Papers › BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection

BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection

5 May 2022arXiv:2205.02717archive 2025-07-28

Min Yang, Guo Chen, Yin-Dong Zheng, Tong Lu, LiMin Wang

Temporal action detection (TAD) is extensively studied in the video understanding community by generally following the object detection pipeline in images. However, complex designs are not uncommon in TAD, such as two-stream feature extraction, multi-stage training, complex temporal modeling, and global context fusion. In this paper, we do not aim to introduce any novel technique for TAD. Instead, we study a simple, straightforward, yet must-known baseline given the current status of complex design and low detection efficiency in TAD. In our simple baseline (termed BasicTAD), we decompose the TAD pipeline into several essential components: data sampling, backbone design, neck construction, and detection head. We extensively investigate the existing techniques in each component for this baseline, and more importantly, perform end-to-end training over the entire pipeline thanks to the simplicity of design. As a result, this simple BasicTAD yields an astounding and real-time RGB-Only baseline very close to the state-of-the-art methods with two-stream inputs. In addition, we further improve the BasicTAD by preserving more temporal and spatial information in network representation (termed as PlusTAD). Empirical results demonstrate that our PlusTAD is very efficient and significantly outperforms the previous methods on the datasets of THUMOS14 and FineAction. Meanwhile, we also perform in-depth visualization and error analysis on our proposed method and try to provide more insights on the TAD problem. Our approach can serve as a strong baseline for future TAD research. The code and model will be released at https://github.com/MCG-NJU/BasicTAD.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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.

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

Code

mcg-nju/basictad officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
cg1177/dcan mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AAAI id aaai_19900 (that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action DetectionObject DetectionTemporal Action LocalizationVideo Understandingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Action Localization THUMOS14 BasicTAD (R50-SlowOnly) Avg mAP (0.3:0.7) 59.6 #1 of 1 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) Avg mAP (0.3:0.7) 59.6 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) mAP IOU@0.3 75.5 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) mAP IOU@0.4 70.8 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) mAP IOU@0.5 63.5 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) mAP IOU@0.6 50.9 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (160,6,192,R50-SlowOnly) mAP IOU@0.7 37.4 #15 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) Avg mAP (0.3:0.7) 54.9 #18 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) mAP IOU@0.3 68.4 #18 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) mAP IOU@0.4 65.0 #18 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) mAP IOU@0.5 58.6 #18 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) mAP IOU@0.6 49.2 #18 of 42 Archive leaderboard report
Temporal Action Localization THUMOS’14 BasicTAD (112,3,96,R50-SlowOnly) mAP IOU@0.7 33.5 #18 of 42 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