Leveraging Panoptic Scene Graph for Evaluating Fine-Grained Text-to-Image Generation
Xueqing Deng, Linjie Yang, Qihang Yu, Chenglin Yang, Liang-Chieh Chen
摘要
A photo of depicting a busy urban street during daytime, with modern buildings, vehicles, and trees lining the sidewalks. A pedestrian crossing in the foreground is occupied by two black luxury sedans. One car is closer to the crossing line. While two city buses in vibrant colors move through the street. Several other vehicles, including a red sports car, add to the lively traffic. A traffic light and street signs regulate movement, while trees provide greenery and cast shadows on the pavement. The glass-paneled buildings reflect sunlight, enhancing the modern cityscape. The scene captures a dynamic blend of transportation, architecture, and urban life.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper21
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 被引用 18,833 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li 等NeurIPS 2022 · 被引用 8,965 次
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 被引用 6,549 次
相关 Paper
- ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action ModelZhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen 等EMNLP 2025 · 被引用 6 次
- Running into Traffic: Investigating External Human-Machine Interfaces for Automated Vehicle-Runner InteractionAmmar Al-Taie, Thomas Goodge, Shaun Alexander Macdonald, Ian Oakley 等CHI 2026 · 被引用 3 次
- PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory PredictionAmir Rasouli, Iuliia Kotseruba, Toni Kunic, John K. TsotsosICCV 2019 · 被引用 411 次
- Interaction Effects of Pedestrian Behavior, Smartphone Distraction and External Communication of Automated Vehicles on Crossing and Gaze BehaviorMirjam Lanzer, Ina Koniakowsky, Mark Colley, Martin BaumannCHI 2023 · 被引用 29 次
- Action-Slot: Visual Action-Centric Representations for Multi-Label Atomic Activity Recognition in Traffic ScenesChi-Hsi Kung, Shu-Wei Lu, Yi-Hsuan Tsai, Yi-Ting ChenCVPR 2024
