Papers › Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers

9 Jun 2021NeurIPS 2021 12arXiv:2106.05392archive 2025-07-28

Mandela Patrick, Dylan Campbell, Yuki M. Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, João F. Henriques

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame t may be entirely unrelated to what is found at that location in frame t+k. These temporal correspondences should be modeled to facilitate learning about dynamic scenes. To this end, we propose a new drop-in block for video transformers -- trajectory attention -- that aggregates information along implicitly determined motion paths. We additionally propose a new method to address the quadratic dependence of computation and memory on the input size, which is particularly important for high resolution or long videos. While these ideas are useful in a range of settings, we apply them to the specific task of video action recognition with a transformer model and obtain state-of-the-art results on the Kinetics, Something--Something V2, and Epic-Kitchens datasets. Code and models are available at: https://github.com/facebookresearch/Motionformer

PaperPDFConference PDFCodeCode 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.

Syntology holds a reference implementation of Trajectory Attention, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Trajectory Attention') (how to connect); the free check have('2106.05392') needs no token.

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

Code

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

By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

facebookresearch/Motionformer officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
facebookresearch/xformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Longformer: The Long-Document Transformer (arXiv:2004.05150; that paper's own run record: 22 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 1 violated, 12 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified) and Self-attention Does Not Need O(n²) Memory (arXiv:2112.05682; that paper's own run record: 33 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 6 violated, 12 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

1ran · our draft was wrong
1unverified

Licence: 2 of the 2 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 facebookresearch/Motionformer. “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.

facebookresearch/Motionformer official repository 2 samples, 1 ran (1 instrument-failed) · 1 unverified
qkv_attn slowfast/models/vit_helper.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 83c9daa7db244c42 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TrajectoryAttention slowfast/models/vit_helper.py unverified no licence file found · pointer only · 667edb27243e3e17 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Trajectory Attention (graph method: Trajectory Attention), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. nystromformer_attention entry · level 3 · ran · honoured contract · 4e59411fad94dc32a487b0b53f24d3960a268c95715854cc53867750701a7af2

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

  1. TrajectoryAttention entry · level 0 · unverified · 667edb27243e3e17
  2. qkv_attn helper · level 1 · ran · our draft was wrong · 83c9daa7db244c42

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="2106.05392") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action ClassificationAction RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 Motionformer-HR Acc@1 81.1 #88 of 207 Archive leaderboard report
Action Classification Kinetics-400 Motionformer-HR Acc@5 95.2 #88 of 207 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-HR Action@1 44.5 #19 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-HR Noun@1 58.5 #19 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-HR Verb@1 67.0 #19 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-L Action@1 44.1 #22 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-L Noun@1 57.6 #22 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer-L Verb@1 67.1 #22 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer Action@1 43.1 #25 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer Noun@1 56.5 #25 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Mformer Verb@1 66.7 #25 of 32 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-L GFLOPs 1181x3 #54 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-L Parameters N/A #54 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-L Top-1 Accuracy 68.1 #54 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-L Top-5 Accuracy 91.2 #54 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-HR GFLOPs 958.8x3 #70 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-HR Parameters N/A #70 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-HR Top-1 Accuracy 67.1 #70 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer-HR Top-5 Accuracy 90.6 #70 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer Top-1 Accuracy 66.5 #80 of 123 Archive leaderboard report
Action Recognition Something-Something V2 Mformer Top-5 Accuracy 90.1 #80 of 123 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