70 citations · 341 across the 32 of their papers we have counts for
22 papers · 1 filter
Semantic-Aware Mixup for Domain Generalization
Chengchao Xu, Xinmei Tian
Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising appr…
Self-Supervision Can Be a Good Few-Shot Learner
Yuning Lu, Liangjian Wen, Jianzhuang Liu +2
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic p…
Bi-Calibration Networks for Weakly-Supervised Video Representation Learning
Fuchen Long, Ting Yao, Zhaofan Qiu +3
The leverage of large volumes of web videos paired with the searched queries or surrounding texts (e.g., title) offers an economic and extensible alternative to supervised video re…
Toward Real-world Single Image Deraining: A New Benchmark and Beyond
Wei Li, Qiming Zhang, Jing Zhang +3
Single image deraining (SID) in real scenarios attracts increasing attention in recent years. Due to the difficulty in obtaining real-world rainy/clean image pairs, previous real d…
Prompt Distribution Learning
Yuning Lu, Jianzhuang Liu, Yonggang Zhang +2
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias pr…
A Style and Semantic Memory Mechanism for Domain Generalization
Yang Chen, Yu Wang, Yingwei Pan +3
Mainstream state-of-the-art domain generalization algorithms tend to prioritize the assumption on semantic invariance across domains. Meanwhile, the inherent intra-domain style inv…
Transferrable Contrastive Learning for Visual Domain Adaptation
Yang Chen, Yingwei Pan, Yu Wang +3
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorpo…
Domain-Class Correlation Decomposition for Generalizable Person Re-Identification
Kaiwen Yang, Xinmei Tian
Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to…
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
Zhen Huang, Xu Shen, Xinmei Tian +3
Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely…
Learning to Localize Actions from Moments
Fuchen Long, Ting Yao, Zhaofan Qiu +3
With the knowledge of action moments (i.e., trimmed video clips that each contains an action instance), humans could routinely localize an action temporally in an untrimmed video.…
Transform-Invariant Convolutional Neural Networks for Image Classification and Search
Xu Shen, Xinmei Tian, Anfeng He +2
Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invaria…
Patch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
Xu Shen, Xinmei Tian, Shaoyan Sun +1
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations…
Continuous Dropout
Xu Shen, Xinmei Tian, Tongliang Liu +2
Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detect…
Quantization Networks
Jiwei Yang, Xu Shen, Jun Xing +5
Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit q…
Gaussian Temporal Awareness Networks for Action Localization
Fuchen Long, Ting Yao, Zhaofan Qiu +3
Temporally localizing actions in a video is a fundamental challenge in video understanding. Most existing approaches have often drawn inspiration from image object detection and ex…
Mocycle-GAN: Unpaired Video-to-Video Translation
Yang Chen, Yingwei Pan, Ting Yao +2
Unsupervised image-to-image translation is the task of translating an image from one domain to another in the absence of any paired training examples and tends to be more applicabl…
Learning Spatio-Temporal Representation with Local and Global Diffusion
Zhaofan Qiu, Ting Yao, Chong-Wah Ngo +2
Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for visual recognition problems. Nevertheless, the convolutional filters in these networks are…
Camera Lens Super-Resolution
Chang Chen, Zhiwei Xiong, Xinmei Tian +2
Existing methods for single image super-resolution (SR) are typically evaluated with synthetic degradation models such as bicubic or Gaussian downsampling. In this paper, we invest…
Exploring Object Relation in Mean Teacher for Cross-Domain Detection
Qi Cai, Yingwei Pan, Chong-Wah Ngo +3
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However…
Towards a Better Match in Siamese Network Based Visual Object Tracker
Anfeng He, Chong Luo, Xinmei Tian +1
Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework st…
Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition
Xikun Zhang, Chang Xu, Xinmei Tian +1
This paper investigates body bones from skeleton data for skeleton based action recognition. Body joints, as the direct result of mature pose estimation technologies, are always th…
A Twofold Siamese Network for Real-Time Object Tracking
Anfeng He, Chong Luo, Xinmei Tian +1
Observing that Semantic features learned in an image classification task and Appearance features learned in a similarity matching task complement each other, we build a twofold Sia…