Projects per year
Abstract
Manual annotations of temporal bounds for object interactions (i.e. start and end times) are typical training input to recognition, localization and detection algorithms. For three publicly available egocentric datasets, we uncover inconsistencies in ground truth temporal bounds within and across annotators and datasets. We systematically assess the robustness of state-of-the-art approaches to changes in labeled temporal bounds, for object interaction recognition. As boundaries are trespassed, a drop of up to 10% is observed for both Improved Dense Trajectories and TwoStream Convolutional Neural Network. We demonstrate that such disagreement stems from a limited understanding of the distinct phases of an action, and propose annotating based on the Rubicon Boundaries, inspired by a similarly named cognitive model, for consistent
temporal bounds of object interactions. Evaluated on a public dataset, we report a 4% increase in overall accuracy, and an increase in accuracy for 55% of classes when Rubicon Boundaries are used for temporal annotations.
temporal bounds of object interactions. Evaluated on a public dataset, we report a 4% increase in overall accuracy, and an increase in accuracy for 55% of classes when Rubicon Boundaries are used for temporal annotations.
Original language | English |
---|---|
Title of host publication | 2017 International Conference on Computer Vision (ICCV 2017) |
Subtitle of host publication | Proceedings of a meeting held 22-29 October 2017, Venice, Italy |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 2905-2913 |
Number of pages | 9 |
ISBN (Electronic) | 9781538610329 |
ISBN (Print) | 9781538610336 |
DOIs | |
Publication status | Published - Feb 2018 |
Event | International Conference on Computer Vision (ICCV), - Duration: 22 Oct 2017 → … |
Publication series
Name | |
---|---|
ISSN (Print) | 2380-7504 |
Conference
Conference | International Conference on Computer Vision (ICCV), |
---|---|
Period | 22/10/17 → … |
Fingerprint
Dive into the research topics of 'Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video'. Together they form a unique fingerprint.Projects
- 2 Finished
-
LOCATE: LOcation adaptive Constrained Activity recognition using Transfer learning
Damen, D. (Principal Investigator)
4/07/16 → 3/05/18
Project: Research
-
GLANCE - EPSRC Call for Outlines - User Interaction with ICT
Mayol-Cuevas, W. W. (Principal Investigator)
4/04/16 → 2/02/22
Project: Research
Profiles
-
Professor Dima Damen
- School of Computer Science - Professor in Computer Vision
Person: Academic , Member