SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16434 · CVPR · 2022

TubeDETR: Spatio-Temporal Video Grounding with Transformers

Cordelia Schmid, Ivan Laptev, Antoine Miech, Antoine Yang, Josef Sivic, Ciirc Ctu Prague

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures 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/2203.16434.json · badge: /api/ran/2203.16434.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
antoyang/TubeDETR marked official in Papers with Code
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
antoyang/TubeDETR/models/tubedetr.py
code served (permissive licence) · get_code("8a09b495672367c2")
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 an instance of its own class, MLP: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'input_dim': 4,
    'hidden_dim': 8,
    'output_dim': 3,
    'num_layers': 2,
    'dropout': 0.1
}
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 MLP — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MLP 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
NestedTensor Ran
ran on a synthesized input · constructed an object; no result was computed
antoyang/TubeDETR/models/tubedetr.py
code served (permissive licence) · get_code("db74b3e6e32586fb")
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 an instance of its own class, NestedTensor: the run constructed the object and did not call it, so no result was computed. 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)

# For the __init__ method, we need:
# - tensors: a torch.Tensor
# - mask: a torch.Tensor or None

# Create a simple tensor (batch of 2, channels 3, height 4, width 5)
tensors = torch.randn(2, 3, 4, 5)

# Create a corresponding mask (batch of 2, height 4, width 5)
mask = torch.ones(2, 4, 5, dtype=torch.bool)

ARGS = {
    'tensors': tensors,
    'mask': mask
}
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 NestedTensor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a NestedTensor 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
TubeDETR Ran
ran on a synthesized input · constructed an object; no result was computed
antoyang/TubeDETR/models/tubedetr.py
code served (permissive licence) · get_code("a0312f1fa47cb07e")
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 an instance of its own class, TubeDETR: the run constructed the object and did not call it, so no result was computed. 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
import math

torch.manual_seed(0)

# Build a minimal backbone
class MinimalBackbone(nn.Module):
    def __init__(self, num_channels=3):
        super().__init__()
        self.num_channels = num_channels
        self.conv = nn.Conv2d(num_channels, num_channels, kernel_size=3, padding=1)
    
    def forward(self, x):
        return self.conv(x)

# Build a minimal transformer
class MinimalTransformer(nn.Module):
    def __init__(self, d_model=64):
        super().__init__()
        self.d_model = d_model
        self.encoder_layer = nn.TransformerEncoderLayer(
            d_model=d_model,
            nhead=4,
            dim_feedforward=128,
            batch_first=True
        )
        self.encoder = nn.TransformerEncoder(self.encoder_layer, num_layers=2)
        self.decoder_layer = nn.TransformerDecoderLayer(
            d_model=d_model,
            nhead=4,
            dim_feedforward=128,
            batch_first=True
        )
        self.decoder = nn.TransformerDecoder(self.decoder_layer, num_layers=2)
    
    def forward(self, src, query_embed, pos=None):
        # Simple forward pass for transformer
        memory = self.encoder(src)
        hs = self.decoder(query_embed, memory)
        return hs

# Build MLP as needed by TubeDETR
class MLP(nn.Module):
    """Very simple multi-layer perceptron (also called FFN)"""

    def __init__(self, input_dim, hidden_dim, output_dim, num_layers, dropout=0):
        super().__init__()
        self.num_layers = num_layers
        h = [hidden_dim] * (num_layers - 1)
        self.layers = nn.ModuleList((nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])))
        self.dropout = dropout
        if dropout:
            self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        for i, layer in enumerate(self.layers):
            x = nn.functional.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
            if self.dropout and i < self.num_layers:
                x = self.dropout(x)
        return x

# Minimal backbone instance
backbone = MinimalBackbone(num_channels=3)

# Minimal transformer instance
transformer = MinimalTransformer(d_model=64)

# Create arguments dictionary
ARGS = {
    'backbone': backbone,
    'transformer': transformer,
    'num_queries': 8,
    'aux_loss': False,
    'video_max_len': 200,
    'stride': 5,
    'guided_attn': False,
    'fast': False,
    'fast_mode': '',
    'sted': True,
}
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 TubeDETR — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TubeDETR 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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
MLP
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2209.13306 (2022-09)
Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding
2401.01578 (2024-01)
Context-Guided Spatio-Temporal Video Grounding

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 consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformerbased architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks.

For agents

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

get_harvested_code_for_paper("2203.16434")
get_code_for_paper("2203.16434")
have("2203.16434")

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

curl https://syntology.ai/api/ran/2203.16434.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16434.svg)](https://syntology.ai/paper/2203.16434)

Connect an agent — have() is free.