SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.00436 · 2020

Exploring Long Tail Visual Relationship Recognition with Large Vocabulary

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2004.00436.json · badge: /api/ran/2004.00436.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
Vision-CAIR/LTVRR canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
Elhoseiny-VisionCAIR-Lab/LTVRR community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
argsort_desc Ran
ran, honoured the contract we drafted
Elhoseiny-VisionCAIR-Lab/LTVRR/lib/datasets/task_evaluation_rel.py
code served (permissive licence) · get_code("7d4002289969a288")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (12, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small numpy array with distinct dimensions for testing
# Using shape (3, 4) to have distinct dimensions
scores = np.array([
    [9.2, 3.1, 7.5, 1.2],
    [4.8, 6.3, 2.1, 8.9],
    [5.4, 1.7, 9.1, 3.6]
], dtype=np.float32)

ARGS = {
    "scores": scores
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (12, 2) — shape (12, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_one_hot Ran
ran; our contract draft was wrong, not the code
Vision-CAIR/LTVRR/lib/modeling/reldn_heads.py
code served (permissive licence) · get_code("83ac5f312d7bb313")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small label tensor with batch size 2
# Labels should be in range [0, classes-1]
y = torch.tensor([0, 2], dtype=torch.long)

# Number of classes
classes = 3

# Device ID (CPU only - use 0 as a valid device_id, though the function will fail on CUDA)
device_id = 0

ARGS = {
    "y": y,
    "classes": classes,
    "device_id": device_id,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
intersect_2d Ran
ran, violated the contract we drafted
Elhoseiny-VisionCAIR-Lab/LTVRR/lib/datasets/task_evaluation_rel.py
code served (permissive licence) · get_code("6727d2d8f1d79998")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct two 2D numpy arrays with matching number of columns
x1 = np.array([
    [1, 2, 3, 4],
    [5, 6, 7, 8],
], dtype=np.int32)

x2 = np.array([
    [1, 2, 3, 4],
    [9, 10, 11, 12],
    [5, 6, 7, 8],
], dtype=np.int32)

ARGS = {
    'x1': x1,
    'x2': x2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
manual_CE Ran
ran, honoured the contract we drafted
Vision-CAIR/LTVRR/lib/modeling/reldn_heads.py
code served (permissive licence) · get_code("23c77da2f0afb733")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# predictions: logits tensor, shape (batch_size, num_classes)
# labels: one-hot encoded labels, shape (batch_size, num_classes)
predictions = torch.randn(2, 4)
labels = torch.tensor([
    [1.0, 0.0, 0.0, 0.0],
    [0.0, 1.0, 0.0, 0.0]
])

ARGS = {
    "predictions": predictions,
    "labels": labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
voc_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Elhoseiny-VisionCAIR-Lab/LTVRR/lib/datasets/voc_eval_rel.py
code served (permissive licence) · get_code("f7051976b9be472b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# voc_ap expects:
# - rec: numpy array of recall values (floats between 0 and 1)
# - prec: numpy array of precision values (floats between 0 and 1)
# Both should be 1D arrays and should have the same length

# Create small recall and precision arrays
rec = np.array([0.1, 0.3, 0.5, 0.7])
prec = np.array([0.9, 0.8, 0.6, 0.4])

ARGS = {
    "rec": rec,
    "prec": prec
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 1 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
argsort_desc 5 other papers
1 dated earlier, 4 later
1903.02728 (2019-03)
Graphical Contrastive Losses for Scene Graph Parsing
2403.17709 (2024-03)
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
2404.02072 (2024-04)
EGTR: Extracting Graph from Transformer for Scene Graph Generation
and 2 more not named here
intersect_2d 5 other papers
5 later
2103.16083 (2021-03)
Fully Convolutional Scene Graph Generation
2403.17709 (2024-03)
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
2404.02072 (2024-04)
EGTR: Extracting Graph from Transformer for Scene Graph Generation
and 2 more not named here
voc_ap 5 other papers
2 dated earlier, 3 later
1505.04474 (2015-05)
Visual Semantic Role Labeling
2003.14023 (2020-03)
Learning Human-Object Interaction Detection using Interaction Points
2007.12107 (2020-07)
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
and 2 more not named here
manual_CE 1 other paper
1 later
2007.12256 (2020-07)
Towards Recognizing Unseen Categories in Unseen Domains

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship Recognition (LTVRR). LTVRR aims at improving the learning of structured visual relationships that come from the long-tail (e.g., "rabbit grazing on grass"). In this setup, the subject, relation, and object classes each follow a long-tail distribution. To begin our study and make a future benchmark for the community, we introduce two LTVRR-related benchmarks, dubbed VG8K-LT and GQA-LT, built upon the widely used Visual Genome and GQA datasets. We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup. Lastly, we propose a visiolinguistic hubless (VilHub) loss and a Mixup augmentation technique adapted to LTVRR setup, dubbed as RelMix. Both VilHub and RelMix can be easily integrated on top of existing models and despite being simple, our results show that they can remarkably improve the performance, especially on tail classes. Benchmarks, code, and models have been made available at: https://github.com/Vision-CAIR/LTVRR.

For agents

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

get_harvested_code_for_paper("2004.00436")
get_code_for_paper("2004.00436")
have("2004.00436")

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

curl https://syntology.ai/api/ran/2004.00436.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.00436.svg)](https://syntology.ai/paper/2004.00436)

Connect an agent — have() is free.