SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.10132 · 2020

VLG-Net: Video-Language Graph Matching Network for Video Grounding

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure 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/2011.10132.json · badge: /api/ran/2011.10132.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
Soldelli/VLG-Net reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
load_pretrained_graph_weights Ran
ran; our contract draft was wrong, not the code
Soldelli/VLG-Net/train_net.py
code served (permissive licence) · get_code("7a734d85428d248e")
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 MinimalModel. 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
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal config object with the required nested attributes
class Config:
    def __init__(self):
        self.MODEL = ModelConfig()

class ModelConfig:
    def __init__(self):
        self.VLG = VLGConfig()

class VLGConfig:
    def __init__(self):
        self.FEATPOOL = FeatpoolConfig()

class FeatpoolConfig:
    def __init__(self):
        self.HIDDEN_SIZE = 256
        self.NUM_AGGREGATOR_LAYERS = 2

# Create a minimal logger that has an info method
class MinimalLogger:
    def info(self, msg):
        pass

# Create a minimal model with context_aggregator layers
class ContextAggregatorLayer(nn.Module):
    def __init__(self):
        super().__init__()
        self.tconvs = nn.Sequential(
            nn.Conv1d(4, 8, 3),
            nn.ReLU(),
            nn.Conv1d(8, 8, 3),
            nn.ReLU(),
            nn.Conv1d(8, 4, 3)
        )
        self.sconvs = nn.Sequential(
            nn.Conv1d(4, 8, 3),
            nn.ReLU(),
            nn.Conv1d(8, 8, 3),
            nn.ReLU(),
            nn.Conv1d(8, 4, 3)
        )

class MinimalModel(nn.Module):
    def __init__(self, num_layers):
        super().__init__()
        self.context_aggregator = nn.ModuleList([
            ContextAggregatorLayer() for _ in range(num_layers)
        ])
    
    def load_state_dict(self, state_dict, strict=False):
        # Minimal implementation that accepts the state dict
        pass

# Create a pretrained dictionary that would be loaded from the checkpoint
def create_pretrained_dict():
    pretrained = {
        'state_dict': {
            'module.x_1d_b.2.tconvs.0.weight': torch.randn(8, 4, 3),
            'module.x_1d_b.2.tconvs.0.bias': torch.randn(8),
            'module.x_1d_b.2.tconvs.2.weight': torch.randn(8, 8, 3),
            'module.x_1d_b.2.tconvs.2.bias': torch.randn(8),
            'module.x_1d_b.2.tconvs.4.weight': torch.randn(4, 8, 3),
            'module.x_1d_b.2.tconvs.4.bias': torch.randn(4),
            'module.x_1d_b.2.fconvs.0.weight': torch.randn(8, 4, 3),
            'module.x_1d_b.2.fconvs.0.bias': torch.randn(8),
            'module.x_1d_b.2.fconvs.2.weight': torch.randn(8, 8, 3),
            'module.x_1d_b.2.fconvs.2.bias': torch.randn(8),
            'module.x_1d_b.2.fconvs.4.weight': torch.randn(4, 8, 3),
            'module.x_1d_b.2.fconvs.4.bias': torch.randn(4),
        }
    }
    return pretrained

# Mock torch.load to return our pretrained dict
original_load = torch.load
def mock_load(path):
    return create_pretrained_dict()

torch.load = mock_load

cfg = Config()
model = MinimalModel(num_layers=2)
logger = MinimalLogger()

ARGS = {
    'model': model,
    'cfg': cfg,
    'logger': logger
}
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 MinimalModel — a MinimalModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalModel 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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 0 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
load_pretrained_graph_weights 1 other paper
1 later
2112.00431 (2021-12)
MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions

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

Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands understanding videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into an algorithmic graph matching problem. Fueled by recent advances in Graph Neural Networks, we propose to leverage Graph Convolutional Networks to model video and textual information as well as their semantic alignment. To enable the mutual exchange of information across the modalities, we design a novel Video-Language Graph Matching Network (VLG-Net) to match video and query graphs. Core ingredients include representation graphs built atop video snippets and query tokens separately and used to model intra-modality relationships. A Graph Matching layer is adopted for cross-modal context modeling and multi-modal fusion. Finally, moment candidates are created using masked moment attention pooling by fusing the moment's enriched snippet features. We demonstrate superior performance over state-of-the-art grounding methods on three widely used datasets for temporal localization of moments in videos with language queries: ActivityNet-Captions, TACoS, and DiDeMo.

For agents

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

get_harvested_code_for_paper("2011.10132")
get_code_for_paper("2011.10132")
have("2011.10132")

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

curl https://syntology.ai/api/ran/2011.10132.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.10132.svg)](https://syntology.ai/paper/2011.10132)

Connect an agent — have() is free.