Papers › You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action...

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

15 Nov 2019arXiv:1911.06644archive 2025-07-28

Okan Köpüklü, Xiangyu Wei, Gerhard Rigoll

Spatiotemporal action localization requires the incorporation of two sources of information into the designed architecture: (1) temporal information from the previous frames and (2) spatial information from the key frame. Current state-of-the-art approaches usually extract these information with separate networks and use an extra mechanism for fusion to get detections. In this work, we present YOWO, a unified CNN architecture for real-time spatiotemporal action localization in video streams. YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation. Since the whole architecture is unified, it can be optimized end-to-end. The YOWO architecture is fast providing 34 frames-per-second on 16-frames input clips and 62 frames-per-second on 8-frames input clips, which is currently the fastest state-of-the-art architecture on spatiotemporal action localization task. Remarkably, YOWO outperforms the previous state-of-the art results on J-HMDB-21 and UCF101-24 with an impressive improvement of ~3% and ~12%, respectively. Moreover, YOWO is the first and only single-stage architecture that provides competitive results on AVA dataset. We make our code and pretrained models publicly available.

PaperPDFCodeCode 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="1911.06644")

Code

Syntology Ran 3 of 12 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · violated contract.

By repository: community (archive-listed): 12 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wei-tim/YOWO officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
BoChenUIUC/YOWO mentioned on GitHubpytorch report
Stepphonwol/my_yowo mentioned on GitHubpytorch report
nuschandra/Tennis-Stroke-Detection mentioned on GitHubpytorch report
zwtu/YOWO-Paddle mentioned on GitHubpaddleApache-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

12 samples harvested; 3 ran; 1 honoured the contract we drafted; 9 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.

1ran · honoured contract
2ran · violated contract
9unverified

Licence: 2 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

ValidateImageSize Stepphonwol/my_yowo/evaluation/Object-Detection-Metrics/pascalvoc.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 00cdc9c574c92329 · report
ValidateMandatoryArgs Stepphonwol/my_yowo/evaluation/Object-Detection-Metrics/pascalvoc.py community (archive-listed) ran · violated contract fingerprinted no licence file found · pointer only · 4cd2ba8f94cbcd1b · report
str2bool zwtu/YOWO-Paddle/applications/Ma-Net/config.py community (archive-listed) ran · violated contract Apache-2.0 (permissive) · 7c508037b40522af · report
build_assigner zwtu/YOWO-Paddle/paddlevideo/modeling/builder.py community (archive-listed) unverified Apache-2.0 (permissive) · 53a344650c2ae128 · report
build_backbone zwtu/YOWO-Paddle/paddlevideo/modeling/builder.py community (archive-listed) unverified Apache-2.0 (permissive) · bd2c60c19da90ad9 · report
build_roi_extractor zwtu/YOWO-Paddle/paddlevideo/modeling/builder.py community (archive-listed) unverified Apache-2.0 (permissive) · 3dc760b0bc6bfea5 · report
convert2cpu zwtu/YOWO-Paddle/paddlevideo/modeling/yowo_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 61eb4d295678667f · report
create_scene_based_summaries zwtu/YOWO-Paddle/paddlevideo/metrics/transnetv2_metric.py community (archive-listed) unverified Apache-2.0 (permissive) · 1e52fb40ae4513b2 · report
evaluate_scenes zwtu/YOWO-Paddle/paddlevideo/metrics/transnetv2_metric.py community (archive-listed) unverified Apache-2.0 (permissive) · 5f86f604143de119 · report
expand_bbox zwtu/YOWO-Paddle/paddlevideo/modeling/bbox_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · c434ee22884ca564 · report
predictions_to_scenes zwtu/YOWO-Paddle/paddlevideo/metrics/transnetv2_metric.py community (archive-listed) unverified Apache-2.0 (permissive) · 3da0df168740c1aa · report
truths_length zwtu/YOWO-Paddle/paddlevideo/modeling/yowo_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · df95880a2809d7b1 · report

Tasks

Action DetectionAction LocalizationAction Recognition In Videos

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Detection J-HMDB YOWO + LFB Frame-mAP 0.5 75.7 #4 of 18 Archive leaderboard report
Action Detection J-HMDB YOWO + LFB Video-mAP 0.2 88.3 #4 of 18 Archive leaderboard report
Action Detection J-HMDB YOWO + LFB Video-mAP 0.5 85.9 #4 of 18 Archive leaderboard report
Action Detection J-HMDB YOWO Frame-mAP 0.5 74.4 #5 of 18 Archive leaderboard report
Action Detection J-HMDB YOWO Video-mAP 0.2 87.8 #5 of 18 Archive leaderboard report
Action Detection J-HMDB YOWO Video-mAP 0.5 85.7 #5 of 18 Archive leaderboard report
Action Detection UCF101-24 YOWO + LFB Frame-mAP 0.5 87.3 #3 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO + LFB Video-mAP 0.1 86.1 #3 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO + LFB Video-mAP 0.2 78.6 #3 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO + LFB Video-mAP 0.5 53.1 #3 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO Frame-mAP 0.5 80.4 #5 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO Video-mAP 0.1 82.5 #5 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO Video-mAP 0.2 75.8 #5 of 19 Archive leaderboard report
Action Detection UCF101-24 YOWO Video-mAP 0.5 48.8 #5 of 19 Archive leaderboard report
Action Recognition In Videos AVA v2.1 YOWO+LFB* mAP (Val) 19.2 #1 of 1 Archive leaderboard report
Action Recognition In Videos AVA v2.2 YOWO+LFB* mAP (Val) 20.2 #1 of 2 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