Papers › MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition...

MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge

15 Mar 2023ICCV 2023 1arXiv:2303.08914archive 2025-07-28

Wei Lin, Leonid Karlinsky, Nina Shvetsova, Horst Possegger, Mateusz Kozinski, Rameswar Panda, Rogerio Feris, Hilde Kuehne, Horst Bischof

Large scale Vision-Language (VL) models have shown tremendous success in aligning representations between visual and text modalities. This enables remarkable progress in zero-shot recognition, image generation & editing, and many other exciting tasks. However, VL models tend to over-represent objects while paying much less attention to verbs, and require additional tuning on video data for best zero-shot action recognition performance. While previous work relied on large-scale, fully-annotated data, in this work we propose an unsupervised approach. We adapt a VL model for zero-shot and few-shot action recognition using a collection of unlabeled videos and an unpaired action dictionary. Based on that, we leverage Large Language Models and VL models to build a text bag for each unlabeled video via matching, text expansion and captioning. We use those bags in a Multiple Instance Learning setup to adapt an image-text backbone to video data. Although finetuned on unlabeled video data, our resulting models demonstrate high transferability to numerous unseen zero-shot downstream tasks, improving the base VL model performance by up to 14\%, and even comparing favorably to fully-supervised baselines in both zero-shot and few-shot video recognition transfer. The code will be released later at \url{https://github.com/wlin-at/MAXI}.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2303.08914")

Code

Syntology Ran 3 of 4 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 4 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wlin-at/maxi officialmentioned in papermentioned on GitHubpytorch 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

4 samples harvested; 3 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
1unverified

Licence: 4 of the 4 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 wlin-at/MAXI. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

load_class_textbag wlin-at/MAXI/trainers/vificlip_caption_aug_mil.py official repository ran · our draft was wrong no licence file found · pointer only · ac0675b539662e24 · report
load_gpt3_verbs wlin-at/MAXI/trainers/vificlip_caption_aug_mil.py official repository ran · our draft was wrong no licence file found · pointer only · 72de8381c8ab4870 · report
load_vid_blip_textbag wlin-at/MAXI/trainers/vificlip_caption_aug_mil.py official repository ran · our draft was wrong no licence file found · pointer only · 20a487dee82777d0 · report
ViFiCLIP_caption_aug_MIL wlin-at/MAXI/trainers/vificlip_caption_aug_mil.py official repository unverified no licence file found · pointer only · 1143df1338a3021b · report

Tasks

Action RecognitionFew Shot Action RecognitionFew-Shot action recognitionImage GenerationMultiple Instance LearningVideo RecognitionZero-Shot Action RecognitionZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Action Recognition Charades MAXI mAP 23.8 #3 of 4 Archive leaderboard report
Zero-Shot Action Recognition HMDB51 MAXI Top-1 Accuracy 52.3 #10 of 29 Archive leaderboard report
Zero-Shot Action Recognition Kinetics MAXI Top-1 Accuracy 71.6 #4 of 20 Archive leaderboard report
Zero-Shot Action Recognition UCF101 MAXI Top-1 Accuracy 78.2 #12 of 35 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

BASE

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