Pith. sign in

REVIEW 1 cited by

baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.03291 v3 pith:2XCDFJOL submitted 2021-02-05 cs.LG cs.MA

classification cs.LGcs.MA
keywords modelingballer2vecmulti-agentspatiotemporalacrossagentsassumptionsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multi-agent spatiotemporal modeling is a challenging task from both an algorithmic design and computational complexity perspective. Recent work has explored the efficacy of traditional deep sequential models in this domain, but these architectures are slow and cumbersome to train, particularly as model size increases. Further, prior attempts to model interactions between agents across time have limitations, such as imposing an order on the agents, or making assumptions about their relationships. In this paper, we introduce baller2vec, a multi-entity generalization of the standard Transformer that can, with minimal assumptions, simultaneously and efficiently integrate information across entities and time. We test the effectiveness of baller2vec for multi-agent spatiotemporal modeling by training it to perform two different basketball-related tasks: (1) simultaneously modeling the trajectories of all players on the court and (2) modeling the trajectory of the ball. Not only does baller2vec learn to perform these tasks well (outperforming a graph recurrent neural network with a similar number of parameters by a wide margin), it also appears to "understand" the game of basketball, encoding idiosyncratic qualities of players in its embeddings, and performing basketball-relevant functions with its attention heads.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories

    cs.LG 2026-02 conditional novelty 6.0 of 10

    Using only player tracking, a dynamic masked CRF infers the possession path and detects soccer events with 75.7% F1, but on a single test match.

Pith tools