Research map / Probabilistic and scientific modeling / Variational and generative sampling
Diverse Trajectory Forecasting with Determinantal Point Processes
Ye Yuan, Kris M. Kitani
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| learn a DSF and optimize its latent samples with expected-cardinality DPP diversity loss | cVAE trajectory forecasting · Synthetic 2D balanced and imbalanced | ASD: 0.022 -> 0.147; 0.021 -> 0.207 | Improved |
| learn a DSF and optimize its latent samples with expected-cardinality DPP diversity loss | cVAE trajectory forecasting · Human motion forecasting | ADE: 0.332 -> 0.259 | Improved |
| replace expected-cardinality loss with DPP negative log likelihood (ablation) | DSF · Human3.6M N=10 | ASD: 0.381 -> 0.343 | Hurt |
| replace expected-cardinality loss with DPP negative log likelihood (ablation) | DSF · Human3.6M N=50 | ADE | Hurt |
| use cosine similarity instead of the Gaussian trajectory similarity kernel (ablation) | DSF · Human3.6M N=10 | ASD: 0.381 -> 5.093 | Improved |
| use cosine similarity instead of the Gaussian trajectory similarity kernel (ablation) | DSF · Human3.6M N=10 | ADE: 0.340 -> 2.588 | Hurt |
| apply DPP selection to sampled latent codes rather than optimizing the sampler in trajectory space (ablation) | cVAE-LDPP · Human3.6M N=10 | ADE: 0.340 -> 0.373 | Hurt |
| apply DPP selection to sampled latent codes rather than optimizing the sampler in trajectory space (ablation) | cVAE-LDPP · Human3.6M N=10 | ASD: 0.381 -> 0.280 | Hurt |
Closest papers by meaning
- Likelihood-Based Diverse Sampling for Trajectory Forecasting (ICCV 2021 · similarity 0.91)
- SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction (ECCV 2020 · similarity 0.87)
- Analyzing the Variety Loss in the Context of Probabilistic Trajectory Prediction (ICCV 2019 · similarity 0.87)
- SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model (CVPR 2024 · similarity 0.85)
- Motion Diversification Networks (CVPR 2024 · similarity 0.85)
- Quantifying Uncertainty in Motion Prediction with Variational Bayesian Mixture (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
