SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.10271 · 2021

End-to-end Temporal Action Detection with Transformer

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 2 failures of our instrument; 1 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/2106.10271.json · badge: /api/ran/2106.10271.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
xlliu7/TadTR canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
get_classes Ran
ran; our contract draft was wrong, not the code
xlliu7/TadTR/Evaluation/eval_detection.py
code served (permissive licence) · get_code("f4bbeee84bc07a00")
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 list, ndim 1, 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
import numpy as np

# Based on the function logic, get_classes takes anno_dict which can have:
# 1. A 'classes' key with a list of class labels, OR
# 2. A 'database' key with a dict of videos, each containing 'annotations' with label info

# Create a sample anno_dict with the 'database' path (more complex case)
database = {
    'video_001': {
        'annotations': [
            {'label': 'person'},
            {'label': 'car'},
            {'label': 'person'}
        ]
    },
    'video_002': {
        'annotations': [
            {'label': 'dog'},
            {'label': 'car'}
        ]
    },
    'video_003': {
        'annotations': [
            {'label': 'cat'},
            {'label': 'person'}
        ]
    }
}

anno_dict = {
    'database': database
}

ARGS = {
    'anno_dict': anno_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
setup_logger Ran
ran; our contract draft was wrong, not the code
xlliu7/TadTR/Evaluation/eval_detection.py
code served (permissive licence) · get_code("483d79f60d8148d2")
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 Logger. 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 sys
import logging
import tempfile
import os

# Create a temporary file for logging
temp_log_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log')
log_file_path = temp_log_file.name
temp_log_file.close()

# Define arguments for setup_logger
ARGS = {
    'log_file_path': log_file_path,
    'name': 'test_logger',
    'level': logging.DEBUG
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
compute_average_precision_detection Not yet run
unverified (harvested, no recorded run)
xlliu7/TadTR/Evaluation/eval_detection.py
code served (permissive licence) · get_code("2795b6049353a54d")
How it ran

no invocation recorded.

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.

For agents

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

get_harvested_code_for_paper("2106.10271")
get_code_for_paper("2106.10271")
have("2106.10271")

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

curl https://syntology.ai/api/ran/2106.10271.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.10271.svg)](https://syntology.ai/paper/2106.10271)

Connect an agent — have() is free.