SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.01686 · AAAI · 2024

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

Xianxian Li, Shengping Zhang, Bineng Zhong, Qihua Liang, Yaozong Zheng, Zhiyi Mo

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/2401.01686.json · badge: /api/ran/2401.01686.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
GXNU-ZhongLab/ODTrack community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ODTrack Ran
ran on a synthesized input · constructed an object; no result was computed
GXNU-ZhongLab/ODTrack/lib/models/odtrack/odtrack.py
code served (permissive licence) · get_code("0002ed5067d80cd9")
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, ODTrack: 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)

# Create a minimal transformer backbone that satisfies the interface
class MinimalTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.add_cls_token = True
        self.linear = nn.Linear(64, 64)
    
    def forward(self, z, x, ce_template_mask=None, ce_keep_rate=None, return_last_attn=False, track_query=None, token_len=1):
        # z is template (copied), x is search
        # Returns (features, aux_dict)
        # features shape: (batch, seq_len, hidden_dim)
        # seq_len includes cls token + search tokens
        batch_size = x.shape[0]
        # cls_token (1 token) + search_tokens (4 tokens for 2x2 feat_sz)
        seq_len = token_len + 4  # 1 cls + 4 search patches (2x2)
        hidden_dim = 64
        features = torch.randn(batch_size, seq_len, hidden_dim)
        aux_dict = {}
        return features, aux_dict

# Create a minimal box head for CORNER head type
class MinimalBoxHead(nn.Module):
    def __init__(self):
        super().__init__()
        self.feat_sz = 2  # 2x2 feature map
        self.conv = nn.Conv2d(64, 4, kernel_size=1)  # Output 4 coords for box
        self.score_conv = nn.Conv2d(64, 1, kernel_size=1)  # Score map
    
    def forward(self, x, return_score=False):
        # x: (batch*num_queries, channels, feat_sz, feat_sz)
        # Output: pred_box (batch*num_queries, 4), score_map (batch*num_queries, 1, feat_sz, feat_sz)
        pred_box = self.conv(x).view(x.shape[0], 4, -1).mean(dim=2)  # (batch*num_queries, 4)
        score_map = self.score_conv(x)  # (batch*num_queries, 1, feat_sz, feat_sz)
        # Clamp to valid box coordinates [0, 1]
        pred_box = torch.clamp(pred_box, 0, 1)
        if return_score:
            return pred_box, score_map
        return pred_box

# Build arguments
transformer = MinimalTransformer()
box_head = MinimalBoxHead()

ARGS = {
    'transformer': transformer,
    'box_head': box_head,
    'aux_loss': False,
    'head_type': 'CORNER',
    'token_len': 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 ODTrack — 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 ODTrack 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

Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named ODTrack, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatiotemporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new SOTA performance on seven benchmarks, while running at real-time speed. Code and models are available at https://github.com/GXNU-ZhongLab/ODTrack.

For agents

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

get_harvested_code_for_paper("2401.01686")
get_code_for_paper("2401.01686")
have("2401.01686")

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

curl https://syntology.ai/api/ran/2401.01686.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.01686.svg)](https://syntology.ai/paper/2401.01686)

Connect an agent — have() is free.