Bristol Egocentric Object Interactions Dataset
The BEOID dataset includes object interactions ranging from preparing a coffee to operating a weight lifting machine and opening a door. The dataset is recorded at six locations: kitchen, workspace, laser printer, corridor with a locked door, cardiac gym, and weight-lifting machine. For the first four locations, sequences from five different operators were recorded (two sequences per operator), and from three operators for the last two locations (three sequences per operator). The wearable gaze tracker hardware (ASL Mobile Eye XG) was used to record the dataset. Synchronized wide-lens video data with calibrated 2D gaze fixations are available. Moreover, we release 3D information using a pre-built cloud point map and PTAM tracking. Three-dimensional information of the image and the gaze fixations are included.
Variants: BEOID
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Weakly Supervised Action Localization | HR-Pro | HR-Pro: Point-supervised Temporal Action Localization … | 2023-08-24 |
| Weakly Supervised Action Localization | LACP | Learning Action Completeness from Points … | 2021-08-11 |
| Weakly Supervised Action Localization | Li et al. | Temporal Action Segmentation from Timestamp … | 2021-03-11 |
| Weakly Supervised Action Localization | Ju et al. | Point-Level Temporal Action Localization: Bridging … | 2020-12-15 |
| Weakly Supervised Action Localization | SF-Net | SF-Net: Single-Frame Supervision for Temporal … | 2020-03-15 |
Recent papers with results on this dataset: