Datasets › BEHAVE
BEHAVE
BEHAVE is a full body human-object interaction dataset with multi-view RGBD frames and corresponding 3D SMPL and object fits along with the annotated contacts between them. Dataset contains ~15k frames at 5 locations with 8 subjects performing a wide range of interactions with 20 common objects.
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Contact Detection | BEHAVE | CONTHO Precision 0.754 | Joint Reconstruction of 3D Human and Object via... | dqj5182/contho_release | 4 | Compare |
| 3D Human Reconstruction | BEHAVE | CONTHO Chamfer Distance 4.99 | Joint Reconstruction of 3D Human and Object via... | dqj5182/contho_release | 3 | Compare |
| 3D Object Reconstruction | BEHAVE | CONTHO Chamfer Distance 8.42 | Joint Reconstruction of 3D Human and Object via... | dqj5182/contho_release | 3 | Compare |
Papers archive 2025-07-28
6 shown of 6 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 53. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer | 1 | 3 | 7 Apr 2024 | ran 4 of 5 samples (1 unverified; 5 pointer-only for licence) |
| DECO: Dense Estimation of 3D Human-Scene Contact In The Wild | 2 | 1 | 26 Sep 2023 | ran 7 of 12 samples (5 unverified; 12 pointer-only for licence) |
| Capturing and Inferring Dense Full-Body Human-Scene Contact | 2 | 1 | 20 Jun 2022 | ran 1 of 1 samples (0 unverified; 1 pointer-only for licence) |
| CHORE: Contact, Human and Object REconstruction from a single RGB image | 1 | 2 | 5 Apr 2022 | ran 6 of 9 samples (3 unverified; 9 pointer-only for licence) |
| Populating 3D Scenes by Learning Human-Scene Interaction | 1 | 1 | 21 Dec 2020 | ran 1 of 1 samples (0 unverified; 1 pointer-only for licence) |
| Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild | 2 | 2 | 30 Jul 2020 | not harvested |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- BEHAVE
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections