SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00969 · 2021

TubeR: Tubelet Transformer for Video Action Detection

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 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/2104.00969.json · badge: /api/ran/2104.00969.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
amazon-science/tubelet-transformer community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran; our contract draft was wrong, not the code
amazon-science/tubelet-transformer/models/transformer/util/misc.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("aa6da43d05cfaf65")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, 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.

box_cxcywh_to_xyxy Ran
ran, honoured the contract we drafted
amazon-science/tubelet-transformer/models/transformer/util/box_ops.py
code served (permissive licence) · get_code("e0a06ded5d4f6c3c")
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) 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)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [center_x, center_y, width, height] values
# It unbinds the last dimension and converts to [x_min, y_min, x_max, y_max]

x = torch.tensor([
    [10.0, 20.0, 4.0, 6.0],
    [30.0, 40.0, 8.0, 10.0]
])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
box_iou Ran
ran, honoured the contract we drafted
amazon-science/tubelet-transformer/models/transformer/util/box_ops.py
code served (permissive licence) · get_code("ce749f837424dd8c")
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, ndim 3, dtype family float; 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 torch
from torchvision.ops.boxes import box_area

torch.manual_seed(0)

# Create two sets of bounding boxes in format [x1, y1, x2, y2]
# boxes1: 2 boxes
# boxes2: 3 boxes
boxes1 = torch.tensor([
    [0.0, 0.0, 2.0, 2.0],
    [1.0, 1.0, 3.0, 3.0]
], dtype=torch.float32)

boxes2 = torch.tensor([
    [0.0, 0.0, 1.0, 1.0],
    [1.5, 1.5, 2.5, 2.5],
    [2.0, 2.0, 4.0, 4.0]
], dtype=torch.float32)

ARGS = {
    "boxes1": boxes1,
    "boxes2": boxes2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
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
box_xyxy_to_cxcywh Ran
ran, honoured the contract we drafted
amazon-science/tubelet-transformer/models/transformer/util/box_ops.py
code served (permissive licence) · get_code("031b02fb990284ba")
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) 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)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [x0, y0, x1, y1] coordinates (xyxy format)
# It unbinds the last dimension and converts to center-xy, width, height format

x = torch.tensor([
    [10.0, 20.0, 30.0, 40.0],
    [5.0, 15.0, 25.0, 35.0]
])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
collate_fn Ran
ran; our contract draft was wrong, not the code
amazon-science/tubelet-transformer/models/transformer/util/misc.py
code served (permissive licence) · get_code("dc78bab96f28fdc8")
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
from typing import List

torch.manual_seed(0)

class NestedTensor(object):
    def __init__(self, tensors, mask=None):
        self.tensors = tensors
        self.mask = mask

    def to(self, device):
        cast_tensor = self.tensors.to(device)
        mask = self.mask
        if mask is not None:
            cast_mask = mask.to(device)
        else:
            cast_mask = None
        return NestedTensor(cast_tensor, cast_mask)

    def decompose(self):
        return (self.tensors, self.mask)

    def __repr__(self):
        return str(self.tensors)

def _max_by_axis(the_list):
    maxes = the_list[0]
    for sublist in the_list[1:]:
        for index, item in enumerate(sublist):
            maxes[index] = max(maxes[index], item)
    return maxes

def nested_tensor_from_tensor_list(tensor_list: List[torch.Tensor]):
    if tensor_list[0].ndim == 3:
        max_size = _max_by_axis([list(img.shape) for img in tensor_list])
        batch_shape = [len(tensor_list)] + max_size
        b, c, h, w = batch_shape
        dtype = tensor_list[0].dtype
        device = tensor_list[0].device
        tensor = torch.zeros(batch_shape, dtype=dtype, device=device)
        mask = torch.ones((b, h, w), dtype=torch.bool, device=device)
        for img, pad_img, m in zip(tensor_list, tensor, mask):
            pad_img[:img.shape[0], :img.shape[1], :img.shape[2]].copy_(img)
            m[:img.shape[1], :img.shape[2]] = False
    elif tensor_list[0].ndim == 4:
        max_size = _max_by_axis([list(clip.shape) for clip in tensor_list])
        batch_shape = [len(tensor_list)] + max_size
        b, c, t, h, w = batch_shape
        dtype = tensor_list[0].dtype
        device = tensor_list[0].device
        tensor = torch.zeros(batch_shape, dtype=dtype, device=device)
        mask = torch.ones((b, h, w), dtype=torch.bool, device=device)
        for img, pad_img, m in zip(tensor_list, tensor, mask):
            pad_img[:img.shape[0], :img.shape[1], :img.shape[2], :img.shape[3]].copy_(img)
            m[:img.shape[2], :img.shape[3]] = False
    else:
        raise ValueError('not supported')
    return NestedTensor(tensor, mask)

