SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.03077 · CVPR · 2024

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding

Didier Stricker, Shaoxiang Wang, Chun-Peng Chang, Alain Pagani

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (10 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 0 failures of our instrument; 5 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/2403.03077.json · badge: /api/ran/2403.03077.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
dfki-av/mikasa-3dvg marked official in Papers with Code
Papers with Code archive
11 ran · 5 no recorded run
FunctionStatusWhere it lives
BatchNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("c9ea4b32ab8ee01d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

Conv2d Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("43954295982678e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

CrossFFN Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("a2c9643fb81b1320")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

FeedForwardLayer Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("7eb05f38c1da0278")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

FusionNet Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("fbfaf9b85641a7d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

GroupAll Ran
ran on a synthesized input
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("d0c66f6eec198b93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

MultiHeadSpatialNet Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("c6818d25fb38e40e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

QueryAndGroup Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("79ba2e730dfd23fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

SharedMLP Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("ce88d757651269ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

_BNBase Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("f3c2a0236652d30c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

_ConvBase Ran
ran on a synthesized input · constructed an object; no result was computed
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("29953e9c8508d4e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

MiKASA_transformer Not yet run
unverified (harvested, no recorded run)
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("234728b3b9078cf1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

PointNetPP Not yet run
unverified (harvested, no recorded run)
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("7225d8c84c7f69c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

PointnetSAModuleMSG Not yet run
unverified (harvested, no recorded run)
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("644b83bc52ec1cc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

_PointnetSAModuleBase Not yet run
unverified (harvested, no recorded run)
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("a7de4c208ca1025c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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.

break_up_pc Not yet run
unverified (harvested, no recorded run)
dfki-av/mikasa-3dvg/models/MiKASA_transformer.py
pointer only (licence: NONE) · get_code("775337099d9f9b3c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dfki-av/mikasa-3dvg 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 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 7 later) and 5 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
QueryAndGroup
brick of this paper's assembly: helper
9 other papers
7 dated earlier, 2 later · 7 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 6 more not named here
BatchNorm2d
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 7 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 5 more not named here
Conv2d
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 6 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 5 more not named here
SharedMLP
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 5 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 5 more not named here
_BNBase
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 7 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 5 more not named here
_ConvBase
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 2 later · 6 only as an assembly brick
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2103.07894 (2021-03)
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
2104.00678 (2021-04)
Group-Free 3D Object Detection via Transformers
and 5 more not named here
_PointnetSAModuleBase
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2009.12606 (2020-09)
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
2406.11142 (2024-06)
Graspness Discovery in Clutters for Fast and Accurate Grasp Detection
break_up_pc
brick of this paper's assembly: helper
2 other papers
2 dated earlier
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
2310.16035 (2023-10)
What's Left? Concept Grounding with Logic-Enhanced Foundation Models
GroupAll
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointNetPP
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
PointnetSAModuleMSG
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1706.02413 (2017-06)
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

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

3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.

For agents

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

get_harvested_code_for_paper("2403.03077")
get_code_for_paper("2403.03077")
have("2403.03077")

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

curl https://syntology.ai/api/ran/2403.03077.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.03077.svg)](https://syntology.ai/paper/2403.03077)

Connect an agent — have() is free.