Under the Hood of Transformer Networks for Trajectory Forecasting
원문 초록
Transformer Networks have established themselves as the de-facto state-of-the-art for trajectory forecasting but there is currently no systematic study on their capability to model the motion patterns of people, without interactions with other individuals nor the social context. This paper proposes the first in-depth study of Transformer Networks (TF) and Bidirectional Transformers (BERT) for the forecasting of the individual motion of people, without bells and whistles. We conduct an exhaustive evaluation of input/output representations, problem formulations and sequence modeling, including a novel analysis of their capability to predict multi-modal futures. Out of comparative evaluation on the ETH+UCY benchmark, both TF and BERT are top performers in predicting individual motions, definitely overcoming RNNs and LSTMs. Furthermore, they remain within a narrow margin wrt more complex techniques, which include both social interactions and scene contexts. Source code will be released for all conducted experiments.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ECAM: A Contrastive Learning Approach to Avoid Environmental Collision in Trajectory Forecasting
Egocentric Event-Based Vision for Ping Pong Ball Trajectory Prediction
Multi-modal Knowledge Distillation-based Human Trajectory Forecasting
Controllable Motion Generation via Diffusion Modal Coupling
EMT: A Visual Multi-Task Benchmark Dataset for Autonomous Driving in the Arab Gulf Region
TrajFlow: A Generative Framework for Occupancy Density Estimation Using Normalizing Flows
토론
이 논문과 연결된 포럼 글이 아직 없습니다.