def collate_fn(batch):
    batch = list(zip(*batch))
    batch[0] = nested_tensor_from_tensor_list(batch[0])
    return tuple(batch)

# Create test data: batch of tuples with 3D tensors and metadata
tensor1 = torch.randn(3, 4, 5)  # (C, H, W)
tensor2 = torch.randn(3, 6, 7)  # (C, H, W) with different spatial dims
metadata1 = "sample_1"
metadata2 = "sample_2"

batch_data = [
    (tensor1, metadata1),
    (tensor2, metadata2)
]

ARGS = {
    "batch": batch_data
}
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
layer_norm Ran
ran; our contract draft was wrong, not the code
amazon-science/tubelet-transformer/models/transformer/transformer_layers.py
code served (permissive licence) · get_code("99c111ef29c683f2")
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 LayerNorm. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    "d_model": 8,
    "condition": 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 LayerNorm — a LayerNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LayerNorm 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
reduce_dict Ran
ran; our contract draft was wrong, not the code
amazon-science/tubelet-transformer/models/transformer/util/misc.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("05992505df9ef0cd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, 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.

build_transformer Not yet run
unverified (harvested, no recorded run)
amazon-science/tubelet-transformer/models/transformer/transformer.py
code served (permissive licence) · get_code("7b94aa61b4d5ecac")
How it ran

no invocation recorded.

plot_precision_recall Not yet run
unverified (harvested, no recorded run)
amazon-science/tubelet-transformer/models/transformer/util/plot_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("fe699ae8220daf07")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 3 the same month, 8 later) and 1 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
box_cxcywh_to_xyxy 49 other papers
4 dated earlier, 45 later · 11 only as an assembly brick
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
and 46 more not named here
box_xyxy_to_cxcywh 45 other papers
3 dated earlier, 42 later · 20 only as an assembly brick
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2103.17154 (2021-03)
Learning Spatio-Temporal Transformer for Visual Tracking
and 42 more not named here
reduce_dict 33 other papers
3 dated earlier, 1 the same month, 29 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
1811.10200 (2018-11)
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
2007.02419 (2020-07)
Attention-based Joint Detection of Object and Semantic Part
and 30 more not named here
all_gather 30 other papers
3 dated earlier, 1 the same month, 26 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
1811.10200 (2018-11)
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
2007.02419 (2020-07)
Attention-based Joint Detection of Object and Semantic Part
and 27 more not named here
box_iou 24 other papers
1 dated earlier, 22 later, 1 undated · 5 only as an assembly brick
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
2203.01666 (2022-03)
Correlation-Aware Deep Tracking
and 21 more not named here
collate_fn 16 other papers
1 dated earlier, 1 the same month, 14 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
2104.08541 (2021-04)
TransVG: End-to-End Visual Grounding with Transformers
2111.10135 (2021-11)
Grounded Situation Recognition with Transformers
and 13 more not named here
plot_precision_recall 2 other papers
2 later
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
2212.02773 (2022-12)
DiffusionInst: Diffusion Model for Instance Segmentation
layer_norm 1 other paper
1 later
2107.03377 (2021-07)
Long Short-Term Transformer for Online Action Detection

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 propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.

For agents

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

get_harvested_code_for_paper("2104.00969")
get_code_for_paper("2104.00969")
have("2104.00969")

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

curl https://syntology.ai/api/ran/2104.00969.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00969.svg)](https://syntology.ai/paper/2104.00969)

Connect an agent — have() is free.