SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.08956 · ECCV · 2022

Panoramic Vision Transformer for Saliency Detection in 360 • Videos

Gunhee Kim, Heeseung Yun, Sehun Lee

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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, 1 violated it and 3 have no contract verdict; 1 failure of our instrument; 2 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/2209.08956.json · badge: /api/ran/2209.08956.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
hs-yn/paver marked official in Papers with Code
Papers with Code archive
5 ran · 2 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("cc958048d557e1e9")
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, shape (2, 3, 5, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

INIT_ARGS = {
    'dim': 4,
    'num_heads': 2,
    'qkv_bias': False,
    'attn_drop': 0.0,
    'proj_drop': 0.0,
}

ARGS = {
    'x': torch.randn(2, 3, 5, 4),
}

if __name__ == '__main__':
    attention = nn.Module()
    attention.__class__ = type('Attention', (nn.Module,), {
        '__init__': Attention.__init__,
        'forward': Attention.forward,
    })
    
    from types import MethodType
    
    class Attention(nn.Module):
        def __init__(self, dim, num_heads=8, qkv_bias=False, attn_drop=0.0, proj_drop=0.0):
            super().__init__()
            self.num_heads = num_heads
            head_dim = dim // num_heads
            self.scale = head_dim ** (-0.5)
            self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
            self.attn_drop = nn.Dropout(attn_drop)
            self.proj = nn.Linear(dim, dim)
            self.proj_drop = nn.Dropout(proj_drop)

        def forward(self, x):
            B, T, N, C = x.shape
            qkv = self.qkv(x).reshape(B, T, N, 3, self.num_heads, C // self.num_heads).permute(3, 0, 1, 4, 2, 5)
            q, k, v = (qkv[0], qkv[1], qkv[2])
            attn = q @ k.transpose(-2, -1) * self.scale
            attn = attn.softmax(dim=-1)
            attn = self.attn_drop(attn)
            x = (attn @ v).transpose(2, 3).reshape(B, T, N, C)
            x = self.proj(x)
            x = self.proj_drop(x)
            return x
    
    model = Attention(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: {ARGS['x'].shape}")
    assert output.shape == ARGS['x'].shape, "Shape mismatch!"
    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 Tensor, ndim 4, dtype family float, shape (2, 3, 5, 4) — shape (2, 3, 5, 4) as a later run recorded it
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)
Block Ran
ran on a synthesized input
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("ac7ba009078385e6")
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 torch.nn as nn

# Define the classes (copy from the problem statement)
class Attention(nn.Module):

    def __init__(self, dim, num_heads=8, qkv_bias=False, attn_drop=0.0, proj_drop=0.0):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = head_dim ** (-0.5)
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

    def forward(self, x):
        B, T, N, C = x.shape
        qkv = self.qkv(x).reshape(B, T, N, 3, self.num_heads, C // self.num_heads).permute(3, 0, 1, 4, 2, 5)
        q, k, v = (qkv[0], qkv[1], qkv[2])
        attn = q @ k.transpose(-2, -1) * self.scale
        attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)
        x = (attn @ v).transpose(2, 3).reshape(B, T, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x

class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """

    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        if self.drop_prob == 0.0 or not self.training:
            return x
        keep_prob = 1 - self.drop_prob
        shape = (x.shape[0],) + (1,) * (x.ndim - 1)
        random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
        random_tensor.floor_()
        output = x.div(keep_prob) * random_tensor
        return output

class Mlp(nn.Module):
    """ MLP as used in Vision Transformer, MLP-Mixer and related networks
    """

    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.0):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x

class Block(nn.Module):

    def __init__(self, dim, num_heads, mlp_ratio=4.0, qkv_bias=False, drop=0.0, attn_drop=0.0, drop_path=0.0, act_layer=nn.GELU, norm_layer=nn.LayerNorm):
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention(dim, num_heads=num_heads, qkv_bias=qkv_bias, attn_drop=attn_drop, proj_drop=drop)
        self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)

    def forward(self, x):
        x = x + self.drop_path(self.attn(self.norm1(x)))
        x = x + self.drop_path(self.mlp(self.norm2(x)))
        return x

