Papers › Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

22 May 2022arXiv:2205.10747archive 2025-07-28

Zhenhailong Wang, Manling Li, Ruochen Xu, Luowei Zhou, Jie Lei, Xudong Lin, Shuohang Wang, ZiYi Yang, Chenguang Zhu, Derek Hoiem, Shih-Fu Chang, Mohit Bansal, Heng Ji

The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Video-language Learner via Image and Language models, which demonstrates strong performance on few-shot video-to-text tasks without the necessity of pretraining or finetuning on any video datasets. We use the image-language models to translate the video content into frame captions, object, attribute, and event phrases, and compose them into a temporal structure template. We then instruct a language model, with a prompt containing a few in-context examples, to generate a target output from the composed content. The flexibility of prompting allows the model to capture any form of text input, such as automatic speech recognition (ASR) transcripts. Our experiments demonstrate the power of language models in understanding videos on a wide variety of video-language tasks, including video captioning, video question answering, video caption retrieval, and video future event prediction. Especially, on video future event prediction, our few-shot model significantly outperforms state-of-the-art supervised models trained on large-scale video datasets. Code and resources are publicly available for research purposes at https://github.com/MikeWangWZHL/VidIL .

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 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 7 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mikewangwzhl/vidil officialmentioned in papermentioned on GitHubpytorchMITSyntology: 7 samples, 7 ran (0 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

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 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 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.

7ran

Licence: 0 of the 7 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 mikewangwzhl/vidil. “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.

mikewangwzhl/vidil official repository 7 samples, 7 ran (0 instrument-failed) · 0 unverified
clean_text in 84 papers eval_video_captioning_results.py ran MIT (permissive) · 1ff44f0d81c9de63 · report fixture: signature text:str/0/str, filter_short_response:bool/0/bool, take_first_sentence:bool/0/bool · returned str · level recorded 2026-09-24
itm_eval in 27 papers eval_retrieval_video.py ran MIT (permissive) · e19e22cd7641eb82 · report fixture: signature scores_v2t:ndarray/2/float, scores_t2v:ndarray/2/float, txt2vmg:ndarray/1/int, vid2txt:ndarray/1/int · returned dict · level recorded 2026-09-24
load_json in 344 papers eval_video_qa_result.py ran MIT (permissive) · 0c5833eaff6e8453 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
load_jsonl in 179 papers eval_video_captioning_results.py ran MIT (permissive) · 8372db08bff4e9da · report fixture: signature jsonl_path:str/0/str · returned list · level recorded 2026-09-24
load_jsonl_gt eval_video_qa_result.py ran MIT (permissive) · 9a76f45dd082992d · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-24
load_jsonl_results_alpro eval_video_qa_result.py ran MIT (permissive) · 4b6a3cc4d51e1b5a · report fixture: signature path:str/0/str, ansid_2_answer:dict/0/? · returned list · level recorded 2026-09-24
process_gpt3_response eval_video_captioning_results.py ran MIT (permissive) · 8bcec8d5e1109d19 · report fixture: signature idx_2_videoid_path:str/0/str, response_jsonl_path:str/0/str, output_path:str/0/str · returned str · level recorded 2026-09-24

Tasks

AttributeAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModellingQuestion AnsweringRetrievalSpeech RecognitionVideo CaptioningVideo Question Answering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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