SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.16265 · ECCV · 2022

SeqTR: A Simple yet Universal Network for Visual Grounding

Chao Chen, Rongrong Ji, Mingbao Lin, Yiyi Zhou, Xiaoshuai Sun, Yunhang Shen, Gen Luo, Chaoyang Zhu, Liujuan Cao, Xingjia Pan

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 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/2203.16265.json · badge: /api/ran/2203.16265.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
luogen1996/simrec community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
autopad Ran
ran, honoured the contract we drafted
luogen1996/simrec/simrec/layers/blocks.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yang-0201/YOLOv6_pro, is pointer only (licence: GPL-3.0) · get_code("988a3c854b1b13d0")
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 yang-0201/YOLOv6_pro, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

darknet_conv Ran
ran; our contract draft was wrong, not the code
luogen1996/simrec/simrec/layers/blocks.py
code served (permissive licence) · get_code("7bbf38c6e78784a8")
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 Sequential. 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 = {
    'in_ch': 3,
    'out_ch': 64,
    'ksize': 3,
    'stride': 1,
    'dilation_rate': 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_activation Ran
ran; our contract draft was wrong, not the code
luogen1996/simrec/simrec/layers/activation.py
code served (permissive licence) · get_code("6e3d5f4c3ce305d7")
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 SiLU. 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 = {
    'name': 'silu',
    'inplace': 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 SiLU — a SiLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SiLU 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
vgg_conv Ran
ran on a synthesized input
luogen1996/simrec/simrec/layers/blocks.py
code served (permissive licence) · get_code("60594d843d65ad4b")
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 Sequential. 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 = {
    'in_ch': 3,
    'out_ch': 64,
    'ksize': 3,
    'stride': 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 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
autopad 23 other papers
7 dated earlier, 16 later · 1 only as an assembly brick
1311.2524 (2013-11)
Rich feature hierarchies for accurate object detection and semantic segmentation
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
and 20 more not named here
get_activation 10 other papers
4 dated earlier, 6 later
1803.11365 (2018-03)
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
2107.08430 (2021-07)
YOLOX: Exceeding YOLO Series in 2021
2108.04230 (2021-08)
Workshop on Autonomous Driving at CVPR 2021: Technical Report for Streaming Perception Challenge
and 7 more not named here
darknet_conv 3 other papers
3 later
Yu_Revisiting_Counterfactual_Problems_in_Referring_Expression_Comprehension_CVPR_2024_paper (2024 (year only))
Revisiting Counterfactual Problems in Referring Expression Comprehension
Chen_DViN_Dynamic_Visual_Routing_Network_for_Weakly_Supervised_Referring_Expression_CVPR_2025_paper (2025 (year only))
DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension
2505.18686 (2025-05)
WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation
vgg_conv 1 other paper
1 later
Yu_Revisiting_Counterfactual_Problems_in_Referring_Expression_Comprehension_CVPR_2024_paper (2024 (year only))
Revisiting Counterfactual Problems in Referring Expression Comprehension

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

In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e.g., phrase localization, referring expression comprehension (REC) and segmentation (RES). The canonical paradigms for visual grounding often require substantial expertise in designing network architectures and loss functions, making them hard to generalize across tasks. To simplify and unify the modeling, we cast visual grounding as a point prediction problem conditioned on image and text inputs, where either the bounding box or binary mask is represented as a sequence of discrete coordinate tokens. Under this paradigm, visual grounding tasks are unified in our SeqTR network without task-specific branches or heads, e.g., the convolutional mask decoder for RES, which greatly reduces the complexity of multi-task modeling. In addition, SeqTR also shares the same optimization objective for all tasks with a simple cross-entropy loss, further reducing the complexity of deploying hand-crafted loss functions. Experiments on five benchmark datasets demonstrate that the proposed SeqTR outperforms (or is on par with) the existing state-of-the-arts, proving that a simple yet universal approach for visual grounding is indeed feasible. Source code is available at https://github.com/sean-zhuh/SeqTR.

For agents

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

get_harvested_code_for_paper("2203.16265")
get_code_for_paper("2203.16265")
have("2203.16265")

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

curl https://syntology.ai/api/ran/2203.16265.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.16265.svg)](https://syntology.ai/paper/2203.16265)

Connect an agent — have() is free.