mlsanityData to 7 Oct 2026

Accurate and Diverse Sampling of Sequences based on a "Best of Many" Sample Objective

arXiv 1806.07772 ↗First posted 20 Jun 2018cs.LG cs.CV stat.MLcited by 56

Not on the map. Why?

Abstract (arXiv)

For autonomous agents to successfully operate in the real world, anticipation of future events and states of their environment is a key competence. This problem has been formalized as a sequence extrapolation problem, where a number of observations are used to predict the sequence into the future. Real-world scenarios demand a model of uncertainty of such predictions, as predictions become increasingly uncertain -- in particular on long time horizons. While impressive results have been shown on point estimates, scenarios that induce multi-modal distributions over future sequences remain challenging. Our work addresses these challenges in a Gaussian Latent Variable model for sequence prediction. Our core contribution is a "Best of Many" sample objective that leads to more accurate and more diverse predictions that better capture the true variations in real-world sequence data. Beyond our analysis of improved model fit, our models also empirically outperform prior work on three diverse tasks ranging from traffic scenes to weather data.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 9; 2022: 17; 2023: 12; 2024: 3; 2025: 8; 2026: 6.

56 papers.

Sort:

By area:

  1. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  2. 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 137
  3. 2022BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Predictioncited by 82
  4. 2023HumanMAC: Masked Motion Completion for Human Motion Predictioncited by 81
  5. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  6. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  7. 2021The Wanderings of Odysseus in 3D Scenescited by 59
  8. 2024THOR: Text to Human-Object Interaction Diffusion via Relation Interventioncited by 46
  9. 2021Divide-and-Conquer for Lane-Aware Diverse Trajectory Predictioncited by 37
  10. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  11. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  12. 2022Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Spacecited by 32
38 more
  1. 2023FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Predictioncited by 31
  2. 2022Motron: Multimodal Probabilistic Human Motion Forecastingcited by 30
  3. 2022Forecasting from LiDAR via Future Object Detectioncited by 28
  4. 2022Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Predictioncited by 28
  5. 2022Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?cited by 28
  6. 2023Stochastic Multi-Person 3D Motion Forecastingcited by 28
  7. 2023CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusioncited by 21
  8. 2021Diverse Video Generation using a Gaussian Process Triggercited by 17
  9. 2021Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centerscited by 16
  10. 2022HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAEcited by 16
  11. 2023TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Predictioncited by 16
  12. 2022Action-based Contrastive Learning for Trajectory Predictioncited by 15
  13. 2021TrajeVAE: Controllable Human Motion Generation from Trajectoriescited by 14
  14. 2022Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecastingcited by 14
  15. 2024Learning Semantic Latent Directions for Accurate and Controllable Human Motion Predictioncited by 14
  16. 2022RAP: Risk-Aware Prediction for Robust Planningcited by 12
  17. 2025Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Predictioncited by 12
  18. 2023R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intentscited by 10
  19. 2026A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokenscited by 9
  20. 2020Learning from Demonstration with Weakly Supervised Disentanglementcited by 8
  21. 2023Diverse Multimedia Layout Generation with Multi Choice Learningcited by 8
  22. 2024MotionWavelet: Human Motion Prediction via Wavelet Manifold Learningcited by 8
  23. 2022Context-Aware Scene Prediction Network (CASPNet)cited by 7
  24. 2022Learning Forward Dynamics Model and Informed Trajectory Sampler for Safe Quadruped Navigationcited by 6
  25. 2022Learning Disentangled Representations for Controllable Human Motion Predictioncited by 5
  26. 2023CASPNet++: Joint Multi-Agent Motion Predictioncited by 4
  27. 2025CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flowcited by 4
  28. 2021Maneuver-Aware Pooling for Vehicle Trajectory Predictioncited by 3
  29. 2022B'ezier Curve Gaussian Processescited by 3
  30. 2025Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networkscited by 2
  31. 2021Maneuver-based Anchor Trajectory Hypotheses at Roundaboutscited by 1
  32. 2023Manifold Contrastive Learning with Variational Lie Group Operatorscited by 1
  33. 2025MObyGaze: a film dataset of multimodal objectification densely annotated by expertscited by 1
  34. 2025HumanCM: One Step Human Motion Predictioncited by 1
  35. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  36. 2022Leveraging Trajectory Prediction for Pedestrian Video Anomaly Detectioncited by 0
  37. 2025Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictionscited by 0
  38. 2025Latent Guided Sampling for Combinatorial Optimizationcited by 0

50 most cited of 56 All 56 (JSON)