SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09416 · CVPR · 2022

Bi-directional Object-Context Prioritization Learning for Saliency Ranking

Ke Xu, Hong Kong, Rynson Lau, Xin Yang, Xin Tian, Baocai Yin, Lin Du

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 (0 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/2203.09416.json · badge: /api/ran/2203.09416.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
GrassBro/OCOR community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
OCOR Ran
ran on a synthesized input
GrassBro/OCOR/mmdet/models/roi_heads/bbox_heads/OCOR.py
code served (permissive licence) · get_code("27e08c4d9ba6fb23")
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, 4, 8, 8) 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 = {
    'hidden_dim': 4,
    'kernel_size': 3,
    'num_head': 2,
    'mlp_1x1': False,
}

ARGS = {
    'x': torch.randn(2, 4, 8, 8),
}

if __name__ == '__main__':
    model = nn.Module()
    
    class OCOR(nn.Module):

        def __init__(self, hidden_dim=512, kernel_size=3, num_head=1, mlp_1x1=False):
            super(OCOR, self).__init__()
            self.hidden_dim = hidden_dim
            self.num_head = num_head
            self.out_channel = int(num_head * hidden_dim)
            padding = kernel_size // 2
            self.conv_q = nn.Conv2d(hidden_dim, self.out_channel, kernel_size, padding=padding, bias=False)
            self.conv_k = nn.Conv2d(hidden_dim, self.out_channel, kernel_size, padding=padding, bias=False)
            self.conv_v = nn.Conv2d(hidden_dim, self.out_channel, kernel_size, padding=padding, bias=False)
            self.conv = nn.Conv2d(self.out_channel, hidden_dim, 1 if mlp_1x1 else kernel_size, padding=0 if mlp_1x1 else padding, bias=False)
            self.norm = nn.GroupNorm(1, self.out_channel, affine=True)
            self.dp = nn.Dropout(0.2)

        def forward(self, x):
            query = self.conv_q(x).unsqueeze(1)
            key = self.conv_k(x).unsqueeze(0)
            att = (query * key).sum(2) / self.hidden_dim ** 0.5
            att = nn.Softmax(dim=1)(att)
            value = self.conv_v(x)
            virt_feats = (att.unsqueeze(2) * value).sum(1)
            virt_feats = self.norm(virt_feats)
            virt_feats = nn.functional.relu(virt_feats)
            virt_feats = self.conv(virt_feats)
            virt_feats = self.dp(virt_feats)
            x = x + virt_feats
            return x

    model = OCOR(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: {ARGS['x'].shape}")
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, 4, 8, 8) — shape (2, 4, 8, 8) 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)

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

The saliency ranking task is recently proposed to study the visual behavior that humans would typically shift their attention over different objects of a scene based on their degrees of saliency. Existing approaches focus on learning either object-object or object-scene relations. Such a strategy follows the idea of object-based attention in Psychology, but it tends to favor objects with strong semantics (e.g., humans), resulting in unrealistic saliency ranking. We observe that spatial attention works concurrently with object-based attention in the human visual recognition system. During the recognition process, the human spatial attention mechanism would move, engage, and disengage from region to region (i.e., context to context). This inspires us to model region-level interactions, in addition to object-level reasoning, for saliency ranking. Hence, we propose a novel bidirectional method to unify spatial attention and objectbased attention for saliency ranking. Our model has two novel modules: (1) a selective object saliency (SOS) module to model object-based attention via inferring the semantic representation of salient objects, and (2) an object-contextobject relation (OCOR) module to allocate saliency ranks to objects by jointly modeling object-context and contextobject interactions of salient objects. Extensive experiments show that our approach outperforms existing state-of-theart methods. Code and pretrained model are available at https://github.com/GrassBro/OCOR.

For agents

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

get_harvested_code_for_paper("2203.09416")
get_code_for_paper("2203.09416")
have("2203.09416")

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

curl https://syntology.ai/api/ran/2203.09416.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.09416.svg)](https://syntology.ai/paper/2203.09416)

Connect an agent — have() is free.