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 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="2106.05392")

Code

Syntology Ran 1 of 2 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/Motionformer officialmentioned in papermentioned on GitHubpytorch report
facebookresearch/xformers mentioned on GitHubpytorch 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

2 samples harvested; 1 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, 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. “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.

qkv_attn facebookresearch/Motionformer/slowfast/models/vit_helper.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 83c9daa7db244c42 · report
TrajectoryAttention facebookresearch/Motionformer/slowfast/models/vit_helper.py official repository unverified no licence file found · pointer only · 667edb27243e3e17 · report

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