Papers › Cross-Modal Adapter for Text-Video Retrieval

Cross-Modal Adapter for Text-Video Retrieval

17 Nov 2022arXiv:2211.09623archive 2025-07-28

Haojun Jiang, Jianke Zhang, Rui Huang, Chunjiang Ge, Zanlin Ni, Jiwen Lu, Jie zhou, Shiji Song, Gao Huang

Text-video retrieval is an important multi-modal learning task, where the goal is to retrieve the most relevant video for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on this task. However, as pre-trained models are scaling up, fully fine-tuning them on text-video retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient fine-tuning. Inspired by adapter-based methods, we adjust the pre-trained model with a few parameterization layers. However, there are two notable differences. First, our method is designed for the multi-modal domain. Secondly, it allows early cross-modal interactions between CLIP's two encoders. Although surprisingly simple, our approach has three notable benefits: (1) reduces 99.6% of fine-tuned parameters, and alleviates the problem of overfitting, (2) saves approximately 30% of training time, and (3) allows all the pre-trained parameters to be fixed, enabling the pre-trained model to be shared across datasets. Extensive experiments demonstrate that, without bells and whistles, it achieves superior or comparable performance compared to fully fine-tuned methods on MSR-VTT, MSVD, VATEX, ActivityNet, and DiDeMo datasets. The code will be available at https://github.com/LeapLabTHU/Cross-Modal-Adapter.

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 15 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 2 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 15 ran (10 with no instrument failure; 5 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

leaplabthu/cross-modal-adapter officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 15 ran (5 instrument-failed) · 0 unverified 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

15 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 2 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
4ran

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from leaplabthu/cross-modal-adapter. “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.

leaplabthu/cross-modal-adapter official repository 15 samples, 15 ran (5 instrument-failed) · 0 unverified
all_gather in 119 papers comm.py ran · our draft was wrong Apache-2.0 (permissive) · d741eb912b24880a · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-24
cached_path in 47 papers modules/file_utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 349d780dd4a89a37 · report fixture: signature url_or_filename:str/0/str, cache_dir:str/0/str · returned str · level recorded 2026-09-26
check_attr in 12 papers modules/modeling_jointvt_upshare_adapter.py ran · violated contract Apache-2.0 (permissive) · 47c2715feba5fd6b · report fixture: signature target_name:str/0/str, task_config:TaskConfig/0/? · returned bool · level recorded 2026-09-22
compute_metrics in 208 papers metrics.py ran fingerprinted Apache-2.0 (permissive) · f45b80d057798fed · report fixture: signature x:ndarray/2/float · returned dict · level recorded 2026-09-24
filename_to_url in 54 papers modules/file_utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · db0ac56aaf6e35e6 · report fixture: signature filename:str/0/str, cache_dir:str/0/str · returned tuple · level recorded 2026-09-26
get_cosine_schedule_with_warmup in 42 papers modules/optimization_xpool.py ran Apache-2.0 (permissive) · 28936c41e64792bd · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, num_cycles:float/0/float, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_linear_schedule_with_warmup in 39 papers modules/optimization_xpool.py ran · our draft was wrong Apache-2.0 (permissive) · afba2c06a42074fe · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-26
reduce_dict in 73 papers comm.py ran · violated contract Apache-2.0 (permissive) · 2a3280757ce5a198 · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-22
tensor_text_to_video_metrics in 8 papers metrics.py ran Apache-2.0 (permissive) · 66bf2e9b33bd27dd · report fixture: signature sim_tensor:Tensor/3/float, top_k:list/1/int · returned dict · level recorded 2026-09-24
tensor_video_to_text_sim in 8 papers metrics.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · b6f9f3930836fe3f · report fixture: signature sim_tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-26
update_attr in 10 papers modules/modeling_jointvt_upshare_adapter.py ran · our draft was wrong Apache-2.0 (permissive) · d34a2226d2cf142e · report fixture: signature target_name:str/0/str, target_config:TargetConfig/0/?, target_attr_name:str/0/str, source_config:SourceConfig/0/?, source_attr_name:str/0/str, default_value:NoneType/0/? · returned TargetConfig · level recorded 2026-09-22
url_to_filename in 73 papers modules/file_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · af64ec220e8bcdbc · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
warmup_constant in 30 papers modules/optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 59e4e730a9dc5dc6 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-26
warmup_cosine in 30 papers modules/optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 20b3d25ba1b796e5 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-26
warmup_linear in 45 papers modules/optimization.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0960afdb0d64aa7 · report fixture: signature x:float/0/float, warmup:float/0/float · returned float · level recorded 2026-09-22

Tasks

RetrievalVideo Retrievalparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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