Multi-heads of both self and cross attentions
Source: Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic VideosPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Pose Estimation | 9 | 14.06% |
Model Predictive Control | 5 | 7.81% |
Collision Avoidance | 5 | 7.81% |
Reinforcement Learning | 4 | 6.25% |
Reinforcement Learning (RL) | 4 | 6.25% |
Action Triplet Recognition | 3 | 4.69% |
Deep Reinforcement Learning | 2 | 3.13% |
Kolmogorov-Arnold Networks | 1 | 1.56% |
Combinatorial Optimization | 1 | 1.56% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |