Methods › General › Attention Mechanisms › Fast Voxel Query
Fast Voxel Query
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Fast Voxel Query is a module used in the Voxel Transformer 3D object detection model implementation of self-attention, specifically Local and Dilated Attention. For each querying index vᵢ, an attending voxel index vⱼ is determined by Local and Dilated Attention. Then we can lookup the non-empty index j in the hash table with hashed vⱼ as the key. Finally, the non-empty index j is used to gather the attending feature fⱼ from ℱ for multi-head attention.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Voxel Transformer for 3D Object Detection 6 Sep 2021 · 1 repository · arXiv:2109.02497Syntology ran 0 of 7 samples · 7 unverified · 7 pointer-only (licence)
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| 3D Object Detection | 1 |
| Computational Efficiency | 1 |
| Object | 1 |
| Object Detection | 1 |
| Object Recognition | 1 |
| object-detection | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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