SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.19899 · ECCV · 2024

OpenKD: Opening Prompt Diversity for Zeroand Few-shot Keypoint Detection

Piotr Koniusz, Zheyuan Liu, Changsheng Lu

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 13 failures of our instrument; 1 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/2409.19899.json · badge: /api/ran/2409.19899.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
AlanLuSun/OpenKD canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
average_representations Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/network/models_gridms2.py
pointer only (licence: NONE) · get_code("5efc70da8ecd43b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

compute_openkd_heatmap_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AlanLuSun/OpenKD/core/misc.py
pointer only (licence: NONE) · get_code("c3f0e5e4591095c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

does_det_success Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AlanLuSun/OpenKD/vis.py
pointer only (licence: NONE) · get_code("a4318543e6349061")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

draw_line Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/vis.py
pointer only (licence: NONE) · get_code("bf44a6653f00c99e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

even_sampling Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/network/openkd_model.py
pointer only (licence: NONE) · get_code("aede916dbfc2618a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

extract_texts Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AlanLuSun/OpenKD/vis.py
pointer only (licence: NONE) · get_code("0d9f8c3391250a0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

get_align_kps_and_mask Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/eval_openkd.py
pointer only (licence: NONE) · get_code("cba0ea99fbeca472")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

get_loss_function Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/core/loss_lw.py
pointer only (licence: NONE) · get_code("5bbf1fcd58116e75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

get_optimizer Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/eval_openkd.py
pointer only (licence: NONE) · get_code("fefd2cc2cdad885f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

heatmap_normalize_layer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AlanLuSun/OpenKD/network/lw_model.py
pointer only (licence: NONE) · get_code("abb30f0c095fc86e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

progressive_sampling Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/network/openkd_model.py
pointer only (licence: NONE) · get_code("938f923090279c87")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

recover_kps Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/eval_diverse_prompts.py
pointer only (licence: NONE) · get_code("ce17a5df5b544fcf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

split_main_aux_heatmaps Ran
ran; our contract draft was wrong, not the code
AlanLuSun/OpenKD/core/misc.py
pointer only (licence: NONE) · get_code("17cc8e9898559474")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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.

get_lw_base_model Not yet run
unverified (harvested, no recorded run)
AlanLuSun/OpenKD/network/lw_model.py
pointer only (licence: NONE) · get_code("09dab04abdb1a64c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AlanLuSun/OpenKD 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

FunctionAlso present inEarliest-datedOthers named
average_representations 1 other paper
1 dated earlier
2112.06183 (2021-12)
Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species

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

Exploiting foundation models (e.g ., CLIP) to build a versatile keypoint detector has gained increasing attention. Most existing models accept either the text prompt (e.g ., the nose of a cat), or the visual prompt (e.g ., support image with keypoint annotations), to detect the corresponding keypoints in query image, thereby, exhibiting either zero-shot or few-shot detection ability. However, the research on multimodal prompting is still underexplored, and the prompt diversity in semantics and language is far from opened. For example, how to handle unseen text prompts for novel keypoint detection and the diverse text prompts like Can you detect the nose and ears of a cat? In this work, we open the prompt diversity in three aspects: modality, semantics (seen vs . unseen), and language, to enable a more general zero-and few-shot keypoint detection (Z-FSKD). We propose a novel OpenKD model which leverages a multimodal prototype set to support both visual and textual prompting. Further, to infer the keypoint location of unseen texts, we add the auxiliary keypoints and texts interpolated in visual and textual domains into training, which improves the spatial reasoning of our model and signicantly enhances zero-shot novel keypoint detection. We also nd large language model (LLM) is a good parser, which achieves over 96% accuracy when parsing keypoints from texts. With LLM, OpenKD can handle diverse text prompts. Experimental results show that our method achieves state-of-the-art performance on Z-FSKD and initiates new ways of dealing with unseen text and diverse texts. The source code and data are available at https://github.com/AlanLuSun/OpenKD. Keypoint detection is a fundamental research problem in computer vision and has numerous applications such as pose estimation for humans [6,8,12,33,37,52] and animals [2,5,23,34], action recognition [30,47], and ne-grained image classication [39,55]. Over the past decade, signicant advancements have been made in deep keypoint detection. However, most existing methods are tailored to close-set detection and struggle to predict novel body parts and species with limited data. Thus, it necessitates such a zero-or few-shot keypoint detection: ⋆ Corresponding author.

For agents

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

get_harvested_code_for_paper("2409.19899")
get_code_for_paper("2409.19899")
have("2409.19899")

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

curl https://syntology.ai/api/ran/2409.19899.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.19899.svg)](https://syntology.ai/paper/2409.19899)

Connect an agent — have() is free.