SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2208.03550 · ECCV · 2022

Frozen CLIP Models are Efficient Video Learners

Hongsheng Li, Gerard De Melo, Xiaogang Wang, Jifeng Dai, Yu Qiao, Renrui Zhang, Peng Gao, Ziyi Lin, Shijie Geng

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 5 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2208.03550.json · badge: /api/ran/2208.03550.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
OpenGVLab/efficient-video-recognition community
Papers with Code archive
5 ran · 5 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input · constructed an object; no result was computed
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("68359211beb5845f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PatchEmbed2D Ran
ran on a synthesized input
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("6dc8dfed11a95191")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TemporalCrossAttention Ran
ran on a synthesized input
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("939b58dc96e7688d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TransformerDecoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("672cd6b662676846")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

TransformerEncoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("827c460499de0c70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

EVLDecoder Not yet run
unverified (harvested, no recorded run)
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("ebbaaa44f01bf0b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

EVLTransformer Not yet run
unverified (harvested, no recorded run)
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("5cfcbd5ab2e4afb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

VisionTransformer2D Not yet run
unverified (harvested, no recorded run)
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("da39da2dd6bd01ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

load_weights_clip Not yet run
unverified (harvested, no recorded run)
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("ee488f9d9228c231")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

model_to_fp16 Not yet run
unverified (harvested, no recorded run)
OpenGVLab/efficient-video-recognition/model.py
pointer only (licence: NONE) · get_code("4a8075639cafecc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenGVLab/efficient-video-recognition when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Video recognition has been dominated by the end-to-end learning paradigm -first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos. This enables the video network to benefit from the pretrained image model. However, this requires substantial computation and memory resources for finetuning on videos and the alternative of directly using pretrained image features without finetuning the image backbone leads to subpar results. Fortunately, recent advances in Contrastive Vision-Language Pre-training (CLIP) pave the way for a new route for visual recognition tasks. Pretrained on large open-vocabulary image-text pair data, these models learn powerful visual representations with rich semantics. In this paper, we present Efficient Video Learning (EVL) -an efficient framework for directly training high-quality video recognition models with frozen CLIP features. Specifically, we employ a lightweight Transformer decoder and learn a query token to dynamically collect frame-level spatial features from the CLIP image encoder. Furthermore, we adopt a local temporal module in each decoder layer to discover temporal clues from adjacent frames and their attention maps. We show that despite being efficient to train with a frozen backbone, our models learn high quality video representations on a variety of video recognition datasets. Code is available at https://github.com/OpenGVLab/efficient-video-recognition.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2208.03550")
get_code_for_paper("2208.03550")
have("2208.03550")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2208.03550.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2208.03550.svg)](https://syntology.ai/paper/2208.03550)

Connect an agent — have() is free.