SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.01166 · ECCV · 2022

Target-absent Human Attention

Dimitris Samaras, Minh Hoai, Seoyoung Ahn, Gregory Zelinsky, Zhibo Yang, Sounak Mondal

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 0 have no contract verdict; 3 failures of our instrument; 3 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/2207.01166.json · badge: /api/ran/2207.01166.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
cvlab-stonybrook/Target-absent-Human-Attention community
Papers with Code archive
3 ran · 3 no recorded run
FunctionStatusWhere it lives
get_foveal_weights Ran
ran; our contract draft was wrong, not the code
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("f6a5a264688d48a4")
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 Tensor, ndim 4, dtype family float, shape (2, 5, 48, 64) 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 math

torch.manual_seed(0)

# Create a small batch of normalized fixation points
# Shape: (batch_size=2, fix_num=3, 2) where last dim is (x, y) normalized to [0, 1]
fixation_batch = torch.rand(2, 3, 2)

# Image dimensions
width = 64
height = 48

# Optional parameters with defaults
sigma = 0.248
p = 7.5
k = 1.5
alpha = 1.25

ARGS = {
    'fixation_batch': fixation_batch,
    'width': width,
    'height': height,
    'sigma': sigma,
    'p': p,
    'k': k,
    'alpha': alpha,
}
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 Tensor, ndim 4, dtype family float, shape (2, 5, 48, 64) — shape (2, 5, 48, 64) 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
get_sinuposition_encoding Ran
ran; our contract draft was wrong, not the code
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("eb4644da46176b93")
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 Tensor, ndim 2, dtype family float, shape (2, 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 numpy as np

torch.manual_seed(0)

# current_fix: tensor of shape (batch_size, 2) with fixation coordinates
# Values can be normalized (0-1) or in patch coordinates
current_fix = torch.tensor([
    [0.3, 0.5],
    [0.7, 0.2]
], dtype=torch.float32)

# d_model: embedding dimension (should be even)
d_model = 8

# patch_num: number of patches (used to scale normalized coordinates)
patch_num = [16, 16]

ARGS = {
    "current_fix": current_fix,
    "d_model": d_model,
    "patch_num": patch_num
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 8) — shape (2, 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: none by the harness; any seed is in the setup block
get_sinuposition_encoding_all Ran
ran; our contract draft was wrong, not the code
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("56a410b6b656e722")
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 Tensor, ndim 3, dtype family float, shape (8, 3, 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 numpy as np

torch.manual_seed(0)

# Analyze the function:
# - d_model: int, used for dimension calculations (divided by 2, used in arange and exp)
# - patch_num: tuple/list with 2 elements, used to create meshgrid and determine spatial dimensions

ARGS = {
    "d_model": 8,
    "patch_num": (4, 3)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 3, dtype family float, shape (8, 3, 4) — shape (8, 3, 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: none by the harness; any seed is in the setup block
FFNGeneratorCond_V2 Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("3149ea3842140254")
How it ran

no invocation recorded.

FeatureFovealNet Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("85326d8128cb4bc0")
How it ran

no invocation recorded.

Self_Attn Not yet run
unverified (harvested, no recorded run)
cvlab-stonybrook/Target-absent-Human-Attention/irl_ffm/FFM_models.py
code served (permissive licence) · get_code("4591f3f9390a162a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 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.

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 prediction of human gaze behavior is important for building human-computer interaction systems that can anticipate the user's attention. Computer vision models have been developed to predict the fixations made by people as they search for target objects. But what about when the target is not in the image? Equally important is to know how people search when they cannot find a target, and when they would stop searching. In this paper, we propose a data-driven computational model that addresses the search-termination problem and predicts the scanpath of search fixations made by people searching for targets that do not appear in images. We model visual search as an imitation learning problem and represent the internal knowledge that the viewer acquires through fixations using a novel state representation that we call Foveated Feature Maps (FFMs). FFMs integrate a simulated foveated retina into a pretrained ConvNet that produces an in-network feature pyramid, all with minimal computational overhead. Our method integrates FFMs as the state representation in inverse reinforcement learning. Experimentally, we improve the state of the art in predicting human target-absent search behavior on the COCO-Search18 dataset. Code is available at: https://github.com/cvlab-stonybrook/Target-absent-Human-Attention.

For agents

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

get_harvested_code_for_paper("2207.01166")
get_code_for_paper("2207.01166")
have("2207.01166")

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

curl https://syntology.ai/api/ran/2207.01166.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.01166.svg)](https://syntology.ai/paper/2207.01166)

Connect an agent — have() is free.