211 citations · 609 across the 13 of their papers we have counts for
14 papers
NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
Chenfei Wu, Jian Liang, Xiaowei Hu +6
In this paper, we present NUWA-Infinity, a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or lo…
GLIPv2: Unifying Localization and Vision-Language Understanding
Haotian Zhang, Pengchuan Zhang, Xiaowei Hu +7
We present GLIPv2, a grounded VL understanding model, that serves both localization tasks (e.g., object detection, instance segmentation) and Vision-Language (VL) understanding tas…
GIT: A Generative Image-to-text Transformer for Vision and Language
Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu +6
In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generati…
K-LITE: Learning Transferable Visual Models with External Knowledge
Sheng Shen, Chunyuan Li, Xiaowei Hu +11
The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. Thi…
Injecting Semantic Concepts into End-to-End Image Captioning
Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu +5
Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Re…
UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Jianfeng Wang, Xiaowei Hu, Zhe Gan +5
In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concat…
Scaling Up Vision-Language Pre-training for Image Captioning
Xiaowei Hu, Zhe Gan, Jianfeng Wang +4
In recent years, we have witnessed significant performance boost in the image captioning task based on vision-language pre-training (VLP). Scale is believed to be an important fact…
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
Zhengyuan Yang, Zhe Gan, Jianfeng Wang +5
We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text d…
An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
Zhengyuan Yang, Zhe Gan, Jianfeng Wang +4
Knowledge-based visual question answering (VQA) involves answering questions that require external knowledge not present in the image. Existing methods first retrieve knowledge fro…
Compressing Visual-linguistic Model via Knowledge Distillation
Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu +3
Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to ef…
VinVL: Revisiting Visual Representations in Vision-Language Models
Pengchuan Zhang, Xiujun Li, Xiaowei Hu +5
This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric re…
MiniVLM: A Smaller and Faster Vision-Language Model
Jianfeng Wang, Xiaowei Hu, Pengchuan Zhang +5
Recent vision-language (VL) studies have shown remarkable progress by learning generic representations from massive image-text pairs with transformer models and then fine-tuning on…
VIVO: Visual Vocabulary Pre-Training for Novel Object Captioning
Xiaowei Hu, Xi Yin, Kevin Lin +4
It is highly desirable yet challenging to generate image captions that can describe novel objects which are unseen in caption-labeled training data, a capability that is evaluated…
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Xiujun Li, Xi Yin, Chunyuan Li +9
Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatena…