Papers › Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Joao Carreira, Andrew Zisserman
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.9% on HMDB-51 and 98.0% on UCF-101.
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):
get_harvested_code_for_paper(arxiv_id="1705.07750")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1705.07750", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1705.07750")
Code
Syntology 28 code samples: 24 from 8 repositories linked to this paper, 4 identical to code harvested from another paper's repository. Across all 28: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 24 samples from 8 repositories, 12 ran (10 with no instrument failure; 2 where Syntology's instrument failed); 4 identical to code first harvested elsewhere. 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 4 of its repositories that Syntology harvested for other papers:
- LukasHedegaard/co3d, community (archive-listed): harvested for another paper, listed under the repository
- OanaIgnat/i3d_keras, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmaction2, community (archive-listed): harvested for another paper, listed under the repository
- xiuyu0000/vision, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
34 repositories listed; official and paper-mentioned ones first.
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
28 samples harvested: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 12 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.
Licence: 7 of the 28 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 8 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. 4 samples are listed last, in a group without a repository. “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”. For 2 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape; for 1, for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.
afb1546ff0edeb60 · report
fixture: returned I3dRgbUcf101 · level recorded 2026-09-22 86ab28ecf5cc710e · report
fixture: returned InceptionModule · level recorded 2026-09-22 0cca1672c970b785 · report
fixture: returned MaxPool3dSamePadding · level recorded 2026-09-22 8f662573b6fac87b · report
fixture: returned Unit3D · level recorded 2026-09-22 ef9a979720d596db · report
d52425813034770e · report
fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24 a0d388f676f51bcf · report
fixture: signature inp:Tensor/5/float · returned Tensor · level recorded 2026-09-22 7d55ae5d78e79327 · report
fixture: signature inp:Tensor/5/float · returned Tensor · level recorded 2026-09-24 c84c49b2d9ed0ea8 · report
fixture: signature filter_shape:tuple/1/int, stride:tuple/1/int, mod:int/0/int · returned tuple · level recorded 2026-09-22 162d0ddf9cfd939e · report
fixture: returned MaxPool3dTFPadding · level recorded 2026-09-22 7db92abddea0028b · report
fixture: returned Unit3Dpy · level recorded 2026-09-22 42f2e711eec1d11f · report
fixture: signature padding_name:bytes/0/?, conv_shape:list/1/int · returned list · level recorded 2026-09-22 040b15375c9a9f1d · report
c8b696aa9e2edd20 · report
8f8c0c36c90310ff · report
fixture: returned ResNet · level recorded 2026-09-22 2e635f36d98dce68 · report
4 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
43c0211ff8dbca5f · report
fixture: signature x:Tensor/5/float, planes:int/0/int, stride:int/0/int · returned Tensor · level recorded 2026-09-22 0b19df9669841d40 · report
fixture: returned list · level recorded 2026-09-22 45cc344e60f640a1 · report
fixture: signature filter_shape:list/1/int, stride:list/1/int · returned tuple · level recorded 2026-09-22 81ec17604dc709cc · report
fixture: signature padding_shapes:list/1/tuple · returned tuple · level recorded 2026-09-22 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
8 sibling assemblies for Two-Stream Inflated 3D Con-vNet (I3D) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- ResNet entry · level 1 · ran ·
8f8c0c36c90310ff - downsample_basic_block model · level 1 · ran · our draft was wrong ·
43c0211ff8dbca5f
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 11 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- I3D entry · level 0 · unverified ·
4165130355776ce6 - MaxPool3dTFPadding model · level 1 · ran ·
162d0ddf9cfd939e - Mixed model · level 0 · unverified ·
1d5fe61bcc4a9357 - Unit3Dpy model · level 1 · ran ·
7db92abddea0028b - load_conv3d helper · level 0 · unverified ·
c8b696aa9e2edd20 - load_mixed helper · level 0 · unverified ·
06d60d111918490e - get_padding_shape helper · level 1 · ran; the contract check could not run (RAISES) ·
45cc344e60f640a1 - simplify_padding helper · level 1 · ran; the contract check could not run (RAISES) ·
81ec17604dc709cc - get_bn_params helper · level 0 · unverified ·
040b15375c9a9f1d - get_conv_params helper · level 1 · ran · our draft was wrong ·
0b19df9669841d40 - _get_padding helper · level 1 · ran · our draft was wrong ·
42f2e711eec1d11f
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- I3D entry · level 1 · ran ·
d52425813034770e
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- InceptionI3d entry · level 0 · unverified ·
ef9a979720d596db - InceptionModule model · level 1 · ran ·
