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

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

20 Jun 2018arXiv:1806.07772archive 2025-07-28

Apratim Bhattacharyya, Bernt Schiele, Mario Fritz

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Human Pose Forecasting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Pose Forecasting Human3.6M BoM ADE 448 #31 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M BoM APD 6265 #31 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M BoM FDE 533 #31 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M BoM MMADE 514 #31 of 33 Archive leaderboard report
Human Pose Forecasting Human3.6M BoM MMFDE 544 #31 of 33 Archive leaderboard report
Human Pose Forecasting HumanEva-I BoM ADE@2000ms 271 #6 of 11 Archive leaderboard report
Human Pose Forecasting HumanEva-I BoM APD@2000ms 2846 #6 of 11 Archive leaderboard report
Human Pose Forecasting HumanEva-I BoM FDE@2000ms 279 #6 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections