|国家预印本平台
首页|PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

来源:Arxiv_logoArxiv
英文摘要

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.

Jang Hyun Cho、Andrea Madotto、Effrosyni Mavroudi、Triantafyllos Afouras、Tushar Nagarajan、Muhammad Maaz、Yale Song、Tengyu Ma、Shuming Hu、Suyog Jain、Miguel Martin、Huiyu Wang、Hanoona Rasheed、Peize Sun、Po-Yao Huang、Daniel Bolya、Nikhila Ravi、Shashank Jain、Tammy Stark、Shane Moon、Babak Damavandi、Vivian Lee、Andrew Westbury、Salman Khan、Philipp Kr?henbühl、Piotr Dollár、Lorenzo Torresani、Kristen Grauman、Christoph Feichtenhofer

计算技术、计算机技术

Jang Hyun Cho,Andrea Madotto,Effrosyni Mavroudi,Triantafyllos Afouras,Tushar Nagarajan,Muhammad Maaz,Yale Song,Tengyu Ma,Shuming Hu,Suyog Jain,Miguel Martin,Huiyu Wang,Hanoona Rasheed,Peize Sun,Po-Yao Huang,Daniel Bolya,Nikhila Ravi,Shashank Jain,Tammy Stark,Shane Moon,Babak Damavandi,Vivian Lee,Andrew Westbury,Salman Khan,Philipp Kr?henbühl,Piotr Dollár,Lorenzo Torresani,Kristen Grauman,Christoph Feichtenhofer.PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding[EB/OL].(2025-04-17)[2025-05-05].https://arxiv.org/abs/2504.13180.点此复制

评论