1

GLIPv2: Unifying Localization and Vision-Language Understanding
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tasks (e.g., VQA, image captioning).
Haotian Zhang, Pengchuan Zhang, Xiaowei Hu, Yen-Chun Chen, Liunian Harold Li, Xiyang Dai, Lijuan Wang, Lu Yuan, Jenq-Neng Hwang, Jianfeng Gao
PDF Cite Code Project
GLIP: Grounded Language-Image Pre-training
This paper presents a grounded language-image pre-training (GLIP) model for learning object-level, language-aware, and semantic-rich visual representations. GLIP unifies object detection and phrase grounding for pre-training.
Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, Kai-Wei Chang, Jianfeng Gao
PDF Cite Code Project
Exploit the connectivity: Multi-object tracking with trackletnet
In this paper, we propose an innovative and effective tracking method called TrackletNet Tracker (TNT) that combines temporal and appearance information together as a unified framework.
Gaoang Wang, Yizhou Wang, Haotian Zhang, Renshu Gu, Jenq-Neng Hwang
PDF Cite Project
Eye in the sky: Drone-based object tracking and 3D localization
In this paper, a drone-based multi-object tracking and 3D localization scheme is proposed based on the deep learning based object detection.
Haotian Zhang, Gaoang Wang, Zhichao Lei, Jenq-Neng Hwang
PDF Cite Project