Auxiliary tasks benefit 3d skeleton-based human motion prediction

C Xu, RT Tan, Y Tan, S Chen… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Exploring spatial-temporal dependencies from observed motions is one of the core
challenges of human motion prediction. Previous methods mainly focus on dedicated …

Singulartrajectory: Universal trajectory predictor using diffusion model

I Bae, YJ Park, HG Jeon - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
There are five types of trajectory prediction tasks: deterministic stochastic domain adaptation
momentary observation and few-shot. These associated tasks are defined by various factors …

Can language beat numerical regression? language-based multimodal trajectory prediction

I Bae, J Lee, HG Jeon - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
Abstract Language models have demonstrated impressive ability in context understanding
and generative performance. Inspired by the recent success of language foundation models …

[HTML][HTML] Gatraj: A graph-and attention-based multi-agent trajectory prediction model

H Cheng, M Liu, L Chen, H Broszio, M Sester… - ISPRS Journal of …, 2023‏ - Elsevier
Trajectory prediction has been a long-standing problem in intelligent systems like
autonomous driving and robot navigation. Models trained on large-scale benchmarks have …

T4p: Test-time training of trajectory prediction via masked autoencoder and actor-specific token memory

D Park, J Jeong, SH Yoon, J Jeong… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Trajectory prediction is a challenging problem that requires considering interactions among
multiple actors and the surrounding environment. While data-driven approaches have been …

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics

L Wu, Z Hou, J Yuan, Y Rong… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Learning to represent and simulate the dynamics of physical systems is a crucial yet
challenging task. Existing equivariant Graph Neural Network (GNN) based methods have …

Lanecpp: Continuous 3d lane detection using physical priors

M Pittner, J Janai… - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
Monocular 3D lane detection has become a fundamental problem in the context of
autonomous driving which comprises the tasks of finding the road surface and locating lane …

A survey of geometric graph neural networks: Data structures, models and applications

J Han, J Cen, L Wu, Z Li, X Kong, R Jiao, Z Yu… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Geometric graph is a special kind of graph with geometric features, which is vital to model
many scientific problems. Unlike generic graphs, geometric graphs often exhibit physical …

Skeleton-in-context: Unified skeleton sequence modeling with in-context learning

X Wang, Z Fang, X Li, X Li… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
In-context learning provides a new perspective for multi-task modeling for vision and NLP.
Under this setting the model can perceive tasks from prompts and accomplish them without …

Socialcircle: Learning the angle-based social interaction representation for pedestrian trajectory prediction

C Wong, B **a, Z Zou, Y Wang… - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
Analyzing and forecasting trajectories of agents like pedestrians and cars in complex scenes
has become more and more significant in many intelligent systems and applications. The …