paper-with-me

Papers

baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents

2021-04-24 · NeurIPS 2021 12 · Michael A. Alcorn, Anh Nguyen

In many multi-agent spatiotemporal systems, agents operate under the influence of shared, unobserved variables (e.g., the play a team is executing in a game of basketball). As a result, the trajectories of the agents are often statistically dependent at any given time step; however, almost universally, multi-agent models implicitly assume the agents' trajectories are statistically independent at each time step. In this paper, we introduce baller2vec++, a multi-entity Transformer that can effectively model coordinated agents. Specifically, baller2vec++ applies a specially designed self-attention mask to a mixture of location and "look-ahead" trajectory sequences to learn the distributions of statistically dependent agent trajectories. We show that, unlike baller2vec (baller2vec++'s predecessor), baller2vec++ can learn to emulate the behavior of perfectly coordinated agents in a simulated toy dataset. Additionally, when modeling the trajectories of professional basketball players, baller2vec++ outperforms baller2vec by a wide margin.

📄 PDF Abstract BibTeX arXiv:2104.11980

Code (1)

airalcorn2/baller2vecplusplus 공식 구현 pytorch

Tasks

Trajectory Modeling

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

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

2021-02-05 · NeurIPS 2021 12 · Michael A. Alcorn, Anh Nguyen

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 doma…

Probing Identity-Specific Motion Signatures: A Controlled Diagnostic Study

2026-07-03 · Yingtie Lei, Fangxun Liu, Baicheng Wu, Colin Lee 외 arxiv

Identity recognition (e.g., person, animal re-identification) has traditionally relied heavily on static appearance cues. Yet motion--consistent, individual-specific dynamics--can provide a complementary and potentially …

Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

2025-10-27 · Junyoung Seo, Rodrigo Mira, Alexandros Haliassos, Stella Bounareli 외 arxiv

Audio-driven human animation models often suffer from identity drift during temporal autoregressive generation, where characters gradually lose their identity over time. One solution is to generate keyframes as intermedi…

RisingBALLER: A player is a token, a match is a sentence, A path towards a foundational model for football players data analytics

2024-10-01 · Akedjou Achraff Adjileye

In this paper, I introduce RisingBALLER, the first publicly available approach that leverages a transformer model trained on football match data to learn match-specific player representations. Drawing inspiration from ad…

Language ModelingLanguage ModellingSentence

Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution

2021-10-07 · Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao 외

This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We…

speech-recognitionSpeech Recognition