HumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video

Nima Kamali; Sana Nasiri; Negar Kamali

cs.CVOct 21, 2026

HumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video

Authors: Nima Kamali, Sana Nasiri, Negar Kamali

Organizations: University of Applied Science and Technology (Allameh Tabataba’i Center), Iran. · Northwestern University.

Abstract

We introduce HumanCentric-Scenes-AI, a human-curated dataset of 296 AI-generated stimuli that depict people across four contexts in which people encounter AI-generated media. The Surveillance subset contains 85 AI-generated CCTV-style images. The Occupations subset contains 128 AI-generated occupational portraits in a balanced paired design covering 64 occupations with one female and one male version of each. The AI-edited subset contains 27 real photographs in which a region was altered or replaced by a generative model. The Video subset contains 56 AI-generated short videos. We curated the images and videos manually over multiple rounds to make them as photorealistic as possible. For each stimulus we release the file, the generation prompt where recorded, and per-stimulus metadata. We report depicted-gender distributions from an initial set of 134 generations without a specified gender and compare them with U.S. Bureau of Labor Statistics occupational gender shares. We report edit-region size and its association with zero-shot detection difficulty for the AI-edited subset. We report image-quality distributions for the Surveillance subset and subject-category coverage for the Video subset. HumanCentric-Scenes-AI is intended first for human-perception research, and also for calibration of AI-detection classifiers and bias analysis of generative models.

Figures & tables

Subset	Domain	Generator(s)	Released
Surveillance	CCTV-style images	Midjourney	85
Occupations	Gender–occupation pairings	Midjourney	128
AI-edited	Partial manipulation	Midjourney inpainting	27
Video	Short-form video	Veo 35, Sora 18, Kling 1, unattr. 2	56
Total			296

Table 1: HumanCentric-Scenes-AI releases all 296 AI-generated stimuli.

Column	Description
file_name	Repository path to the media file
filename	Content-hash filename (stable across releases)
original_filename	Descriptive curation-time name (e.g., go_f_054 )
modality	image / video
label	ai_generated
generator	midjourney / veo / sora / kling / unknown

Table 2: Schema of metadata.csv (one row per released file).

Measure (median [range])	Midjourney AI ( $n{=}25$ )	Real CCTV ( $n{=}25$ )
Resolution (px)	$600\times 600$	$600\times 600$
File size (KB)	128 [77–203]	98 [67–157]
Sharpness (Laplacian var.)	649 [31–9898]	212 [25–2383]

Table 3: Surveillance-subset image characteristics for the 25-stimulus characterization subset and its paired real references (the full release contains 85 Midjourney images). All stimuli were normalized to

600\times 600

px square format during curation. Despite degradation-oriented prompts (“grainy low-resolution CCTV footage, 1990s video compression”), Midjourney generations are sharper than real CCTV frames on this measure. The median Laplacian variance is 649 for Midjourney and 212 for real frames (Mann–Whitney

U=482

z=3.29

p=0.001

Prompt style	$N$	Male	Female	Unclear	Binomial $p$
Explicit occupation name	67	55 (82.1%)	11 (16.4%)	1	$3.6\times 10^{-8}$
Descriptive (role described)	67	44 (65.7%)	22 (32.8%)	1	$9.2\times 10^{-3}$
Overall	134	99 (73.9%)	33 (24.6%)	2

Table 4: Depicted gender in Midjourney generations under gender-neutral prompts (initial set without a specified gender;

N=134

generations across 67 occupations, one generation per occupation and prompt style). Two-sided exact binomial tests against

P(\text{male})=0.5

exclude gender-unclear generations.

Occupation (MJ renders female)	BLS detailed occupation	% women
Nurse	Registered nurses	87.3
Dental hygienist	Dental hygienists	95.0
Hairdresser	Hairdressers, hairstylists, and cosmetologists	92.0
Assistant	Secretaries and admin. assistants a	91.9
Interior designer	Interior designers	82.8
Teacher	Elementary and middle school teachers	79.2

Table 5: Occupations rendered female under gender-neutral occupation-name prompts are predominantly female-majority occupations in U.S. labor statistics. The table lists all 11 of 67 occupations for which Midjourney depicted a woman under occupation-name prompting, alongside the percent of employed women in the closest matching detailed occupation from the U.S. Bureau of Labor Statistics Current Population Survey (2025 annual averages, Table cpsaat11) [ 18 ] . Across all occupations, women are 47.1% of the employed. Seven of the eight occupations with a published share exceed this baseline. Newscaster is the exception at 41.1%.

Quantity	Value
Occupations tested	67
Same depicted gender under both prompt styles	52
Flipped male $\rightarrow$ female (descriptive)	13
Flipped female $\rightarrow$ male (descriptive)	2
Sign test (two-sided)	$p=0.007$

Table 6: Prompt-style ablation in the initial set of generations without a specified gender. Each of the 67 occupations was prompted twice. One prompt names the occupation (“portrait of a doctor”). One prompt describes the role without naming it (“someone who helps people in hospital”). Fifteen occupations changed depicted gender between prompt styles, and thirteen of the fifteen flips moved toward female under descriptive phrasing (two-sided sign test

p=0.007

Figure 1: Midjourney defaults to male across occupations, and descriptive prompts soften the default. Depicted gender for each of 67 occupations in the initial set of generations without a specified gender, under two gender-neutral prompt styles. One style names the occupation and the other describes the role without naming it. Rows are sorted by outcome. Occupations rendered female under occupation-name prompting cluster among female-majority occupations in U.S. labor statistics ( Table 5 ).

