915 citations · 3.2k across the 107 of their papers we have counts for
36 papers · 1 filter
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses
Chen Ju, Peisen Zhao, Ya Zhang +2
Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the…
UnrealPerson: An Adaptive Pipeline towards Costless Person Re-identification
Tianyu Zhang, Lingxi Xie, Longhui Wei +4
The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a no…
Privileged Knowledge Distillation for Online Action Detection
Peisen Zhao, Lingxi Xie, Ya Zhang +2
Online Action Detection (OAD) in videos is proposed as a per-frame labeling task to address the real-time prediction tasks that can only obtain the previous and current video frame…
ESAD: End-to-end Deep Semi-supervised Anomaly Detection
Chaoqin Huang, Fei Ye, Peisen Zhao +3
This paper explores semi-supervised anomaly detection, a more practical setting for anomaly detection where a small additional set of labeled samples are provided. We propose a new…
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
Haohang Xu, Xiaopeng Zhang, Hao Li +3
Self-supervised learning based on instance discrimination has shown remarkable progress. In particular, contrastive learning, which regards each image as well as its augmentations…
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Xinyue Huo, Lingxi Xie, Longhui Wei +6
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial…
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Longhui Wei, Lingxi Xie, Jianzhong He +5
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported h…
Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs
Lin Liu, Shanxin Yuan, Jianzhuang Liu +3
Moire artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera. Existing deep lear…
Omni-GAN: On the Secrets of cGANs and Beyond
Peng Zhou, Lingxi Xie, Bingbing Ni +2
The conditional generative adversarial network (cGAN) is a powerful tool of generating high-quality images, but existing approaches mostly suffer unsatisfying performance or the ri…
Center-wise Local Image Mixture For Contrastive Representation Learning
Hao Li, Xiaopeng Zhang, Hongkai Xiong
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the se…
One-bit Supervision for Image Classification
Hengtong Hu, Lingxi Xie, Zewei Du +2
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accu…
Reinforced Axial Refinement Network for Monocular 3D Object Detection
Lijie Liu, Chufan Wu, Jiwen Lu +3
Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. This is an ill-posed problem with a major difficulty lying in the inf…
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Lingxi Xie, Xin Chen, Kaifeng Bi +8
Neural architecture search (NAS) has attracted increasing attentions in both academia and industry. In the early age, researchers mostly applied individual search methods which sam…
Video Super-Resolution with Recurrent Structure-Detail Network
Takashi Isobe, Xu Jia, Shuhang Gu +3
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the…
Corner Proposal Network for Anchor-free, Two-stage Object Detection
Kaiwen Duan, Lingxi Xie, Honggang Qi +3
The goal of object detection is to determine the class and location of objects in an image. This paper proposes a novel anchor-free, two-stage framework which first extracts a numb…
Video Super-resolution with Temporal Group Attention
Takashi Isobe, Songjiang Li, Xu Jia +6
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we pro…
Social Adaptive Module for Weakly-supervised Group Activity Recognition
Rui Yan, Lingxi Xie, Jinhui Tang +2
This paper presents a new task named weakly-supervised group activity recognition (GAR) which differs from conventional GAR tasks in that only video-level labels are available, yet…
Wavelet-Based Dual-Branch Network for Image Demoireing
Lin Liu, Jianzhuang Liu, Shanxin Yuan +4
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-b…
Universal-to-Specific Framework for Complex Action Recognition
Peisen Zhao, Lingxi Xie, Ya Zhang +1
Video-based action recognition has recently attracted much attention in the field of computer vision. To solve more complex recognition tasks, it has become necessary to distinguis…
GOLD-NAS: Gradual, One-Level, Differentiable
Kaifeng Bi, Lingxi Xie, Xin Chen +2
There has been a large literature of neural architecture search, but most existing work made use of heuristic rules that largely constrained the search flexibility. In this paper,…
Distilling Object Detectors with Task Adaptive Regularization
Ruoyu Sun, Fuhui Tang, Xiaopeng Zhang +2
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a…
Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks
Peng Zhou, Lingxi Xie, Xiaopeng Zhang +2
Conditional Generative Adversarial Networks (cGAN) were designed to generate images based on the provided conditions, \eg, class-level distributions. However, existing methods have…
ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised Medical Image Segmentation
Xinyue Huo, Lingxi Xie, Jianzhong He +2
In medical image analysis, semi-supervised learning is an effective method to extract knowledge from a small amount of labeled data and a large amount of unlabeled data. This paper…
Unsupervised Person Re-identification via Softened Similarity Learning
Yutian Lin, Lingxi Xie, Yu Wu +2
Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and…