It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
By Karttikeya Mangalam, Harshayu Girase, Shreya Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, Adrien Gaidon. European Conference on Computer Vision, 2020
597 citations recorded by the source corpus.
Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple "truncation-trick" for improving few-shot multi-modal trajectory prediction performance. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by ~20.9% and on the ETH/UCY benchmark by ~40.8%. Project homepage: this https URL
Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/08809dada9c78ed7cb6eec79e41c72759364d22f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernt Schiele
- Cordelia Schmid
- Chen Sun
- Luc Van Gool
- Jitendra Malik
- Trevor Darrell
- Andrew Zisserman
- Hang Zhao
In Automotive Engineering
- Hang Zhao
- Shaoshuai Shi
- Dengxin Dai
- Bernt Schiele
- Li Jiang
- Benjamin Sapp
- Chen Sun
- Karttikeya Mangalam
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Cordelia Schmid
- Xiaogang Wang
- Jitendra Malik
- Bernt Schiele
- Andrew Zisserman
- Dacheng Tao
- Trevor Darrell
Citations in the corpus
- Motion Transformer with Global Intention Localization and Local Movement Refinement (2022, background): “Goal-based methods [61, 40, 15, 30] are another kinds of models where they first estimate several goal points of the agents and then complete full trajectory for each goal.”
- Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos (2022, methodology): “Following the evaluation protocol in previous work [57, 59, 67, 89] that involves stochastic unit in trajectory estimation, we report the minimum of among 20 samples for trajectory evaluation.”
- From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting (2020, methodology): “This is highlighted in [28] which establish previous state-of-the-art without any RGB information underlining the mis-use of image information in prior works.”
- GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation (2021, methodology): “69 Generative methods can also be used to obtain multimodal predictions, through either Variational 70 Auto Encoders [10, 16, 11, 17] or Generative Adversarial Networks [18, 19], but they require multi71 ple forward passes for each prediction, do not guarantee diversity in the samples obtained and t”
- TNT: Target-driveN Trajectory Prediction (2020, methodology): “First, future time steps are conditionally independent, which makes our model computationally efficient by avoiding sequential predictions, as is done in [33, 34, 21, 31].”