Papers › Temporal Recurrent Networks for Online Action Detection

Temporal Recurrent Networks for Online Action Detection

18 Nov 2018ICCV 2019 10arXiv:1811.07391archive 2025-07-28

Mingze Xu, Mingfei Gao, Yi-Ting Chen, Larry S. Davis, David J. Crandall

Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. However, important real-time applications including surveillance and driver assistance systems require identifying actions as soon as each video frame arrives, based only on current and historical observations. In this paper, we propose a novel framework, Temporal Recurrent Network (TRN), to model greater temporal context of a video frame by simultaneously performing online action detection and anticipation of the immediate future. At each moment in time, our approach makes use of both accumulated historical evidence and predicted future information to better recognize the action that is currently occurring, and integrates both of these into a unified end-to-end architecture. We evaluate our approach on two popular online action detection datasets, HDD and TVSeries, as well as another widely used dataset, THUMOS'14. The results show that TRN significantly outperforms the state-of-the-art.

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="1811.07391")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: official repository: 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xumingze0308/TRN.pytorch officialmentioned on GitHubpytorchMIT 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

6 samples harvested; 0 ran; 0 honoured the contract we drafted; 6 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.

6unverified

Licence: 0 of the 6 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 xumingze0308/TRN.pytorch. “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.

build_data_info xumingze0308/TRN.pytorch/configs/build.py official repository unverified MIT (permissive) · 4888ea60ba4fbdc8 · report
build_feature_extractor xumingze0308/TRN.pytorch/lib/models/feature_extractor.py official repository unverified MIT (permissive) · 1c7598692f8b3506 · report
compute_result xumingze0308/TRN.pytorch/lib/utils/eval_utils.py official repository unverified MIT (permissive) · dbc431aa4aaf475c · report
compute_result_multilabel xumingze0308/TRN.pytorch/lib/utils/eval_utils.py official repository unverified MIT (permissive) · 6d8e72ad0258e9b9 · report
fc_relu xumingze0308/TRN.pytorch/lib/models/generalized_trn.py official repository unverified MIT (permissive) · 15ae50b882b812af · report
setup_logger xumingze0308/TRN.pytorch/lib/utils/logger.py official repository unverified MIT (permissive) · a21f1dc5b99f0411 · report

Tasks

Action DetectionOnline Action Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Online Action Detection THUMOS'14 TRN mAP 62.1 #13 of 15 Archive leaderboard report
Online Action Detection TVSeries TRN mCAP 86.2 #12 of 13 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