Trajectory Transformer

Trajectory Transformers are a class of neural network models designed to predict and analyze sequences of movements or events, finding applications in diverse fields like autonomous driving, robotics, and video processing. Current research focuses on improving generalization across different scenarios (e.g., unseen domains), enhancing efficiency through techniques like sparse activation and optimized memory usage, and leveraging latent variables for improved planning and decision-making. These advancements are significant because they enable more robust and efficient solutions for complex temporal prediction tasks, impacting areas such as next-POI recommendation, 3D object detection, and video frame interpolation.

Papers

February 13, 2024

MetaTra: Meta-Learning for Generalized Trajectory Prediction in Unseen Domain
Xiaohe Li, Feilong Huang, Zide Fan, Fangli Mou, Yingyan Hou, Chen Qian, Lijie Wen
Trajectory Prediction Unseen Domain Meta Learning Framework Trajectory Pattern Trajectory Transformer

February 7, 2024

Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference
Deqian Kong, Dehong Xu, Minglu Zhao, Bo Pang, Jianwen Xie, Andrew Lizarraga, Yuhao Huang, Sirui Xie, Ying Nian Wu
Offline Reinforcement Learning Generative Modeling Task Planning Latent Variable Planning Transformer Trajectory Transformer

December 13, 2023

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection
Kuan-Chih Huang, Weijie Lyu, Ming-Hsuan Yang, Yi-Hsuan Tsai
Object Detection Long Short Term Memory Lidar Based 3D Object Detector Trajectory Transformer Trajectory Encoder

March 3, 2023

GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
Song Yang, Jiamou Liu, Kaiqi Zhao
Spatio Temporal Context Next DiT POI Recommendation Trajectory Transformer

July 19, 2022

TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation
Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian
Motion Estimation Video Frame Interpolation Consecutive Frame Image Warping Intermediate Frame Trajectory Transformer

May 8, 2022

Mutual Distillation Learning Network for Trajectory-User Linking
Wei Chen, Shuzhe Li, Chao Huang, Yanwei Yu, Yongguo Jiang, Junyu Dong
User Trajectory Trajectory Transformer Mobility Datasets Trajectory Encoder

April 8, 2022

Learning Trajectory-Aware Transformer for Video Super-Resolution
Chengxu Liu, Huan Yang, Jianlong Fu, Xueming Qian
LeArning Abstract Long Range Video Super Resolution Spatio Temporal Learning Trajectory Transformer

March 14, 2022

Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning
Qinjie Lin, Han Liu, Biswa Sengupta
Reinforcement Learning Multi Task Reinforcement Learning Multi Task Policy Trajectory Transformer