Papers › EZ-CLIP: Efficient Zeroshot Video Action Recognition

EZ-CLIP: Efficient Zeroshot Video Action Recognition

13 Dec 2023arXiv:2312.08010archive 2025-07-28

Shahzad Ahmad, Sukalpa Chanda, Yogesh S Rawat

Recent advancements in large-scale pre-training of visual-language models on paired image-text data have demonstrated impressive generalization capabilities for zero-shot tasks. Building on this success, efforts have been made to adapt these image-based visual-language models, such as CLIP, for videos extending their zero-shot capabilities to the video domain. While these adaptations have shown promising results, they come at a significant computational cost and struggle with effectively modeling the crucial temporal aspects inherent to the video domain. In this study, we present EZ-CLIP, a simple and efficient adaptation of CLIP that addresses these challenges. EZ-CLIP leverages temporal visual prompting for seamless temporal adaptation, requiring no fundamental alterations to the core CLIP architecture while preserving its remarkable generalization abilities. Moreover, we introduce a novel learning objective that guides the temporal visual prompts to focus on capturing motion, thereby enhancing its learning capabilities from video data. We conducted extensive experiments on five different benchmark datasets, thoroughly evaluating EZ-CLIP for zero-shot learning and base-to-novel video action recognition, and also demonstrating its potential for few-shot generalization.Impressively, with a mere 5.2 million learnable parameters (as opposed to the 71.1 million in the prior best model), EZ-CLIP can be efficiently trained on a single GPU, outperforming existing approaches in several evaluations.

PaperPDFCodeCode 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="2312.08010")

Code

Syntology Ran 9 of 13 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shahzadnit/ez-clip officialmentioned in papermentioned on GitHubpytorchMIT 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

13 samples harvested; 9 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
1ran · fixture could not drive it
4ran
4unverified

Licence: 0 of the 13 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 shahzadnit/ez-clip. “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.

basic_clean shahzadnit/ez-clip/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 98f385d847636a3e · report
drop_path shahzadnit/ez-clip/clip/model.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3ac6b7d76e8e3584 · report
fixed_patch shahzadnit/ez-clip/modules/prompters.py official repository ran MIT (permissive) · fe803eb0c1276891 · report
get_pairs shahzadnit/ez-clip/clip/simple_tokenizer.py official repository ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report
padding shahzadnit/ez-clip/modules/prompters.py official repository ran MIT (permissive) · b32a7826dc4c1939 · report
print_time shahzadnit/ez-clip/train_base_to_novel.py official repository ran fingerprinted MIT (permissive) · 9c9c401fc5d4adf7 · report
random_patch shahzadnit/ez-clip/modules/prompters.py official repository ran MIT (permissive) · 5debe27f7868e61c · report
trunc_normal_ shahzadnit/ez-clip/modules/Visual_Prompt.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5cb5985f521b3573 · report
whitespace_clean shahzadnit/ez-clip/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9542161e9640b858 · report
build_model shahzadnit/ez-clip/clip/model.py official repository unverified MIT (permissive) · 9505aef5443f0743 · report
dump_frames shahzadnit/ez-clip/Dataset_creation_scripts/data_creation_kinetic-400.py official repository unverified MIT (permissive) · 5c8f57e83614642d · report
generate_triplet_samples shahzadnit/ez-clip/train_base_to_novel.py official repository unverified MIT (permissive) · ea4ec5d9601fa229 · report
load shahzadnit/ez-clip/clip/clip.py official repository unverified MIT (permissive) · 4414ea60788c64a8 · report

Tasks

Action RecognitionTemporal Action LocalizationVisual PromptingZero-Shot Action RecognitionZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Action Recognition UCF101 EZ-CLIP Top-1 Accuracy 79.1 #11 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

CLIPFocus

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