SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.05328 · ECCV · 2022

Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking

Wei Wu, Bo Li, Lei Bai, Wanli Ouyang, Qiuhong Shen, Boyu Chen, Weihao Gan, Peixia Li, Lei Qiao

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has 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/2203.05328.json · badge: /api/ran/2203.05328.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
LPXTT/SimTrack community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SimTrack Ran
ran on a synthesized input · constructed an object; no result was computed
LPXTT/SimTrack/lib/models/stark/simtrack.py
code served (permissive licence) · get_code("a269cbe97ebf8b9c")
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, SimTrack: 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
from torch import nn

torch.manual_seed(0)

# Build a minimal backbone that satisfies the usage in SimTrack
class MinimalBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        self.num_features = 16
        self.sz = 4
        self.conv = nn.Conv2d(3, self.num_features, kernel_size=3, padding=1)
    
    def forward(self, x):
        # x is [template_img, search_img, template_anno]
        # Process and return feature tensor
        if isinstance(x, list):
            x = x[0]  # Take first image
        out = self.conv(x)
        return out

# Build a minimal box_head that satisfies the usage in SimTrack
class MinimalBoxHead(nn.Module):
    def __init__(self, in_channels=16):
        super().__init__()
        self.channel = 8
        self.conv = nn.Conv2d(in_channels, 4, kernel_size=1)
    
    def forward(self, x):
        # x has shape (bs, C, H, W)
        # Return bounding box predictions in xyxy format
        out = self.conv(x)
        # out shape: (bs, 4, H, W)
        # Reshape to (bs*H*W, 4)
        bs, c, h, w = out.shape
        out = out.permute(0, 2, 3, 1).reshape(-1, 4)
        return out

# Create instances
backbone = MinimalBackbone()
box_head = MinimalBoxHead(in_channels=backbone.num_features)

ARGS = {
    'backbone': backbone,
    'box_head': box_head,
    'aux_loss': False,
    'head_type': 'CORNER'
}
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 SimTrack — 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 SimTrack 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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 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.

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

Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest. However, existing tracking approaches rely on customized submodules and need prior knowledge for architecture selection, hindering the development of tracking in a more general system. This paper presents a Simplified Tracking architecture (SimTrack) by leveraging a transformer backbone for joint feature extraction and interaction. Unlike existing Siamese trackers, we serialize the input images and concatenate them directly before the one-branch backbone. Feature interaction in the backbone helps to remove well-designed interaction modules and produce a more efficient and effective framework. To reduce the information loss from down-sampling in vision transformers, we further propose a foveal window strategy, providing more diverse input patches with acceptable computational costs. Our SimTrack improves the baseline with 2.5%/2.6% AUC gains on LaSOT/TNL2K and gets results competitive with other specialized tracking algorithms without bells and whistles. The source codes are available at https://github.com/LPXTT/SimTrack.

For agents

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

get_harvested_code_for_paper("2203.05328")
get_code_for_paper("2203.05328")
have("2203.05328")

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

curl https://syntology.ai/api/ran/2203.05328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.05328.svg)](https://syntology.ai/paper/2203.05328)

Connect an agent — have() is free.