Papers › Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

17 Jul 2023ICCV 2023 1arXiv:2307.08243archive 2025-07-28

Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, Yu Kong

Hand trajectory forecasting from egocentric views is crucial for enabling a prompt understanding of human intentions when interacting with AR/VR systems. However, existing methods handle this problem in a 2D image space which is inadequate for 3D real-world applications. In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view. To fulfill this goal, we propose an uncertainty-aware state space Transformer (USST) that takes the merits of the attention mechanism and aleatoric uncertainty within the framework of the classical state-space model. The model can be further enhanced by the velocity constraint and visual prompt tuning (VPT) on large vision transformers. Moreover, we develop an annotation workflow to collect 3D hand trajectories with high quality. Experimental results on H2O and EgoPAT3D datasets demonstrate the superiority of USST for both 2D and 3D trajectory forecasting. The code and datasets are publicly released: https://actionlab-cv.github.io/EgoHandTrajPred.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.08243")

Code

Syntology Ran 9 of 13 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 9 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

oppo-us-research/USST officialmentioned on GitHubpytorchApache-2.0 report

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

13 samples harvested; 9 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

9ran
4unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from oppo-us-research/USST. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

denormalize_traj oppo-us-research/USST/src/H2OLoader.py official repository ran Apache-2.0 (permissive) · dad48a20c072ff6e · report
draw_uv_points oppo-us-research/USST/src/utils_vis.py official repository ran Apache-2.0 (permissive) · 681c38dc9a4a43ce · report
get_depth_anchors oppo-us-research/USST/src/utils.py official repository ran Apache-2.0 (permissive) · a0bee2e8ddb51a58 · report
get_optimizer oppo-us-research/USST/src/optimizers.py official repository ran Apache-2.0 (permissive) · 1df9d391050a4608 · report
get_scheduler oppo-us-research/USST/src/optimizers.py official repository ran Apache-2.0 (permissive) · 6652cb820c60c46b · report
load_checkpoint oppo-us-research/USST/src/utils_io.py official repository ran Apache-2.0 (permissive) · 6039e11b8c330d4d · report
normalize_traj oppo-us-research/USST/src/H2OLoader.py official repository ran Apache-2.0 (permissive) · 8da2effca700d6c7 · report
send_to_gpu oppo-us-research/USST/src/utils.py official repository ran Apache-2.0 (permissive) · 4b07133043aed642 · report
world_to_camera oppo-us-research/USST/src/H2OLoader.py official repository ran Apache-2.0 (permissive) · 9b2d18e6c9ff858a · report
build_dataloaders oppo-us-research/USST/src/EgoPAT3DLoader.py official repository unverified Apache-2.0 (permissive) · 92f4580f0daea9e6 · report
gather_eval_results oppo-us-research/USST/src/utils.py official repository unverified Apache-2.0 (permissive) · aa4989cb736e5e1f · report
parse_configs oppo-us-research/USST/src/config.py official repository unverified Apache-2.0 (permissive) · 169badeb8cb30b4a · report
vis_demo oppo-us-research/USST/src/utils_vis.py official repository unverified Apache-2.0 (permissive) · b09593fc01e9188e · report

Tasks

3D Human Pose TrackingTrajectory ForecastingTrajectory PredictionVisual Prompt Tuning

Datasets

Introduced by this paper, per the archive.

EgoPAT3D-DT

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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