{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:18:01Z","timestamp":1778051881627,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00398","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4087-4096","source":"Crossref","is-referenced-by-count":0,"title":["HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models"],"prefix":"10.1109","author":[{"given":"Anubhooti","family":"Jain","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Jodhpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayank","family":"Vatsa","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Jodhpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richa","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Jodhpur,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00608"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref3","article-title":"Announcing black forest labs","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB54206.2022.10007961"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_12"},{"key":"ref6","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen"},{"key":"ref7","article-title":"Evaluating text-to-image generative models: An empirical study on human image synthesis","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01162"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2024.3361657"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00610"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3051842"},{"key":"ref15","article-title":"Evaluating numerical reasoning in text-to-image models","author":"Kajic","year":"2024","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00538"},{"key":"ref17","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML PMLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref20","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref22","article-title":"Evaluating and predicting distorted human body parts for generated images","author":"Ma","year":"2025","journal-title":"CoRR"},{"key":"ref23","article-title":"Investigating and improving counter-stereotypical action relation in text-to-image diffusion models","author":"Malakouti","year":"2025","journal-title":"CoRR"},{"key":"ref24","article-title":"MidJourneyV6","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_4"},{"key":"ref27","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML PMLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02658"},{"key":"ref29","article-title":"Evaluating the generation of spatial relations in text and image generative models","author":"Sim","year":"2024","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01608"},{"key":"ref31","article-title":"Gender bias evaluation in text-to-image generation: A survey","author":"Wu","year":"2024","journal-title":"CoRR"},{"key":"ref32","article-title":"Grok","year":"2025"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492264.pdf?arnumber=11492264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:31:56Z","timestamp":1778049116000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00398","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}