Papers › Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?

10 Apr 2020arXiv:2004.04968archive 2025-07-28

Hirokatsu Kataoka, Tenga Wakamiya, Kensho Hara, Yutaka Satoh

How can we collect and use a video dataset to further improve spatiotemporal 3D Convolutional Neural Networks (3D CNNs)? In order to positively answer this open question in video recognition, we have conducted an exploration study using a couple of large-scale video datasets and 3D CNNs. In the early era of deep neural networks, 2D CNNs have been better than 3D CNNs in the context of video recognition. Recent studies revealed that 3D CNNs can outperform 2D CNNs trained on a large-scale video dataset. However, we heavily rely on architecture exploration instead of dataset consideration. Therefore, in the present paper, we conduct exploration study in order to improve spatiotemporal 3D CNNs as follows: (i) Recently proposed large-scale video datasets help improve spatiotemporal 3D CNNs in terms of video classification accuracy. We reveal that a carefully annotated dataset (e.g., Kinetics-700) effectively pre-trains a video representation for a video classification task. (ii) We confirm the relationships between #category/#instance and video classification accuracy. The results show that #category should initially be fixed, and then #instance is increased on a video dataset in case of dataset construction. (iii) In order to practically extend a video dataset, we simply concatenate publicly available datasets, such as Kinetics-700 and Moments in Time (MiT) datasets. Compared with Kinetics-700 pre-training, we further enhance spatiotemporal 3D CNNs with the merged dataset, e.g., +0.9, +3.4, and +1.1 on UCF-101, HMDB-51, and ActivityNet datasets, respectively, in terms of fine-tuning. (iv) In terms of recognition architecture, the Kinetics-700 and merged dataset pre-trained models increase the recognition performance to 200 layers with the Residual Network (ResNet), while the Kinetics-400 pre-trained model cannot successfully optimize the 200-layer architecture.

PaperPDFCodeCode 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 22 code samples harvested from 4 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 3 repositories, 6 ran (4 with no instrument failure; 2 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

kenshohara/3D-ResNets-PyTorch officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 10 ran (0 instrument-failed) · 2 unverified report
3D-ResNets-Reproduction/Reference-Project mentioned on GitHubpytorchMITSyntology: not harvested report
KevinPang180/3D-ResNets-PaddlePaddle mentioned on GitHubpytorchApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
Mind23-2/MindCode-68 mentioned on GitHubmindsporeSyntology: not harvested report
Oichii/resnet3D_pulse mentioned on GitHubpytorchMITSyntology: 3 samples, 0 ran · 3 unverified report
Shito0907/3D_resnet mentioned on GitHubpytorchMITSyntology: not harvested report
kaleab-k/VideoAT mentioned on GitHubpytorchSyntology: not harvested report
rutajoshi/cs231n-project mentioned on GitHubpytorchMITSyntology: not harvested report
ziqi-zhang/3D-ResNets-PyTorch mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 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

22 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
14ran
6unverified

Licence: 0 of the 22 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 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

kenshohara/3D-ResNets-PyTorch official repository 12 samples, 10 ran (0 instrument-failed) · 2 unverified
conv1x3x3 in 6 papers models/resnet2p1d.py ran MIT (permissive) · b471bd70ae7033b7 · report fixture: signature in_planes:int/0/int, mid_planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-25
conv3x1x1 models/resnet2p1d.py ran MIT (permissive) · 69cf8d9e032b3251 · report fixture: signature mid_planes:int/0/int, planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-25
generate_model in 8 papers models/densenet.py ran MIT (permissive) · f1faf2b3a11cd3c6 · report fixture: signature model_depth:int/0/int · returned DenseNet · level recorded 2026-09-25
get_class_labels in 6 papers datasets/activitynet.py ran MIT (permissive) · 0b3b02ceef079aae · report fixture: signature data:dict/0/? · returned dict · level recorded 2026-09-25
get_fine_tuning_parameters in 14 papers model.py ran MIT (permissive) · c59254c1a5526d41 · report fixture: signature model:callable/0/?, ft_begin_module:str/0/str · returned list · level recorded 2026-09-25
get_mean_std in 17 papers mean.py ran MIT (permissive) · d35f7d3b70ef9b70 · report fixture: signature value_scale:float/0/float, dataset:str/0/str · returned tuple · level recorded 2026-09-25
get_module_name in 7 papers model.py ran fingerprinted MIT (permissive) · c347904eafd0d22e · report fixture: signature name:str/0/str · returned str · level recorded 2026-09-25
get_n_frames datasets/activitynet.py ran MIT (permissive) · 92f569d7dc7c5f17 · report fixture: signature video_path:PosixPath/0/? · returned int · level recorded 2026-09-25
get_video_ids_annotations_and_fps datasets/activitynet.py ran MIT (permissive) · 8dd3e55b4ebf8cc6 · report fixture: signature data:dict/0/?, subset:str/0/str · returned tuple · level recorded 2026-09-25
image_name_formatter dataset.py ran fingerprinted MIT (permissive) · 138fe18f637e2e35 · report fixture: signature x:int/0/int · returned str · level recorded 2026-09-25
generate_model in 8 papers models/pre_act_resnet.py unverified MIT (permissive) · 45343fb6310c6c49 · report
get_video_results inference.py unverified MIT (permissive) · c0e7431aff3ed281 · report
KevinPang180/3D-ResNets-PaddlePaddle community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
group_multi_scale_crop reader.py ran Apache-2.0 (permissive) · 1f00a5b96d91ec0d · report fixture: signature img_group:list/1/Image, target_size:int/0/int, scales:list/1/int, max_distort:int/0/int, fix_crop:bool/0/bool, more_fix_crop:bool/0/bool · returned list · level recorded 2026-09-24
group_random_crop reader.py ran Apache-2.0 (permissive) · 865572e58d23a992 · report fixture: signature img_group:list/1/Image, target_size:int/0/int · returned list · level recorded 2026-09-24
group_random_flip reader.py ran fingerprinted Apache-2.0 (permissive) · e5bd557fa83521ca · report fixture: signature img_group:list/1/Image · returned list · level recorded 2026-09-24
merge_configs in 11 papers config.py ran Apache-2.0 (permissive) · 0e03ada3bc54e4fb · report fixture: signature cfg:Config/0/?, sec:str/0/str, args_dict:dict/0/? · returned Config · level recorded 2026-09-24
Oichii/resnet3D_pulse community (archive-listed) 3 samples, 0 ran · 3 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
ResNet_train.py unverified MIT (permissive) · f0c9a29156911331 · report
generate_model in 8 papers ResNet_model.py unverified MIT (permissive) · c03ab7046d986487 · report
validate in 313 papers ResNet_train.py unverified MIT (permissive) · 9436376f4d71d64e · report
ziqi-zhang/3D-ResNets-PyTorch community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
conv1x1x1 in 11 papers models/resnet.py ran · our draft was wrong MIT (permissive) · 213ccc8fb87ee8d9 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-22
conv3x3x3 in 32 papers models/resnet.py ran · our draft was wrong MIT (permissive) · c3b215555357b9d1 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv3d · level recorded 2026-09-22
generate_model in 8 papers models/resnet.py unverified MIT (permissive) · 392a1ed5b8624559 · report

Tasks

General ClassificationOpen-Ended Question AnsweringVideo ClassificationVideo Recognition

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