, we show how to extrapolate meaning from the memorability scores generated on video shots. We perform a quantitative analysis to relate video shot memorability to a variety of aspects of the show. The insights we present in this paper illustrate the importance of video memorability in applications which use multimedia in areas like education, marketing, indexing, as well as in the case here namely TV and film production.

show abstract

“…Saliency has been shown to be effective in image cropping [36], [37] around objects of interest so, in this paper, we generate regions of interest (ROIs) based on the heatmap from saliency prediction. To do this, we first erode and then dilate the saliency map with a 5×5 kernel.…”

Section: B Rois Generationmentioning

confidence: 99%

Saliency Guided 2D-Object Annotation for Instrumented Vehicles

Venkatesh

O’Connor

et al. 2019

2019 International Conference on Content-Based Multimedia Indexing (CBMI)

Self Cite

View full text Add to dashboard Cite

Instrumented vehicles can produce huge volumes of video data per vehicle per day that must be analysed automatically, often in real time. This analysis should include identifying the presence of objects and tagging these as semantic concepts such as car, pedestrian, etc. An important element in achieving this is the annotation of training data for machine learning algorithms, which requires accurate labels at a highlevel of granularity. Current practise is to use trained human annotators who can annotate only a limited volume of video per day. In this paper, we demonstrate how a generic human saliency classifier can provide visual cues for object detection using deep learning approaches. Our work is applied to datasets for autonomous driving. Our experiments show that utilizing visual saliency improves the detection of small objects and increases the overall accuracy compared with a standalone single shot multibox detector.

show abstract

Image Aesthetics and Content in Selecting Memorable Keyframes from Lifelogs

Cited by 5 publications

References 18 publications

Managing Personal Information

Managing Personal Information

Analysing the Memorability of a Procedural Crime-Drama TV Series, CSI

Saliency Guided 2D-Object Annotation for Instrumented Vehicles

Contact Info

Product

Resources

About