290 citations · 1k across the 35 of their papers we have counts for
14 papers · 1 filter
Delving Deeper into Data Scaling in Masked Image Modeling
Cheng-Ze Lu, Xiaojie Jin, Qibin Hou +3
Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the…
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang +3
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This…
Privileged Prior Information Distillation for Image Matting
Cheng Lyu, Jiake Xie, Bo Xu +6
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are seman…
Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition
Qibin Hou, Cheng-Ze Lu, Ming-Ming Cheng +1
This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features.…
3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching
Runyu Mao, Chen Bai, Yatong An +2
We tackle the essential task of finding dense visual correspondences between a pair of images. This is a challenging problem due to various factors such as poor texture, repetitive…
Contrastive Masked Autoencoders are Stronger Vision Learners
Zhicheng Huang, Xiaojie Jin, Chengze Lu +5
Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty…
Situational Perception Guided Image Matting
Bo Xu, Jiake Xie, Han Huang +4
Most automatic matting methods try to separate the salient foreground from the background. However, the insufficient quantity and subjective bias of the current existing matting da…
Safe Self-Refinement for Transformer-based Domain Adaptation
Tao Sun, Cheng Lu, Tianshuo Zhang +1
Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a…
Semantic Distillation Guided Salient Object Detection
Bo Xu, Guanze Liu, Han Huang +2
Most existing CNN-based salient object detection methods can identify local segmentation details like hair and animal fur, but often misinterpret the real saliency due to the lack…
Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation
Changwei Xu, Jianfei Yang, Haoran Tang +3
Unsupervised Domain Adaptation (UDA), a branch of transfer learning where labels for target samples are unavailable, has been widely researched and developed in recent years with t…
Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation
Ziwen Li, Bo Xu, Han Huang +2
Several video-based 3D pose and shape estimation algorithms have been proposed to resolve the temporal inconsistency of single-image-based methods. However it still remains challen…
Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction
Bo Xu, Han Huang, Cheng Lu +2
Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM…
DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild
Xingxun Jiang, Yuan Zong, Wenming Zheng +4
Recently, facial expression recognition (FER) in the wild has gained a lot of researchers' attention because it is a valuable topic to enable the FER techniques to move from the la…
Discriminative Multi-modality Speech Recognition
Bo Xu, Cheng Lu, Yandong Guo +1
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly dete…