SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.04608 · 2020

Actions as Moving Points

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 5 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/2001.04608.json · badge: /api/ran/2001.04608.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
MCG-NJU/MOC-Detector canonical (classifier label)
classifier basis: census
3 ran · 5 no recorded run
NEUdeep/MOC-Detector-Pytorch1.4 community (classifier label)
classifier basis: plan_row
1 ran · 0 no recorded run
FunctionStatusWhere it lives
draw_umich_gaussian Ran
ran; our contract draft was wrong, not the code
MCG-NJU/MOC-Detector/src/MOC_utils/gaussian_hm.py
pointer only (licence: MIT); the stored copy get_code serves, from henglan/cgstvg, is pointer only (licence: NONE) · get_code("fd3666d3bd51e693")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from henglan/cgstvg, 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.

flip_tensor Ran
ran; our contract draft was wrong, not the code
NEUdeep/MOC-Detector-Pytorch1.4/src/MOC_utils/utils.py
code served (permissive licence) · get_code("6e3e0dbceafbf01c")
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 4, dtype family float, shape (2, 4, 3, 5) 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 flip_tensor takes a tensor x and flips it along dimension 3
# We need to create a tensor with at least 4 dimensions (since we're flipping dimension [3])
# Using shape (2, 4, 3, 5) to have distinct sizes for each dimension
x = torch.randn(2, 4, 3, 5)

ARGS = {
    "x": x
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
gaussian2D Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MCG-NJU/MOC-Detector/src/MOC_utils/gaussian_hm.py
pointer only (licence: MIT); the stored copy get_code serves, from CrazyShout/INSTINCT, is pointer only (licence: NOASSERTION) · get_code("86282b7f90be63f2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from CrazyShout/INSTINCT, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

gaussian_radius Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MCG-NJU/MOC-Detector/src/MOC_utils/gaussian_hm.py
pointer only (licence: MIT); the stored copy get_code serves, from henglan/cgstvg, is pointer only (licence: NONE) · get_code("f2a33236566ea043")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from henglan/cgstvg, 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.

DataParallel Not yet run
unverified (harvested, no recorded run)
MCG-NJU/MOC-Detector/src/MOC_utils/data_parallel.py
code served (permissive licence) · get_code("ddb5a5004c8da97a")
How it ran

no invocation recorded.

data_parallel Not yet run
unverified (harvested, no recorded run)
MCG-NJU/MOC-Detector/src/MOC_utils/data_parallel.py
code served (permissive licence) · get_code("61bf3906cbd2ee87")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
MCG-NJU/MOC-Detector/src/MOC_utils/model.py
code served (permissive licence) · get_code("b32caffdac3e2e03")
How it ran

no invocation recorded.

scatter Not yet run
unverified (harvested, no recorded run)
MCG-NJU/MOC-Detector/src/MOC_utils/scatter_gather.py
code served (permissive licence) · get_code("4c7015c577141603")
How it ran

no invocation recorded.

scatter_kwargs Not yet run
unverified (harvested, no recorded run)
MCG-NJU/MOC-Detector/src/MOC_utils/scatter_gather.py
code served (permissive licence) · get_code("08aa371b972a4c91")
How it ran

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, 0 the same month, 6 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
data_parallel 9 other papers
6 dated earlier, 3 later
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
and 6 more not named here
gaussian2D 9 other papers
1 dated earlier, 8 later
1904.07850 (2019-04)
Objects as Points
2104.07986 (2021-04)
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
2105.05003 (2021-05)
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
and 6 more not named here
DataParallel 5 other papers
2 dated earlier, 3 later
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1904.07850 (2019-04)
Objects as Points
2003.14023 (2020-03)
Learning Human-Object Interaction Detection using Interaction Points
and 2 more not named here
gaussian_radius 4 other papers
1 dated earlier, 3 later
1909.00700 (2019-09)
Training-Time-Friendly Network for Real-Time Object Detection
2104.07986 (2021-04)
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection
and 1 more not named here
draw_umich_gaussian 3 other papers
3 later
2105.05003 (2021-05)
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection
2401.01578 (2024-01)
Context-Guided Spatio-Temporal Video Grounding
scatter 3 other papers
3 dated earlier
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
1904.08189 (2019-04)
CenterNet: Keypoint Triplets for Object Detection
scatter_kwargs 3 other papers
3 dated earlier
1603.00831 (2016-03)
MOT16: A Benchmark for Multi-Object Tracking
1808.01244 (2018-08)
CornerNet: Detecting Objects as Paired Keypoints
1904.08189 (2019-04)
CenterNet: Keypoint Triplets for Object Detection
flip_tensor 1 other paper
1 later
2308.09351 (2023-08)
RLIPv2: Fast Scaling of Relational Language-Image Pre-training

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

The existing action tubelet detectors often depend on heuristic anchor design and placement, which might be computationally expensive and sub-optimal for precise localization. In this paper, we present a conceptually simple, computationally efficient, and more precise action tubelet detection framework, termed as MovingCenter Detector (MOC-detector), by treating an action instance as a trajectory of moving points. Based on the insight that movement information could simplify and assist action tubelet detection, our MOC-detector is composed of three crucial head branches: (1) Center Branch for instance center detection and action recognition, (2) Movement Branch for movement estimation at adjacent frames to form trajectories of moving points, (3) Box Branch for spatial extent detection by directly regressing bounding box size at each estimated center. These three branches work together to generate the tubelet detection results, which could be further linked to yield video-level tubes with a matching strategy. Our MOC-detector outperforms the existing state-of-the-art methods for both metrics of frame-mAP and video-mAP on the JHMDB and UCF101-24 datasets. The performance gap is more evident for higher video IoU, demonstrating that our MOC-detector is particularly effective for more precise action detection. We provide the code at https://github.com/MCG-NJU/MOC-Detector.

For agents

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

get_harvested_code_for_paper("2001.04608")
get_code_for_paper("2001.04608")
have("2001.04608")

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

curl https://syntology.ai/api/ran/2001.04608.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.04608.svg)](https://syntology.ai/paper/2001.04608)

Connect an agent — have() is free.