As an important step towards visual reasoning, visual grounding (e.g., phrase localization, referring expression comprehension/segmentation) has been widely explored Previous approaches to referring expression comprehension (REC) or segmentation (RES) either suffer from limited performance, due to a two-stage setup, or require the designing of complex task-specific one-stage architectures. In this paper, we propose a simple one-stage multi-task framework for visual grounding tasks. Specifically, we leverage a transformer architecture, where two modalities are fused in a visual-lingual encoder. In the decoder, the model learns to generate contextualized lingual queries which are then decoded and used to directly regress the bounding box and produce a segmentation mask for the corresponding referred regions. With this simple but highly contextualized model, we outperform state-of-the-arts methods by a large margin on both REC and RES tasks. We also show that a simple pre-training schedule (on an external dataset) further improves the performance. Extensive experiments and ablations illustrate that our model benefits greatly from contextualized information and multi-task training.
Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（中国科学院计算技术研究所智能信息处理重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）；Peng Cheng Laboratory（鹏城实验室）
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension
School of Computer Science and Technology, Xi’an Jiaotong University（西安交通大学计算机科学与技术学院）；Institute of Big Data, Fudan University（复旦大学大数据学院）；Shanghai University of Finance and Economics（上海财经大学）；Nanyang Technological University（南洋理工大学）
University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；University of Science and Technology of China（中国科学技术大学）；Nanjing University of Science and Technology（南京理工大学）；Huawei Cloud & AI（华为云与人工智能部门）
The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Southern University of Science and Technology（南方科技大学）
AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring
University of Science and Technology of China（中国科学技术大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Hefei University of Technology（合肥工业大学）
MIMO: A medical vision language model with visual referring multimodal input and pixel grounding multimodal output
School of Software & Microelectronics, Peking University（软件与微电子学院，北京大学）；School of Computer Science, Peking University（计算机学院，北京大学）；National Engineering Research Center for Software Engineering, Peking University（软件工程国家工程研究中心，北京大学）；Peking University Sixth Hospital（北京大学第六医院）；Augusta University（奥古斯塔大学）；Peking University First Hospital（北京大学第一医院）
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）
A-PAIR: A Benchmark and Identity-Consistent Grounding Framework for Air-Ground Cross-View Referring Person Detection
School of Automation, Southeast University（东南大学自动化学院）；Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Sports Training, Tianjin University of Sport（天津体育学院运动训练学院）；Tianjin University（天津大学）；National University of Defense Technology（国防科技大学）
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models
College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Centre for Perceptual and Interactive Intelligence, the Chinese University of Hong Kong（香港中文大学感知与交互智能中心）；Department of Electronic Engineering, the Chinese University of Hong Kong（香港中文大学电子工程系）
