Papers › TEMOS: Generating diverse human motions from textual descriptions

TEMOS: Generating diverse human motions from textual descriptions

25 Apr 2022arXiv:2204.14109archive 2025-07-28

Mathis Petrovich, Michael J. Black, Gül Varol

We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE) training with human motion data, in combination with a text encoder that produces distribution parameters compatible with the VAE latent space. We show the TEMOS framework can produce both skeleton-based animations as in prior work, as well more expressive SMPL body motions. We evaluate our approach on the KIT Motion-Language benchmark and, despite being relatively straightforward, demonstrate significant improvements over the state of the art. Code and models are available on our webpage.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 5 ran (1 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Mathux/TEMOS officialmentioned on GitHubpytorchSyntology: 7 samples, 5 ran (4 instrument-failed) · 2 unverified 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

7 samples harvested: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
1ran
2unverified

Licence: 0 of the 7 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 Mathux/TEMOS. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Mathux/TEMOS official repository 7 samples, 5 ran (4 instrument-failed) · 2 unverified
BaseModel in 92 papers temos/model/temos.py ran MIT (permissive) · 9fe0c956aa5a444b · report fixture: returned BaseModel · level recorded 2026-09-22
l2_norm in 71 papers
census: 17 implementations from 25 papers, 8 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
temos/model/temos.py ran · our draft was wrong fingerprinted MIT (permissive) · 840f427610121a9d · report fixture: signature x1:Tensor/2/float, x2:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
matrix_of_angles temos/model/temos.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · e5840ca8045beb48 · report fixture: signature cos:Tensor/2/float, sin:Tensor/2/float, inv:bool/0/bool, dim:int/0/int · returned Tensor · level recorded 2026-09-22
remove_padding in 5 papers temos/model/temos.py ran · our draft was wrong MIT (permissive) · 6bc33934bce796a9 · report fixture: signature tensors:list/1/Tensor, lengths:list/1/int · returned list · level recorded 2026-09-22
variance temos/model/temos.py ran · our draft was wrong fingerprinted MIT (permissive) · 6ffe6eb8f867a2e8 · report fixture: signature x:Tensor/2/float, T:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-22
ComputeMetrics temos/model/temos.py unverified MIT (permissive) · 9d384a28631fdf57 · report
TEMOS temos/model/temos.py unverified MIT (permissive) · e0d65b0a859550f0 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for TEMOS (graph method: TEMOS). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. TEMOS entry · level 0 · unverified · e0d65b0a859550f0
  2. BaseModel helper · level 1 · ran · 9fe0c956aa5a444b
  3. ComputeMetrics helper · level 0 · unverified · 9d384a28631fdf57
  4. remove_padding helper · level 1 · ran · our draft was wrong · 6bc33934bce796a9
  5. l2_norm helper · level 1 · ran · our draft was wrong · 840f427610121a9d
  6. matrix_of_angles helper · level 1 · ran; the contract check could not run (RAISES) · e5840ca8045beb48
  7. variance helper · level 1 · ran · our draft was wrong · 6ffe6eb8f867a2e8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.14109") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Motion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis Inter-X TEMOS FID 29.258 #5 of 6 Archive leaderboard report
Motion Synthesis Inter-X TEMOS MMDist 6.867 #5 of 6 Archive leaderboard report
Motion Synthesis Inter-X TEMOS MModality 0.672 #5 of 6 Archive leaderboard report
Motion Synthesis Inter-X TEMOS R-Precision Top3 0.238 #5 of 6 Archive leaderboard report
Motion Synthesis InterHuman TEMOS FID 17.375 #10 of 10 Archive leaderboard report
Motion Synthesis InterHuman TEMOS MMDist 6.342 #10 of 10 Archive leaderboard report
Motion Synthesis InterHuman TEMOS MModality 0.535 #10 of 10 Archive leaderboard report
Motion Synthesis InterHuman TEMOS R-Precision Top3 0.450 #10 of 10 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