SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.10451 · ICCV · 2023

Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation

Zhenghua Chen, Jianfei Yang, Yunjiao Zhou, Yuecong Xu, Min Wu, Xiaoli Li

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 2 have no contract verdict; 0 failures of our instrument; 0 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/2303.10451.json · badge: /api/ran/2303.10451.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
xuyu0010/SSA2lign canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
generate_support_file Ran
ran on a synthesized input
xuyu0010/SSA2lign/dataset/generate_support_sets.py
code served (permissive licence) · get_code("930411e693830f49")
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 int, ndim 0, dtype family int; 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
import os
import tempfile
import shutil

# Create a temporary directory structure for the test
temp_dir = tempfile.mkdtemp()
dataset_name = "TestDataset"
domain_name = "TestDomain"
dataset_path = os.path.join(temp_dir, dataset_name)
raw_path = os.path.join(dataset_path, 'raw', 'list_cvt')
os.makedirs(raw_path, exist_ok=True)

# Change to temp directory for the function to work
original_cwd = os.getcwd()
os.chdir(temp_dir)

# Create a mock get_config function
def get_config(domain):
    return {'num_classes': 3}

# Inject get_config into the module namespace
import sys
current_module = sys.modules[__name__]
setattr(current_module, 'get_config', get_config)

# Create a train file with sample data
train_file_name = dataset_name.lower() + '_' + domain_name.lower() + '_train.txt'
train_file_path = os.path.join(raw_path, train_file_name)

# Write sample training data with 3 classes, multiple samples per class
train_data_content = """video_001.mp4 0
video_002.mp4 0
video_003.mp4 1
video_004.mp4 1
video_005.mp4 2
video_006.mp4 2
video_007.mp4 0
video_008.mp4 1
video_009.mp4 2
"""

with open(train_file_path, 'w') as f:
    f.write(train_data_content)

# Set up arguments
ARGS = {
    'dataset': dataset_name,
    'domain': domain_name,
    'seed': 42,
    'support_num': 2
}
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 int, ndim 0, dtype family int — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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
get_config Ran
ran on a synthesized input
xuyu0010/SSA2lign/dataset/config.py
code served (permissive licence) · get_code("8136abe8ff118c05")
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 dict. 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 logging

# The function get_config takes a single parameter 'name' which is a string
# It looks up the string in a dictionary-like pattern and returns a config dict
# We need to provide a valid dataset name that will match one of the conditions

ARGS = {
    'name': 'ORI'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

For video models to be transferred and applied seamlessly across video tasks in varied environments, Video Unsupervised Domain Adaptation (VUDA) has been introduced to improve the robustness and transferability of video models. However, current VUDA methods rely on a vast amount of high-quality unlabeled target data, which may not be available in real-world cases. We thus consider a more realistic Few-Shot Video-based Domain Adaptation (FSVDA) scenario where we adapt video models with only a few target video samples. While a few methods have touched upon Few-Shot Domain Adaptation (FSDA) in images and in FSVDA, they rely primarily on spatial augmentation for target domain expansion with alignment performed statistically at the instance level. However, videos contain more knowledge in terms of rich temporal and semantic information, which should be fully considered while augmenting target domains and performing alignment in FSVDA. We propose a novel SSA 2 lign to address FSVDA at the snippet level, where the target domain is expanded through a simple snippet-level augmentation followed by the attentive alignment of snippets both semantically and statistically, where semantic alignment of snippets is conducted through multiple perspectives. Empirical results demonstrate state-of-the-art performance of SSA 2 lign across multiple cross-domain action recognition benchmarks. Code will be provided at: https://github.com/xuyu0010/SSA2lign.

For agents

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

get_harvested_code_for_paper("2303.10451")
get_code_for_paper("2303.10451")
have("2303.10451")

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

curl https://syntology.ai/api/ran/2303.10451.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.10451.svg)](https://syntology.ai/paper/2303.10451)

Connect an agent — have() is free.