Papers › TIM: A Time Interval Machine for Audio-Visual Action Recognition

TIM: A Time Interval Machine for Audio-Visual Action Recognition

8 Apr 2024CVPR 2024 1arXiv:2404.05559archive 2025-07-28

Jacob Chalk, Jaesung Huh, Evangelos Kazakos, Andrew Zisserman, Dima Damen

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale interval queries, outperforming SOTA on EPIC-KITCHENS-100 for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of integrating the two modalities and modelling their time intervals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2404.05559")

Code

Syntology Ran 11 of 12 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 10 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jacobchalk/tim officialmentioned in papermentioned 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

12 samples harvested; 11 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
10ran
1unverified

Licence: 12 of the 12 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 JacobChalk/TIM. “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.

get_sinusoid_encoding_table JacobChalk/TIM/feature_extractors/VideoMAE/modeling_finetune.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · da651e3979a18f84 · report
load_gt_segmentations JacobChalk/TIM/detection/eval_detection/evaluate_detection_json.py official repository ran no licence file found · pointer only · 3777cf3d1476af2d · report
load_gt_segmentations JacobChalk/TIM/detection/eval_detection/evaluate_detection_json_ek100.py official repository ran no licence file found · pointer only · 5a45614aa6767966 · report
load_predicted_segmentations JacobChalk/TIM/detection/eval_detection/evaluate_detection_json.py official repository ran no licence file found · pointer only · 91dbf25ea34df77b · report
load_predicted_segmentations JacobChalk/TIM/detection/eval_detection/evaluate_detection_json_ek100.py official repository ran no licence file found · pointer only · 67d66192df8ebf14 · report
sec_to_timestamp JacobChalk/TIM/feature_extractors/make_framepickle.py official repository ran fingerprinted no licence file found · pointer only · eb3884a04aa0a2ed · report
sec_to_timestamp JacobChalk/TIM/feature_extractors/make_videoinfo.py official repository ran fingerprinted no licence file found · pointer only · 2e4e22e309ff1d23 · report
timestamp_to_sec JacobChalk/TIM/feature_extractors/make_framepickle.py official repository ran no licence file found · pointer only · 8a8e3d27500e4fd8 · report
timestamp_to_seconds JacobChalk/TIM/feature_extractors/make_videoinfo.py official repository ran no licence file found · pointer only · 61dfbd1801e160f7 · report
timestamp_to_seconds JacobChalk/TIM/detection/eval_detection/evaluate_detection_json.py official repository ran no licence file found · pointer only · d45a7468dd11e23d · report
train_class_batch JacobChalk/TIM/feature_extractors/VideoMAE/engine_for_finetuning.py official repository ran no licence file found · pointer only · 93f25c853b7eeac5 · report
get_loss_scale_for_deepspeed JacobChalk/TIM/feature_extractors/VideoMAE/engine_for_finetuning.py official repository unverified no licence file found · pointer only · 29416043c7035e7c · report

Tasks

Action DetectionAction Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition EPIC-KITCHENS-100 TIM Action@1 56.4 #2 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TIM Noun@1 66.4 #2 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 TIM Verb@1 76.2 #2 of 32 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