The Object at Hand: Automated Editing for Mixed Reality Video Guidance from Hand-Object Interactions
Not on the map. Why?
Abstract (arXiv)
In this paper, we concern with the problem of how to automatically extract the steps that compose real-life hand activities. This is a key competence towards processing, monitoring and providing video guidance in Mixed Reality systems. We use egocentric vision to observe hand-object interactions in real-world tasks and automatically decompose a video into its constituent steps. Our approach combines hand-object interaction (HOI) detection, object similarity measurement and a finite state machine (FSM) representation to automatically edit videos into steps. We use a combination of Convolutional Neural Networks (CNNs) and the FSM to discover, edit cuts and merge segments while observing real hand activities. We evaluate quantitatively and qualitatively our algorithm on two datasets: the GTEAciteli2015delving, and a new dataset we introduce for Chinese Tea making. Results show our method is able to segment hand-object interaction videos into key step segments with high levels of precision.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 29 Sep 2021.
Builds on
16 of 31 references.
References · 16
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2015Fast R-CNNcited by 2,930
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
- 2013Network In Networkcited by 600
- 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 504
- 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
- 2019MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationcited by 370
- 2020Understanding Human Hands in Contact at Internet Scalecited by 281
- 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 229
- 2021Anticipative Video Transformercited by 197
4 more
- 2021Video Summarization Using Deep Neural Networks: A Surveycited by 85
- 2017From Lifestyle Vlogs to Everyday Interactionscited by 42
- 2020Temporal Relational Modeling with Self-Supervision for Action Segmentationcited by 29
- 2016Automated capture and delivery of assistive task guidance with an eyewear computer: The GlaciAR systemcited by 3
Built on by
Citing papers per year: 2022: 1.
1 paper.