Methods › General › Affinity Functions › Embedded Dot Product Affinity
Embedded Dot Product Affinity
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Embedded Dot Product Affinity is a type of affinity or self-similarity function between two points 𝕩ᵢ and 𝕩ⱼ that uses a dot product function in an embedding space:
f(𝕩ᵢ, 𝕩ⱼ) = θ(𝕩ᵢ)ᵀϕ(𝕩ⱼ)
Here θ(xᵢ) = W_θxᵢ and ϕ(xⱼ) = Wᵩxⱼ are two embeddings.
The main difference between the dot product and embedded Gaussian affinity functions is the presence of softmax, which plays the role of an activation function.
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.
-
Non-local Neural Networks 21 Nov 2017 · 32 repositories · arXiv:1711.07971Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
Tasks archive 2025-07-28
9 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 |
|---|---|
| Action Classification | 1 |
| Action Recognition | 1 |
| Instance Segmentation | 1 |
| Keypoint Detection | 1 |
| Object Detection | 1 |
| Pose Estimation | 1 |
| Position | 1 |
| Text-To-SQL | 1 |
| Video Classification | 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