Research map / Video / Action recognition
OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments
Hymalai Bello, Lala Ray, Joanna Sorysz, Sungho Suh, Paul Lukowicz
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fuse inertial with vision (late-fusion transformer) (ablation) | inertial-only HAR · OpenMarcie HAR scenario (a) | Macro F1: 0.834 -> 0.882 | Improved |
| fuse inertial with vision (ablation) | vision-only HAR · OpenMarcie HAR scenario (a) | Macro F1: 0.757 -> 0.882 | Improved |
| add acoustic to inertial + vision (ablation) | I + V HAR · OpenMarcie HAR scenario (a) | Macro F1: 0.882 -> 0.859 | Hurt |
| add acoustic to inertial + vision (ablation) | I + V captioning · OpenMarcie captioning scenario (a) | cosine similarity: 0.561 -> 0.547 | Hurt |
| add acoustic to inertial (ablation) | inertial HAR · OpenMarcie HAR scenario (a) | Macro F1: 0.834 -> 0.803 | Hurt |
| fuse inertial with vision (ablation) | vision captioning · OpenMarcie captioning scenario (b) | cosine similarity: 0.632 -> 0.655 | Improved |
| add inertial to vision + text alignment (ablation) | V + T · OpenMarcie alignment scenario (a) | R@1: 0.437 -> 0.485 | Improved |
| add acoustic to I + V + T alignment (ablation) | I + V + T · OpenMarcie alignment scenario (a) | R@1: 0.485 -> 0.470 | Hurt |
| add acoustic to acoustic-only partners (ablation) | A + T alignment · OpenMarcie alignment scenario (a) | R@1: 0.241 -> 0.412 (A+V+T) | Improved |
Closest papers by meaning
- IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants (NeurIPS 2025 · similarity 0.86)
- CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities (NeurIPS 2024 · similarity 0.84)
- MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments (CVPR 2025 · similarity 0.83)
- Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild (AAAI 2024 · similarity 0.82)
- GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities (CVPR 2025 · similarity 0.82)
- Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
