195 citations · 479 across the 26 of their papers we have counts for
19 papers · 1 filter
Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation
Shiqi Sun, Shancheng Fang, Qian He +1
Diffusion models are able to generate photorealistic images in arbitrary scenes. However, when applying diffusion models to image translation, there exists a trade-off between main…
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning
Yatai Ji, Rongcheng Tu, Jie Jiang +6
Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspi…
Egocentric Video-Language Pretraining @ Ego4D Challenge 2022
Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan +13
In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for four Ego4D challenge tasks, including Natural Language Query (NLQ), Moment Q…
Egocentric Video-Language Pretraining @ EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2022
Kevin Qinghong Lin, Alex Jinpeng Wang, Rui Yan +9
In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for the EPIC-KITCHENS-100 Multi-Instance Retrieval (MIR) challenge. Especially,…
Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization
Mengyin Liu, Chao Zhu, Hongyu Gao +4
With the prosperity of e-commerce industry, various modalities, e.g., vision and language, are utilized to describe product items. It is an enormous challenge to understand such di…
Towards Generalizable Person Re-identification with a Bi-stream Generative Model
Xin Xu, Wei Liu, Zheng Wang +2
Generalizable person re-identification (re-ID) has attracted growing attention due to its powerful adaptation capability in the unseen data domain. However, existing solutions ofte…
Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning
Li Yang, Yan Xu, Chunfeng Yuan +3
Visual grounding is a task to locate the target indicated by a natural language expression. Existing methods extend the generic object detection framework to this problem. They bas…
Egocentric Video-Language Pretraining
Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan +13
Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention…
XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation
Wei Liu, Fangyue Liu, Fei Ding +2
Generating a new font library is a very labor-intensive and time-consuming job for glyph-rich scripts. Few-shot font generation is thus required, as it requires only a few glyph re…
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
Zihao Wang, Wei Liu, Qian He +2
Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper,…
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing
Bingchuan Li, Shaofei Cai, Wei Liu +4
The semantic controllability of StyleGAN is enhanced by unremitting research. Although the existing weak supervision methods work well in manipulating the style codes along one att…
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
Qiming Zhang, Jing Zhang, Wei Liu +1
Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance sin…
Context-Gated Convolution
Xudong Lin, Lin Ma, Wei Liu +1
As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in…
Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Prediction
Xiangbo Shu, Liyan Zhang, Guo-Jun Qi +2
Human motion prediction aims to generate future motions based on the observed human motions. Witnessing the success of Recurrent Neural Networks (RNN) in modeling the sequential da…
Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
Yipeng Sun, Jiaming Liu, Wei Liu +3
Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of trainin…
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables
Yan Xu, Baoyuan Wu, Fumin Shen +4
In this work, we study the robustness of a CNN+RNN based image captioning system being subjected to adversarial noises. We propose to fool an image captioning system to generate so…
Spatio-temporal Video Re-localization by Warp LSTM
Yang Feng, Lin Ma, Wei Liu +1
The need for efficiently finding the video content a user wants is increasing because of the erupting of user-generated videos on the Web. Existing keyword-based or content-based v…
Image Deformation Meta-Networks for One-Shot Learning
Zitian Chen, Yanwei Fu, Yu-Xiong Wang +3
Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed in…
Video De-fencing
Yadong Mu, Wei Liu, Shuicheng Yan
This paper describes and provides an initial solution to a novel video editing task, i.e., video de-fencing. It targets automatic restoration of the video clips that are corrupted…