Papers › Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

29 Mar 2024CVPR 2024 1arXiv:2403.20254archive 2025-07-28

Runhao Zeng, Xiaoyong Chen, Jiaming Liang, Huisi Wu, Guangzhong Cao, Yong Guo

Temporal action detection (TAD) aims to locate action positions and recognize action categories in long-term untrimmed videos. Although many methods have achieved promising results, their robustness has not been thoroughly studied. In practice, we observe that temporal information in videos can be occasionally corrupted, such as missing or blurred frames. Interestingly, existing methods often incur a significant performance drop even if only one frame is affected. To formally evaluate the robustness, we establish two temporal corruption robustness benchmarks, namely THUMOS14-C and ActivityNet-v1.3-C. In this paper, we extensively analyze the robustness of seven leading TAD methods and obtain some interesting findings: 1) Existing methods are particularly vulnerable to temporal corruptions, and end-to-end methods are often more susceptible than those with a pre-trained feature extractor; 2) Vulnerability mainly comes from localization error rather than classification error; 3) When corruptions occur in the middle of an action instance, TAD models tend to yield the largest performance drop. Besides building a benchmark, we further develop a simple but effective robust training method to defend against temporal corruptions, through the FrameDrop augmentation and Temporal-Robust Consistency loss. Remarkably, our approach not only improves robustness but also yields promising improvements on clean data. We believe that this study will serve as a benchmark for future research in robust video analysis. Source code and models are available at https://github.com/Alvin-Zeng/temporal-robustness-benchmark.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

alvin-zeng/temporal-robustness-benchmark officialmentioned in papermentioned on GitHubSyntology: 16 samples, 12 ran (5 instrument-failed) · 4 unverified 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

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
5ran · our draft was wrong
3ran
4unverified

Licence: 16 of the 16 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 alvin-zeng/temporal-robustness-benchmark. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

alvin-zeng/temporal-robustness-benchmark official repository 16 samples, 12 ran (5 instrument-failed) · 4 unverified
cosine_scheduler in 74 papers extract_corrupted_feature_code/videomae_v2/utils.py ran · honoured contract no licence file found · pointer only · b700fb0a3496b255 · report fixture: signature base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_epochs:int/0/int, start_warmup_value:float/0/float, warmup_steps:int/0/int · returned ndarray · level recorded 2026-09-25
get_grad_norm_ in 22 papers extract_corrupted_feature_code/videomae_v2/utils.py ran · honoured contract no licence file found · pointer only · ba1356e8ceb654d2 · report fixture: signature parameters:list/1/Tensor, norm_type:float/0/float · returned Tensor · level recorded 2026-09-25
get_loss_scale_for_deepspeed in 20 papers extract_corrupted_feature_code/videomae_v2/engine_for_finetuning.py ran · honoured contract no licence file found · pointer only · 29416043c7035e7c · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-25
get_sinusoid_encoding_table in 51 papers extract_corrupted_feature_code/videomae_v2/models/modeling_finetune.py ran · honoured contract fingerprinted no licence file found · pointer only · da651e3979a18f84 · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-22
get_start_idx_range extract_corrupted_feature_code/videomae_v2/copy_extract_tad_feature.py ran · our draft was wrong no licence file found · pointer only · 64c14fdce33f430d · report fixture: signature data_set:str/0/str · returned function · level recorded 2026-09-24
get_start_idx_range extract_corrupted_feature_code/videomae_v2/extract_tad_feature_thumos14.py ran · our draft was wrong no licence file found · pointer only · ecd670b7a5bb15ed · report fixture: signature data_set:str/0/str · returned function · level recorded 2026-09-24
load_json in 344 papers extract_corrupted_feature_code/videomae_v2/libs/pre_process_data_anet.py ran · our draft was wrong no licence file found · pointer only · a8ccf61e0ee23809 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
multiple_samples_collate in 8 papers extract_corrupted_feature_code/videomae_v2/utils.py ran · our draft was wrong no licence file found · pointer only · 024894a396cde124 · report fixture: signature batch:list/1/tuple, fold:bool/0/bool · returned tuple · level recorded 2026-09-24
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
extract_corrupted_feature_code/videomae_v2/copy_extract_tad_feature.py ran no licence file found · pointer only · 8d1dc1aa52fe2112 · report fixture: signature vid:Tensor/4/float, size:int/0/int, interpolation:str/0/str · returned Tensor · level recorded 2026-09-24
tensor_normalize in 18 papers extract_corrupted_feature_code/videomae_v2/dataset/datasets.py ran no licence file found · pointer only · 14b3b13b2e7ee844 · report fixture: signature tensor:Tensor/2/int, mean:list/1/float, std:list/1/float · returned Tensor · level recorded 2026-09-25
to_normalized_float_tensor extract_corrupted_feature_code/videomae_v2/copy_extract_tad_feature.py ran · our draft was wrong no licence file found · pointer only · eab677b96697e36b · report fixture: signature vid:Tensor/4/int · returned Tensor · level recorded 2026-09-24
train_class_batch in 17 papers extract_corrupted_feature_code/videomae_v2/engine_for_finetuning.py ran no licence file found · pointer only · c7976ea27edc377a · report fixture: signature model:callable/0/?, samples:Tensor/2/float, target:Tensor/1/int, criterion:callable/0/? · returned tuple · level recorded 2026-09-25
build_dataset in 151 papers extract_corrupted_feature_code/videomae_v2/dataset/build.py unverified no licence file found · pointer only · 283de3b7dcb770a3 · report
build_pretraining_dataset extract_corrupted_feature_code/videomae_v2/dataset/build.py unverified no licence file found · pointer only · cb5e3e409ec627d3 · report
pre_process_annotations_data extract_corrupted_feature_code/videomae_v2/libs/pre_process_data_anet.py unverified no licence file found · pointer only · a0ba0d4e39b8caf0 · report
spatial_sampling in 8 papers extract_corrupted_feature_code/videomae_v2/dataset/datasets.py unverified no licence file found · pointer only · 7e49117a60f3b108 · report

Tasks

Action DetectionBenchmarking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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