SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_28398 · AAAI · 2024

Heterogeneous Test-Time Training for Multi-Modal Person Re-identification

Ran He, Zi Wang, Huaibo Huang, Aihua Zheng

Open in the Atlas

Code that ran

5 of 7 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/aaai_28398.json · badge: /api/ran/aaai_28398.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
ziwang1121/HTT canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
cosine_dist Ran
ran; our contract draft was wrong, not the code
ziwang1121/HTT/loss/triplet_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from stone96123/MDReID, is pointer only (licence: NONE) · get_code("71b4e1d375d8fd78")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from stone96123/MDReID, and GitHub detected no licence in that repository 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.

euclidean_dist Ran
ran; our contract draft was wrong, not the code
ziwang1121/HTT/loss/triplet_loss.py
pointer only (licence: MIT); the stored copy get_code serves, from stone96123/MDReID, is pointer only (licence: NONE) · get_code("5315f75bf5367f0a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from stone96123/MDReID, and GitHub detected no licence in that repository 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.

normalize Ran
ran; our contract draft was wrong, not the code
ziwang1121/HTT/loss/triplet_loss.py
code served (permissive licence) · get_code("e3b2a83f52101f2d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create a small tensor with batch size 2 and feature dimension 4
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "axis": -1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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, shape (2, 4) — shape (2, 4) 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
read_image Ran
ran, honoured the contract we drafted
ziwang1121/HTT/datasets/bases.py
code served (permissive licence) · get_code("5f1101145f896208")
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 Image. The image it ran in was not recorded. If your copy returns the same type 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 tempfile
import os
from PIL import Image

# Create a temporary directory and a valid test image
temp_dir = tempfile.mkdtemp()
img_path = os.path.join(temp_dir, "test_image.jpg")

# Create a small valid RGB image and save it
test_img = Image.new('RGB', (4, 3), color=(255, 0, 0))
test_img.save(img_path)

ARGS = {
    'img_path': img_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
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
shuffle_unit Ran
ran on a synthesized input
ziwang1121/HTT/model/make_model.py
code served (permissive licence) · get_code("fa0d6dd791ce2927")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 4) 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)

# Construct a small features tensor
# Shape: (batch_size, sequence_length, feature_dim)
# Using batch=2, sequence_length=5, feature_dim=4
features = torch.randn(2, 5, 4)

# shift parameter - used for cyclic shifting
shift = 2

# group parameter - used to reshape and transpose
group = 2

# begin parameter - starting index (default=1)
begin = 1

ARGS = {
    "features": features,
    "shift": shift,
    "group": group,
    "begin": begin
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 4) 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
make_loss Not yet run
unverified (harvested, no recorded run)
ziwang1121/HTT/loss/make_loss.py
code served (permissive licence) · get_code("d82f0ad0e206efec")
How it ran

no invocation recorded.

make_loss_ttt Not yet run
unverified (harvested, no recorded run)
ziwang1121/HTT/loss/make_loss.py
code served (permissive licence) · get_code("b47cda5b79428a91")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
normalize 29 other papers
21 dated earlier, 3 later, 5 same year, order not determinable
1609.01775 (2016-09)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
1811.07130 (2018-11)
Batch DropBlock Network for Person Re-identification and Beyond
and 26 more not named here
cosine_dist 15 other papers
9 dated earlier, 3 later, 3 same year, order not determinable
1609.01775 (2016-09)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
2105.09701 (2021-05)
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
and 12 more not named here
euclidean_dist 15 other papers
9 dated earlier, 3 later, 3 same year, order not determinable
1609.01775 (2016-09)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
1804.01438 (2018-04)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
2105.09701 (2021-05)
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
and 12 more not named here
read_image 10 other papers
10 dated earlier
1903.07071 (2019-03)
Bag of Tricks and A Strong Baseline for Deep Person Re-identification
1904.07223 (2019-04)
Joint Discriminative and Generative Learning for Person Re-identification
1905.13143 (2019-05)
Semantics-Aligned Representation Learning for Person Re-identification
and 7 more not named here
shuffle_unit 3 other papers
3 dated earlier
1609.01775 (2016-09)
Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
2111.12084 (2021-11)
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
2302.14335 (2023-02)
DC-Former: Diverse and Compact Transformer for Person Re-identification

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

Multi-modal person re-identification (ReID) seeks to mitigate challenging lighting conditions by incorporating diverse modalities. Most existing multi-modal ReID methods concentrate on leveraging complementary multi-modal information via fusion or interaction. However, the relationships among heterogeneous modalities and the domain traits of unlabeled test data are rarely explored. In this paper, we propose a Heterogeneous Test-time Training (HTT) framework for multi-modal person ReID. We first propose a Cross-identity Inter-modal Margin (CIM) loss to amplify the differentiation among distinct identity samples. Moreover, we design a Multi-modal Test-time Training (MTT) strategy to enhance the generalization of the model by leveraging the relationships in the heterogeneous modalities and the information existing in the test data. Specifically, in the training stage, we utilize the CIM loss to further enlarge the distance between anchor and negative by forcing the inter-modal distance to maintain the margin, resulting in an enhancement of the discriminative capacity of the ultimate descriptor. Subsequently, since the test data contains characteristics of the target domain, we adapt the MTT strategy to optimize the network before the inference by using self-supervised tasks designed based on relationships among modalities. Experimental results on benchmark multi-modal ReID datasets RGBNT201, Market1501-MM, RGBN300, and RGBNT100 validate the effectiveness of the proposed method. The codes can be found at https://github.com/ziwang1121/HTT.

For agents

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

get_harvested_code_for_paper("aaai_28398")
get_code_for_paper("aaai_28398")
have("aaai_28398")

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

curl https://syntology.ai/api/ran/aaai_28398.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_28398.svg)](https://syntology.ai/paper/aaai_28398)

Connect an agent — have() is free.