Papers › VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

28 Sep 2021EMNLP 2021 11arXiv:2109.14084archive 2025-07-28

Hu Xu, Gargi Ghosh, Po-Yao Huang, Dmytro Okhonko, Armen Aghajanyan, Florian Metze, Luke Zettlemoyer, Christoph Feichtenhofer

We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.

PaperPDFConference PDFCode

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

pytorch/fairseq officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer (arXiv:2105.08206; that paper's own run record: 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), Cascaded Head-colliding Attention (arXiv:2105.14850; that paper's own run record: 9 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified) and Modeling Dual Read/Write Paths for Simultaneous Machine Translation (arXiv:2203.09163; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
facebookresearch/fairseq mentioned on GitHubpytorchMITSyntology: 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.

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 LocalizationAction SegmentationLong Video Retrieval (Background Removed)RetrievalTemporal Action LocalizationTemporal Relation ExtractionVideo RetrievalZero-Shot Video Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation COIN VideoClip Frame accuracy 68.7 #4 of 9 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP Cap. Avg. R@1 74.5 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP Cap. Avg. R@10 97.9 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP Cap. Avg. R@5 94.5 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP DTW R@1 56.0 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP DTW R@10 89.9 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP DTW R@5 96.3 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP OTAM R@1 52.8 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP OTAM R@10 89.2 #3 of 6 Archive leaderboard report
Long Video Retrieval (Background Removed) YouCook2 VideoCLIP OTAM R@5 95.0 #3 of 6 Archive leaderboard report
Temporal Action Localization CrossTask VideoCLIP Recall 47.3 #1 of 7 Archive leaderboard report
Temporal Relation Extraction Vinoground VideoCLIP Group Score 1.2 #22 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground VideoCLIP Text Score 17 #22 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground VideoCLIP Video Score 2.8 #22 of 24 Archive leaderboard report
Video Retrieval MSR-VTT-1kA VideoCLIP text-to-video R@1 30.9 #50 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA VideoCLIP text-to-video R@10 66.8 #50 of 63 Archive leaderboard report
Video Retrieval MSR-VTT-1kA VideoCLIP text-to-video R@5 55.4 #50 of 63 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP text-to-video R@1 32.2 #3 of 16 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP text-to-video R@10 75.0 #3 of 16 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP text-to-video R@5 62.6 #3 of 16 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP (zero-shot) text-to-video R@1 22.7 #8 of 16 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP (zero-shot) text-to-video R@10 63.1 #8 of 16 Archive leaderboard report
Video Retrieval YouCook2 VideoCLIP (zero-shot) text-to-video R@5 50.4 #8 of 16 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo VideoCLIP text-to-video R@1 16.6 #26 of 26 Archive leaderboard report
Zero-Shot Video Retrieval DiDeMo VideoCLIP text-to-video R@5 46.9 #26 of 26 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VideoCLIP text-to-video R@1 10.4 #36 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VideoCLIP text-to-video R@10 30.0 #36 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT VideoCLIP text-to-video R@5 22.2 #36 of 41 Archive leaderboard report
Zero-Shot Video Retrieval YouCook2 VideoCLIP text-to-video R@1 22.7 #3 of 9 Archive leaderboard report
Zero-Shot Video Retrieval YouCook2 VideoCLIP text-to-video R@10 63.1 #3 of 9 Archive leaderboard report
Zero-Shot Video Retrieval YouCook2 VideoCLIP text-to-video R@5 50.4 #3 of 9 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