SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.09052 · ICCV · 2021

Object Tracking by Jointly Exploiting Frame and Event Domain

Xin Yang, Bo Dong, Baocai Yin, Jiqing Zhang, Xiaopeng Wei, Yingkai Fu

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have 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/2109.09052.json · badge: /api/ran/2109.09052.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
Jee-King/ICCV2021_Event_Frame_Tracking community
Papers with Code archive
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Cha_Spa Ran
ran on a synthesized input
Jee-King/ICCV2021_Event_Frame_Tracking/ltr/models/backbone/inter_attention.py
code served (permissive licence) · get_code("6760cc45c53c2c38")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned list. 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

class ChannelAttention(nn.Module):

    def __init__(self, in_planes, ratio=16):
        super(ChannelAttention, self).__init__()
        self.max_pool = nn.AdaptiveMaxPool2d(1)
        self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
        self.relu1 = nn.ReLU()
        self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
        out = max_out
        return self.sigmoid(out)

class SpatialAttention(nn.Module):

    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.conv1 = nn.Conv2d(1, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = max_out
        x = self.conv1(x)
        return self.sigmoid(x)

class Cha_Spa(nn.Module):

    def __init__(self):
        super(Cha_Spa, self).__init__()
        self.cha1 = ChannelAttention(128)
        self.cha2 = ChannelAttention(256)
        self.spa1 = SpatialAttention()
        self.spa2 = SpatialAttention()

    def forward(self, frame, event):
        temp1 = event[0].mul(self.cha1(event[0]))
        temp1 = temp1.mul(self.spa1(temp1))
        x1 = frame[0] + temp1
        temp2 = event[1].mul(self.cha2(event[1]))
        temp2 = temp2.mul(self.spa2(temp2))
        x2 = frame[1] + temp2
        return [x1, x2]

INIT_ARGS = {}

ARGS = {
    'frame': [
        torch.randn(2, 128, 4, 3),
        torch.randn(2, 256, 4, 3)
    ],
    'event': [
        torch.randn(2, 128, 4, 3),
        torch.randn(2, 256, 4, 3)
    ]
}

if __name__ == '__main__':
    model = Cha_Spa(**INIT_ARGS)
    output = model(**ARGS)
    print("Output shapes:", [x.shape for x in output])
    print("Success!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ChannelAttention Ran
ran on a synthesized input
Jee-King/ICCV2021_Event_Frame_Tracking/ltr/models/backbone/inter_attention.py
code served (permissive licence) · get_code("66870979109f65c3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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

# INIT_ARGS for ChannelAttention.__init__(in_planes, ratio=16)
INIT_ARGS = {
    'in_planes': 64,
    'ratio': 16
}

# ARGS for forward(x)
# x should be a 4D tensor: (batch, channels, height, width)
# channels must match in_planes=64
ARGS = {
    'x': torch.randn(2, 64, 8, 8)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SpatialAttention Ran
ran on a synthesized input · constructed an object; no result was computed
Jee-King/ICCV2021_Event_Frame_Tracking/ltr/models/backbone/inter_attention.py
code served (permissive licence) · get_code("e93262cac6f69156")
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, SpatialAttention: 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
import torch.nn as nn

torch.manual_seed(0)

class SpatialAttention(nn.Module):

    def __init__(self, kernel_size=7):
        super(SpatialAttention, self).__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.conv1 = nn.Conv2d(1, 1, kernel_size, padding=padding, bias=False)
        self.sigmoid = nn.Sigmoid()

    def forward(self, x):
        max_out, _ = torch.max(x, dim=1, keepdim=True)
        x = max_out
        x = self.conv1(x)
        return self.sigmoid(x)


# Create a small test input tensor: batch=2, channels=4, height=3, width=3
test_input = torch.randn(2, 4, 3, 3)

# Arguments for SpatialAttention
ARGS = {
    "kernel_size": 7
}

# Instantiate and execute
model = SpatialAttention(**ARGS)
output = model(test_input)
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 SpatialAttention — 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 SpatialAttention 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 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

Inspired by the complementarity between conventional frame-based and bio-inspired event-based cameras, we propose a multi-modal based approach to fuse visual cues from the frame-and event-domain to enhance the single object tracking performance, especially in degraded conditions (e.g., scenes with high dynamic range, low light, and fastmotion objects). The proposed approach can effectively and adaptively combine meaningful information from both domains. Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self-and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains. To exploit event-based visual cues in single-object tracking, we construct a largescale frame-event-based dataset, which we subsequently employ to train a novel frame-event fusion based model. Extensive experiments show that the proposed approach outperforms state-of-the-art frame-based tracking methods by at least 10.4% and 11.9% in terms of representative success rate and precision rate, respectively. Besides, the effectiveness of each key component of our approach is evidenced by our thorough ablation study.

For agents

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

get_harvested_code_for_paper("2109.09052")
get_code_for_paper("2109.09052")
have("2109.09052")

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

curl https://syntology.ai/api/ran/2109.09052.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.09052.svg)](https://syntology.ai/paper/2109.09052)

Connect an agent — have() is free.