aquamam
An autoregressive, quaternion manifold model for rapidly estimating complex SO(3) distributions. (by airalcorn2)
baller2vecplusplus
A look-ahead multi-entity Transformer for modeling coordinated agents. (by airalcorn2)
| aquamam | baller2vecplusplus | |
|---|---|---|
| 3 | 5 | |
| 1 | 38 | |
| - | - | |
| 3.6 | 0.0 | |
| 8 months ago | over 2 years ago | |
| Python | Python | |
| MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
aquamam
Posts with mentions or reviews of aquamam.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-07-27.
-
DeepVoxels: Learning Persistent 3D Feature Embeddings
This paper is near and dear to my heart because I saw the presentation at the first and only machine learning conference I've ever attended (thanks a lot, ICML, NeurIPS (x2), and ICLR!). It's a neural rendering approach that precedes NeRF, but you can see some similarities (even more so in the follow-up paper about "Scene Representation Networks"). Sitzmann and co-authors also published a paper about using sinusoidal activations in implicit representation models at NeurIPS 2020, the same conference where the "Fourier Features" paper (which has many of the same authors as the NeRF paper) was also presented. It's always interesting to me to see how ideas in science often pop-up at the same time from different researchers (e.g., attention).
- AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions
-
[R] AQuaMaM: An Autoregressive, Quaternion Manifold Model for Rapidly Estimating Complex SO(3) Distributions
Code for the paper can be found here.
baller2vecplusplus
Posts with mentions or reviews of baller2vecplusplus.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-07-27.
-
DeepVoxels: Learning Persistent 3D Feature Embeddings
This paper is near and dear to my heart because I saw the presentation at the first and only machine learning conference I've ever attended (thanks a lot, ICML, NeurIPS (x2), and ICLR!). It's a neural rendering approach that precedes NeRF, but you can see some similarities (even more so in the follow-up paper about "Scene Representation Networks"). Sitzmann and co-authors also published a paper about using sinusoidal activations in implicit representation models at NeurIPS 2020, the same conference where the "Fourier Features" paper (which has many of the same authors as the NeRF paper) was also presented. It's always interesting to me to see how ideas in science often pop-up at the same time from different researchers (e.g., attention).
-
"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem", Wen et al 2022 (Decision Transformer for MARL: interleave agent choices)
Another prior art from /r/ML discussion: "baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents", Alcorn & Nguyen 2021 (what a name).
-
[R] Multi-Agent Reinforcement Learning can now be solved by the Transformer!
Congratulations on the paper! Could you consider citing baller2vec++ as relevant prior work? baller2vec++ exploits a chain rule decomposition of the joint distribution (instead of policy) of simultaneous agent behaviors to better model multi-agent systems, and similarly uses an autoregressive Transformer over the agents to accomplish this task.
-
[D] The reviews and my rebuttals for my rejected ICML and NeurIPS submissions
To increase transparency about the review process, and in the hopes that it might help others shape their papers/rebuttals, I'm sharing the reviews and my rebuttals for my ICML submission of baller2vec, my NeurIPS submission of baller2vec, and my NeurIPS submission of baller2vec++, each of which was rejected.
-
[R] baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents
Code for the paper can be found here.
What are some alternatives?
When comparing aquamam and baller2vecplusplus you can also consider the following projects:
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
baller2vec - A multi-entity Transformer for multi-agent spatiotemporal modeling.
Hierarchical-Localization - Visual localization made easy with hloc
ailia-models - The collection of pre-trained, state-of-the-art AI models for ailia SDK
SuperGluePretrainedNetwork - SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
DeepLabCut - Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
AI-basketball-analysis - :basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.