SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.09105 · AAAI · 2020

Location-Aware Graph Convolutional Networks for Video Question Answering

Mingkui Tan, Chuang Gan, Peihao Chen, Runhao Zeng, Deng Huang, Qing Du

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 2 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure of our instrument; 0 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/2008.09105.json · badge: /api/ran/2008.09105.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
SunDoge/L-GCN canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
cat_into_shared_memory Ran
ran on a synthesized input
SunDoge/L-GCN/dataset/tgifqa_dataset.py
code served (permissive licence) · get_code("c2169e0a378c6014")
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, 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 torch
from typing import List

torch.manual_seed(0)

# Create a batch of small tensors
# The function expects a list of tensors that will be stacked
batch = [
    torch.randn(4, 3),
    torch.randn(4, 3),
]

ARGS = {
    "batch": batch,
}
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, 3) — shape (2, 4, 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
clean_str Ran
ran; our contract draft was wrong, not the code
SunDoge/L-GCN/utils/dictionary.py
code served (permissive licence) · get_code("9dd016f6325a3959")
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 str. 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 re

def clean_str(string, downcase=True):
    """
    Currently we don't use it.
    Tokenization/string cleaning for strings.
    Taken from https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
    """
    string = re.sub("[^A-Za-z0-9(),!?\\'\\`(_____)]", ' ', string)
    string = re.sub("\\'s", " 's", string)
    string = re.sub("\\'ve", " 've", string)
    string = re.sub("n\\'t", " n't", string)
    string = re.sub("\\'re", " 're", string)
    string = re.sub("\\'d", " 'd", string)
    string = re.sub("\\'ll", " 'll", string)
    string = re.sub(',', ' , ', string)
    string = re.sub('!', ' ! ', string)
    string = re.sub('\\(', ' \\( ', string)
    string = re.sub('\\)', ' \\) ', string)
    string = re.sub('\\?', ' \\? ', string)
    string = re.sub('\\s{2,}', ' ', string)
    return string.strip().lower() if downcase else string.strip()

ARGS = {
    "string": "Hello, world! This is a test. It's great, isn't it?",
    "downcase": True
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
collate_fn Ran
ran on a synthesized input
SunDoge/L-GCN/dataset/tgifqa_dataset.py
code served (permissive licence) · get_code("8f7e86b2fe2ed11d")
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 tuple. 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 torch

torch.manual_seed(0)

# Create a single batch item with all required components
def create_batch_item():
    question = torch.randint(0, 100, (5,))  # sequence of word indices
    question_length = 5
    question_chars = torch.randint(0, 26, (5, 3))  # 5 words, 3 chars max per word
    
    a1 = torch.randint(0, 100, (4,))
    a1_length = 4
    a1_chars = torch.randint(0, 26, (4, 3))
    
    a2 = torch.randint(0, 100, (6,))
    a2_length = 6
    a2_chars = torch.randint(0, 26, (6, 3))
    
    a3 = torch.randint(0, 100, (3,))
    a3_length = 3
    a3_chars = torch.randint(0, 26, (3, 3))
    
    a4 = torch.randint(0, 100, (7,))
    a4_length = 7
    a4_chars = torch.randint(0, 26, (7, 3))
    
    a5 = torch.randint(0, 100, (2,))
    a5_length = 2
    a5_chars = torch.randint(0, 26, (2, 3))
    
    features = torch.randn(2048)  # video features
    c3d_features = torch.randn(4096)  # C3D features
    bbox_features = torch.randn(1024)  # bounding box features
    bbox = torch.randn(8)  # bounding boxes
    answer = 1  # answer index (0-4 for 5 answers)
    
    return (question, question_length, question_chars, 
            a1, a1_length, a1_chars, 
            a2, a2_length, a2_chars, 
            a3, a3_length, a3_chars, 
            a4, a4_length, a4_chars, 
            a5, a5_length, a5_chars, 
            features, c3d_features, bbox_features, bbox, answer)

# Create batch of 2 items
batch = [create_batch_item(), create_batch_item()]

ARGS = {
    "batch": batch
}
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 tuple — a tuple output has no array shape of its own; none is 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
get_timestamp Ran
ran on a synthesized input
SunDoge/L-GCN/arguments.py
code served (permissive licence) · get_code("1187f71dfcb968ef")
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 str. 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 time

def get_timestamp(fmt: str='%Y%m%d_%H%M%S') -> str:
    timestamp = time.strftime(fmt, time.localtime())
    return timestamp

ARGS = {
    'fmt': '%Y%m%d_%H%M%S'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
max_along_time Ran
ran on a synthesized input
SunDoge/L-GCN/model/rnn.py
code served (permissive licence) · get_code("4e8b207ee04445f8")
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)

# outputs: (B, T, D) - batch size 2, time steps 5, dimension 4
outputs = torch.randn(2, 5, 4)

# lengths: (B,) - batch size 2, specifying actual sequence lengths
lengths = torch.tensor([3, 4])

ARGS = {
    "outputs": outputs,
    "lengths": lengths,
}
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
positionalencoding1d Ran
ran, honoured the contract we drafted
SunDoge/L-GCN/model/PosEmbed.py
code served (permissive licence) · get_code("3c3fb01a914c2038")
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
import math

torch.manual_seed(0)

# The function positionalencoding1d takes two parameters:
# - d_model: dimension of the model (must be even)
# - length: length of positions

ARGS = {
    "d_model": 4,
    "length": 2
}
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
positionalencoding2d Ran
ran, honoured the contract we drafted
SunDoge/L-GCN/model/PosEmbed.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from wzlxjtu/PositionalEncoding2D, is pointer only (licence: NONE) · get_code("69664111108e8701")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from wzlxjtu/PositionalEncoding2D, 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.

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, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
positionalencoding2d 9 other papers
1 dated earlier, 8 later
1706.03762 (2017-06)
Attention Is All You Need
2106.12102 (2021-06)
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
2112.06197 (2021-12)
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering
and 6 more not named here
positionalencoding1d 5 other papers
5 later
2106.12102 (2021-06)
LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
2112.06197 (2021-12)
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering
2203.11934 (2022-03)
Learning from All Vehicles
and 2 more not named here
clean_str 1 other paper
1 dated earlier
1904.04357 (2019-04)
Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
max_along_time 1 other paper
1 dated earlier
1809.01696 (2018-09)
TVQA: Localized, Compositional Video Question Answering

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

We addressed the challenging task of video question answering, which requires machines to answer questions about videos in a natural language form. Previous state-of-the-art methods attempt to apply spatio-temporal attention mechanism on video frame features without explicitly modeling the location and relations among object interaction occurred in videos. However, the relations between object interaction and their location information are very critical for both action recognition and question reasoning. In this work, we propose to represent the contents in the video as a locationaware graph by incorporating the location information of an object into the graph construction. Here, each node is associated with an object represented by its appearance and location features. Based on the constructed graph, we propose to use graph convolution to infer both the category and temporal locations of an action. As the graph is built on objects, our method is able to focus on the foreground action contents for better video question answering. Lastly, we leverage an attention mechanism to combine the output of graph convolution and encoded question features for final answer reasoning. Extensive experiments demonstrate the effectiveness of the proposed methods. Specifically, our method significantly outperforms state-of-the-art methods on TGIF-QA, Youtube2Text-QA and MSVD-QA datasets.

For agents

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

get_harvested_code_for_paper("2008.09105")
get_code_for_paper("2008.09105")
have("2008.09105")

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

curl https://syntology.ai/api/ran/2008.09105.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.09105.svg)](https://syntology.ai/paper/2008.09105)

Connect an agent — have() is free.