Papers › InternVideo: General Video Foundation Models via Generative and Discriminative Learning

InternVideo: General Video Foundation Models via Generative and Discriminative Learning

6 Dec 2022arXiv:2212.03191archive 2025-07-28

Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang, LiMin Wang, Yu Qiao

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for dynamic and complex video-level understanding tasks. To fill the gap, we present general video foundation models, InternVideo, by taking advantage of both generative and discriminative self-supervised video learning. Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications. Without bells and whistles, InternVideo achieves state-of-the-art performance on 39 video datasets from extensive tasks including video action recognition/detection, video-language alignment, and open-world video applications. Especially, our methods can obtain 91.1% and 77.2% top-1 accuracy on the challenging Kinetics-400 and Something-Something V2 benchmarks, respectively. All of these results effectively show the generality of our InternVideo for video understanding. The code will be released at https://github.com/OpenGVLab/InternVideo .

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 3 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

opengvlab/internvideo officialmentioned in papermentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
yingsen1/unimd mentioned on GitHubpytorchSyntology: not harvested 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

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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
1ran; the contract check could not run

Licence: 0 of the 3 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 opengvlab/internvideo. “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.

opengvlab/internvideo official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
compute_acc in 61 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
Data/InternVid/utils/basic_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · aa81d03f07735ab8 · report fixture: signature logits:Tensor/2/float, label:Tensor/1/int, reduction:str/0/str · returned float · level recorded 2026-09-22
compute_n_params in 30 papers Data/InternVid/utils/basic_utils.py ran · our draft was wrong Apache-2.0 (permissive) · ad12a494674d23fb · report fixture: signature model:callable/0/?, return_str:bool/0/bool · returned str · level recorded 2026-09-22
load_json in 344 papers Data/InternVid/utils/basic_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 2d946250dd2f5a4f · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22

Tasks

Action ClassificationAction RecognitionContrastive LearningOpen Set Action RecognitionSpatio-Temporal Action LocalizationTemporal Action LocalizationVideo Question AnsweringVideo RetrievalVideo UnderstandingVisual Question Answering (VQA)Zero-Shot Video Question AnswerZero-Shot Video Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification Kinetics-400 InternVideo Acc@1 91.1 #5 of 207 Archive leaderboard report
Action Classification Kinetics-600 InternVideo-T Top-1 Accuracy 91.3 #5 of 65 Archive leaderboard report
Action Classification Kinetics-700 InternVideo-T Top-1 Accuracy 84.0 #3 of 36 Archive leaderboard report
Action Recognition AVA v2.2 InternVideo mAP 41.01 #6 of 38 Archive leaderboard report
Action Recognition Something-Something V1 InternVideo Top 1 Accuracy 70.0 #1 of 74 Archive leaderboard report
Action Recognition Something-Something V2 InternVideo Top-1 Accuracy 77.2 #3 of 123 Archive leaderboard report
Open Set Action Recognition UCF-HMDB InternVideo AUROC 85.48 #1 of 1 Archive leaderboard report
Open Set Action Recognition UCF101-MiTv2 InternVideo AUROC 91.85 #1 of 1 Archive leaderboard report
Spatio-Temporal Action Localization AVA-Kinetics InternVideo val mAP 41.01 #3 of 7 Archive leaderboard report
Temporal Action Localization ActivityNet-1.3 InternVideo mAP 39.00 #9 of 33 Archive leaderboard report
Temporal Action Localization FineAction InternVideo mAP 17.57 #6 of 9 Archive leaderboard report
Temporal Action Localization HACS InternVideo Average-mAP 41.55 #7 of 12 Archive leaderboard report
Temporal Action Localization THUMOS’14 ActionFormer (InternVideo features) Avg mAP (0.3:0.7) 71.58 #5 of 42 Archive leaderboard report
Video Question Answering STAR Benchmark InternVideo Average Accuracy 58.7 #4 of 17 Archive leaderboard report
Video Retrieval ActivityNet InternVideo text-to-video R@1 62.2 #8 of 31 Archive leaderboard report
Video Retrieval ActivityNet InternVideo video-to-text R@1 62.8 #8 of 31 Archive leaderboard report
Video Retrieval DiDeMo InternVideo text-to-video R@1 57.9 #10 of 40 Archive leaderboard report
Video Retrieval DiDeMo InternVideo video-to-text R@1 59.1 #10 of 40 Archive leaderboard report
Video Retrieval LSMDC InternVideo text-to-video R@1 34.0 #8 of 38 Archive leaderboard report
Video Retrieval LSMDC InternVideo video-to-text R@1 34.9 #8 of 38 Archive leaderboard report
Video Retrieval MSR-VTT InternVideo text-to-video R@1 55.2 #8 of 40 Archive leaderboard report
Video Retrieval MSR-VTT InternVideo video-to-text R@1 57.9 #8 of 40 Archive leaderboard report
Video Retrieval MSVD InternVideo text-to-video R@1 58.4 #3 of 24 Archive leaderboard report
Video Retrieval MSVD InternVideo video-to-text R@1 76.3 #3 of 24 Archive leaderboard report
Video Retrieval VATEX InternVideo text-to-video R@1 71.1 #6 of 13 Archive leaderboard report
Video Retrieval VATEX InternVideo video-to-text R@1 87.2 #6 of 13 Archive leaderboard report
Visual Question Answering (VQA) MSRVTT-QA InternVideo Accuracy 0.471 #6 of 34 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA InternVideo Accuracy 0.555 #12 of 36 Archive leaderboard report
Visual Question Answering (VQA) TGIF-QA InternVideo Accuracy 0.722 #2 of 2 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) InternVideo Accuracy 32.1 #25 of 29 Archive leaderboard report
Zero-Shot Video Question Answer STAR Benchmark InternVideo Accuracy 41.6 #4 of 4 Archive leaderboard report
Zero-Shot Video Question Answer TVQA InternVideo (no speech) Accuracy 35.9 #8 of 9 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet InternVideo text-to-video R@1 30.7 #11 of 12 Archive leaderboard report
Zero-Shot Video Retrieval ActivityNet InternVideo video-to-text R@1 31.4 #11 of 12 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo text-to-video R@1 31.5 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo text-to-video R@10 68.2 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo text-to-video R@5 57.6 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo video-to-text R@1 33.5 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo video-to-text R@10 71.1 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo InternVideo video-to-text R@5 60.3 #16 of 26 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo text-to-video R@1 17.6 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo text-to-video R@10 40.2 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo text-to-video R@5 32.4 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo video-to-text R@1 13.2 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo video-to-text R@10 34.9 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval LSMDC InternVideo video-to-text R@5 27.8 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT InternVideo text-to-video R@1 40.7 #14 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT InternVideo video-to-text R@1 39.6 #14 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSVD InternVideo text-to-video R@1 43.4 #11 of 14 Archive leaderboard report
Zero-Shot Video Retrieval MSVD InternVideo video-to-text R@1 67.6 #11 of 14 Archive leaderboard report
Zero-Shot Video Retrieval VATEX InternVideo text-to-video R@1 49.5 #5 of 5 Archive leaderboard report
Zero-Shot Video Retrieval VATEX InternVideo video-to-text R@1 69.5 #5 of 5 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.

Methods

Contrastive LearningInternVideo

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