INIT_ARGS = {
    'dim': 4,
    'num_heads': 2,
    'mlp_ratio': 4.0,
    'qkv_bias': False,
    'drop': 0.0,
    'attn_drop': 0.0,
    'drop_path': 0.0,
    'act_layer': nn.GELU,
    'norm_layer': nn.LayerNorm,
}

ARGS = {
    'x': torch.randn(2, 3, 5, 4),
}

if __name__ == '__main__':
    block = Block(**INIT_ARGS)
    block.eval()
    output = block(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
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 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)
DropPath Ran
ran on a synthesized input
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("511f72cb4c20504a")
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 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """

    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        if self.drop_prob == 0.0 or not self.training:
            return x
        keep_prob = 1 - self.drop_prob
        shape = (x.shape[0],) + (1,) * (x.ndim - 1)
        random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
        random_tensor.floor_()
        output = x.div(keep_prob) * random_tensor
        return output


INIT_ARGS = {
    'drop_prob': 0.5
}

ARGS = {
    'x': torch.randn(2, 4, 3)
}

if __name__ == '__main__':
    model = DropPath(**INIT_ARGS)
    model.train()
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output:\n{output}")
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 Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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)
full_model Ran
ran; our contract draft was wrong, not the code
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("749238c52b987779")
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) and returned SimpleModel. 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 SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

target = SimpleModel()

ARGS = {
    "target": target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel 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
sphere_to_threed Ran
ran, violated the contract we drafted
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("49d32e2b965eb4a6")
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) and returned ndarray, ndim 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# The function sphere_to_threed takes spherical coordinates (theta, phi)
# and converts them to 3D Cartesian coordinates on a unit sphere.
# It expects data with shape (..., 2) where the last dimension contains
# [theta, phi] angles in radians.

# Create sample spherical coordinate data
# Shape: (2, 4, 2) - batch of 2, sequence of 4, with 2 angles (theta, phi)
data = np.random.randn(2, 4, 2) * np.pi

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
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
BaseDecoder Not yet run
unverified (harvested, no recorded run)
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("4268375daf6321ec")
How it ran

no invocation recorded.

PAVER Not yet run
unverified (harvested, no recorded run)
hs-yn/paver/code/model/decoder.py
code served (permissive licence) · get_code("963c1ed89e281395")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 6 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
Block
brick of this paper's assembly: model
7 other papers
2 dated earlier, 5 later · 1 only as an assembly brick
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2204.01678 (2022-04)
MultiMAE: Multi-modal Multi-task Masked Autoencoders
2302.01056 (2023-02)
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
and 4 more not named here

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

360 • video saliency detection is one of the challenging benchmarks for 360 • video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360 • videos, and capture-worthy viewpoint in the omnidirectional sphere is ambiguous by nature. We present a new framework named Panoramic Vision Transformer (PAVER). We design the encoder using Vision Transformer with deformable convolution, which enables us not only to plug pretrained models from normal videos into our architecture without additional modules or finetuning but also to perform geometric approximation only once, unlike previous deep CNN-based approaches. Thanks to its powerful encoder, PAVER can learn the saliency from three simple relative relations among local patch features, outperforming state-of-the-art models for the Wild360 benchmark by large margins without supervision or auxiliary information like class activation. We demonstrate the utility of our saliency prediction model with the omnidirectional video quality assessment task in VQA-ODV, where we consistently improve performance without any form of supervision, including head movement.

For agents

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

get_harvested_code_for_paper("2209.08956")
get_code_for_paper("2209.08956")
have("2209.08956")

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

curl https://syntology.ai/api/ran/2209.08956.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.08956.svg)](https://syntology.ai/paper/2209.08956)

Connect an agent — have() is free.