86ab28ecf5cc710e - MaxPool3dSamePadding helper · level 1 · ran ·
0cca1672c970b785 - Unit3D model · level 1 · ran ·
8f662573b6fac87b
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- I3dRgbUcf101 entry · level 1 · ran ·
afb1546ff0edeb60
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- InceptionI3d entry · level 0 · unverified ·
2e635f36d98dce68 - InceptionModule model · level 1 · ran ·
86ab28ecf5cc710e - MaxPool3dSamePadding helper · level 1 · ran ·
0cca1672c970b785 - Unit3D model · level 1 · ran ·
8f662573b6fac87b
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 8 siblings
- InceptionI3d entry · level 0 · unverified ·
434390ea358bf40f - InceptionModule model · level 1 · ran ·
86ab28ecf5cc710e - MaxPool3dSamePadding model · level 1 · ran ·
0cca1672c970b785 - Unit3D model · level 1 · ran ·
8f662573b6fac87b
harvested Assembly for Two-Stream Inflated 3D Con-vNet (I3D) (graph method: Two-Stream Inflated 3D Con-vNet (I3D)). 11 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- I3D entry · level 0 · unverified ·
c124939daa593331 - MaxPool3dTFPadding model · level 1 · ran ·
a0d388f676f51bcf - Mixed model · level 0 · unverified ·
1f304ea60f4c8fe0 - Unit3Dpy model · level 1 · ran ·
7d55ae5d78e79327 - load_conv3d helper · level 0 · unverified ·
5864cfb44b943815 - load_mixed helper · level 0 · unverified ·
42cfae5f88305c31 - get_padding_shape helper · level 1 · ran; the contract check could not run (RAISES) ·
c84c49b2d9ed0ea8 - simplify_padding helper · level 1 · ran; the contract check could not run (RAISES) ·
81ec17604dc709cc - get_bn_params helper · level 0 · unverified ·
040b15375c9a9f1d - get_conv_params helper · level 1 · ran · our draft was wrong ·
0b19df9669841d40 - _get_padding helper · level 1 · ran · our draft was wrong ·
42f2e711eec1d11f
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1705.07750") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Classification | Charades | I3D | MAP | 32.9 | #39 of 49 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | I3D | Acc@1 | 71.1 | #179 of 207 | Archive leaderboard | report |
| Action Classification | Kinetics-400 | I3D | Acc@5 | 89.3 | #179 of 207 | Archive leaderboard | report |
| Action Classification | MiT | I3D | Top 1 Accuracy | 29.51% | #23 of 29 | Archive leaderboard | report |
| Action Classification | MiT | I3D | Top 5 Accuracy | 56.06% | #23 of 29 | Archive leaderboard | report |
| Action Classification | Toyota Smarthome dataset | I3D | CS | 53.4 | #10 of 13 | Archive leaderboard | report |
| Action Classification | Toyota Smarthome dataset | I3D | CV1 | 34.9 | #10 of 13 | Archive leaderboard | report |
| Action Classification | Toyota Smarthome dataset | I3D | CV2 | 45.1 | #10 of 13 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | Two-stream I3D | Average accuracy of 3 splits | 80.9 | #20 of 77 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | Two-Stream I3D (Imagenet+Kinetics pre-training) | Average accuracy of 3 splits | 80.7 | #21 of 77 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | Flow-I3D (Kinetics pre-training) | Average accuracy of 3 splits | 77.3 | #33 of 77 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | Flow-I3D (Imagenet+Kinetics pre-training) | Average accuracy of 3 splits | 77.1 | #34 of 77 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | RGB-I3D (Imagenet+Kinetics pre-training) | Average accuracy of 3 splits | 74.8 | #40 of 77 | Archive leaderboard | report |
| Action Recognition | HMDB-51 | RGB-I3D (Kinetics pre-training) | Average accuracy of 3 splits | 74.3 | #44 of 77 | Archive leaderboard | report |
| Action Recognition | UCF101 | Two-Stream I3D (Imagenet+Kinetics pre-training) | 3-fold Accuracy | 98.0 | #12 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | Two-Stream I3D (Kinetics pre-training) | 3-fold Accuracy | 97.8 | #15 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | Flow-I3D (Imagenet+Kinetics pre-training) | 3-fold Accuracy | 96.7 | #33 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | Flow-I3D (Kinetics pre-training) | 3-fold Accuracy | 96.5 | #36 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | RGB-I3D (Imagenet+Kinetics pre-training) | 3-fold Accuracy | 95.6 | #43 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | RGB-I3D (Kinetics pre-training) | 3-fold Accuracy | 95.1 | #48 of 91 | Archive leaderboard | report |
| Action Recognition | UCF101 | Two-stream I3D | 3-fold Accuracy | 93.4 | #60 of 91 | Archive leaderboard | report |
| Hand Gesture Recognition | EgoGesture | I3D | Accuracy | 92.78 | #4 of 4 | Archive leaderboard | report |
| Hand Gesture Recognition | VIVA Hand Gestures Dataset | I3D | Accuracy | 83.1 | #2 of 3 | Archive leaderboard | report |
| Skeleton Based Action Recognition | J-HMDB | I3D | Accuracy (RGB+pose) | 84.1 | #4 of 13 | Archive leaderboard | report |
| Video Object Tracking | CATER | I3D-50 + LSTM | L1 | 1.2 | #7 of 7 | Archive leaderboard | report |
| Video Object Tracking | CATER | I3D-50 + LSTM | Top 1 Accuracy | 60.2 | #7 of 7 | Archive leaderboard | report |
| Video Object Tracking | CATER | I3D-50 + LSTM | Top 5 Accuracy | 81.8 | #7 of 7 | 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