Measure	Median	Min	Max
Edited pixels (%)	14.3	1.3	53.9
Edit bounding box (% of image)	60.4	17.9	100.0
SSIM (source vs. edit)	0.788	0.469	0.988

Table 7: AI-edited subset edit-region statistics over the 25 characterized real–edited pairs (the full release contains 27 edited images). Edited-pixel percentage uses a per-pixel absolute-difference threshold of 25/255 after aligning resolutions; SSIM is computed globally.

Edit type	Pairs	Median edited pixels (%)
Person replaced with another person	9	12.7
Background replaced	6	23.2
Object inserted or replaced	5	9.8
Person replaced with an object or animal	4	26.3
Local attribute re-rendered	1	1.3
Total	25	14.3

Table 8: AI-edited subset edit-type taxonomy over the 25 characterized real–edited pairs. Each pair was coded manually into one category by inspecting the source photograph, the edited image and their pixel-difference map. Replacing one person with another person is the most common edit, and the median share of altered pixels varies by category.

Figure 2: Larger edit regions are associated with higher zero-shot classification accuracy. Each point is one partially manipulated image in the AI-edited subset (

N=25

); the x-axis gives the percent of pixels altered relative to the source photograph and the y-axis the mean zero-shot classification accuracy across three LLMs (GPT-4.1, Claude Opus, Gemini Pro). Edit-region size is positively associated with accuracy (Spearman

\rho=0.55

, permutation

p=0.005

Subject category	AI-generated videos
Physical activity	3
Street interviews	3
Protest and documentary	3
Public speaking	3
Social media	5
Virtual communication	3

Table 9: Video-subset subject-category coverage for the 20-stimulus characterization subset (the full release contains 56 AI videos; the generator split appears in Table 1 ).

Measure	Sora (AI, $n{=}20$ )	Real ( $n{=}20$ )
Duration, median [range] (s)	8.0 [5.7–10.0]	8.0 [6.6–8.5]
Frame rate (fps)	24, 30	24–60
Resolutions (distinct)	10 (528–1280 px wide)	2 ( $960{\times}540$ , $360{\times}360$ )
Audio track present	20/20	20/20

Table 10: Video-subset per-video technical characteristics for the characterization subset (measured with ffprobe ). Median durations are 8.0 s for both AI-generated videos and real references. AI-generated videos span a wider range of aspect ratios; real clips are either

960\times 540

360\times 360

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 3: Example AI-generated stimuli from each subset (top to bottom: Surveillance, Occupations, AI-edited, Video frames). All stimuli shown are AI-generated.

AI-Generated Image Detection

AI-generated image detection identifies synthetic or AI-edited images and develops methods that generalize across generators, domains, and image transformations.

See all 194 papers

TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images
Jun 25, 2026Jay Barot, Dan LinTransformer Image Forgery Localization
Vanderbilt University, Nashville TN, USA
Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations
Sep 16, 2026Shesh Narayan Gupta, Nik Bear BrownT2I Generation Demographic Bias in T2I Models
College of Engineering, Northeastern University, Boston, MA 02115, USA
Grounding and Explaining Visual Evidence for AI-Generated Image Detection in Human-Centric Scenes
Aug 3, 2026Kun Guo, Yuzhou Yang, Haoyue Wang +3Visual Grounding AI-Generated Image Detection
College of Computer Science and Artificial Intelligence, Fudan University · NVIDIA

Jun 25, 2026J/K move · Enter open · S save

TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images

Jay Barot, Dan Lin

Vanderbilt University, Nashville TN, USA

Transformer Image Forgery Localization AI-Generated Image Detection

Open paper AskPDF arXiv

AI generated images are proliferating across the Internet. While some are used for entertainment, others are weaponized for fraud and social engineering attacks on social media users. Existing detectors overfit to generators seen during training, treat detection as opaque binary classification, or rely on costly Large Language Models (LLMs) to explain their outputs. In this paper, we present TruEye, a novel model for fine grained detection and localization of AI manipulated or AI generated humans and scenes. Unlike conventional detectors that assign a single authenticity label, TruEye is the first to distinguish among five compositional categories of synthetic content, including the most challenging case in which a real human is composited into a real scene where they were never physically present. At its core is a mask conditioned dual stream transformer that separates human and scene tokens while preserving patch level spatial correspondence. Specialized reasoning within each stream and region gated cross attention enforce semantic coherence between subject and background, while token level supervision and global compositional classification yield robust, interpretable predictions without invoking an LLM. By restricting intra stream attention to semantically coherent tokens, TruEye also runs over

100\times

faster than LLM based competitors. Experiments on 6 datasets and our newly curated FineSyn dataset, show that TruEye surpasses state of the art detectors with higher accuracy, faster inference, and stronger generalization to unseen AI generated or manipulated images.

Abstract

AI-Generated Image Detection

Explore similar work

TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images

Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations

Grounding and Explaining Visual Evidence for AI-Generated Image Detection in Human-Centric Scenes