PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Abstract
Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models. https://github.com/facebookresearch/perception_models
Cite
@article{arxiv.2504.13180,
title = {PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding},
author = {Jang Hyun Cho and Andrea Madotto and Effrosyni Mavroudi and Triantafyllos Afouras and Tushar Nagarajan and Muhammad Maaz and Yale Song and Tengyu Ma and Shuming Hu and Suyog Jain and Miguel Martin and Huiyu Wang and Hanoona Rasheed and Peize Sun and Po-Yao Huang and Daniel Bolya and Nikhila Ravi and Shashank Jain and Tammy Stark and Shane Moon and Babak Damavandi and Vivian Lee and Andrew Westbury and Salman Khan and Philipp Krähenbühl and Piotr Dollár and Lorenzo Torresani and Kristen Grauman and Christoph Feichtenhofer},
journal= {arXiv preprint arXiv:2504.13180},
year = {2025}
}
Comments
Technical Report