Selective keyframe summarisation for egocentric videos based on semantic concept search
Allbwn ymchwil: Cyfraniad at gynhadledd › Papur › adolygiad gan gymheiriaid
Fersiynau electronig
Dogfennau
- SelectiveVideoSummarisation
Proflen, 1.54 MB, dogfen-PDF
Large volumes of egocentric video data are being continually collected every day. While the standard video summarisation approach offers all-purpose summaries, here we propose a method for selective video summarisation. The user can query the video with an unlimited vocabulary of terms. The result is a time-tagged summary of keyframes related to the query concept. Our method uses a pre-trained Convolutional Neural Network (CNN) for the semantic search, and visualises the generated summary as a compass. Two commonly used datasets were chosen for the evaluation: UTEgo egocentric video and EDUB lifelog.
| Iaith wreiddiol | Saesneg |
|---|---|
| Nifer y tudalennau | 6 |
| Statws | Cyhoeddwyd - 2018 |
| Digwyddiad | The International Image Processing Applications and Systems Conference - Sophia Antipolis, Ffrainc Hyd: 12 Rhag 2018 → 14 Rhag 2018 |
Cynhadledd
| Cynhadledd | The International Image Processing Applications and Systems Conference |
|---|---|
| Teitl cryno | IPAS |
| Gwlad/Tiriogaeth | Ffrainc |
| Dinas | Sophia Antipolis |
| Cyfnod | 12/12/18 → 14/12/18 |
Cyfanswm lawlrlwytho
Nid oes data ar gael