Xiaoou Tang
YOU?
Author Swipe
View article: From human herpes virus‐6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID
From human herpes virus‐6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID Open
Inflammation and autoimmune responses contribute to the pathophysiology of Long COVID, and its affective and chronic fatigue syndrome symptoms, labeled “the physio‐affective phenome.” To investigate whether Long COVID and its physio‐affect…
View article: From HHV-6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID.
From HHV-6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID. Open
Background: Inflammation and autoimmune responses contribute to the pathophysiology of Long COVID, and its affective and chronic fatigue syndrome (CFS) symptoms, labeled "the physio-affective phenome." Objectives: To investigate whether Lo…
View article: From HHV-6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID
From HHV-6 reactivation to autoimmune reactivity against tight junctions and neuronal antigens, to inflammation, depression, and chronic fatigue syndrome due to Long COVID Open
Background Inflammation and autoimmune responses contribute to the pathophysiology of Long COVID, and its affective and chronic fatigue syndrome (CFS) symptoms, labeled “the physio-affective phenome.” Objectives To investigate whether Long…
View article: Towards an Intelligent Algorithm for Profile Authentication and Identification
Towards an Intelligent Algorithm for Profile Authentication and Identification Open
In the context digital transformation, the necessity for secure and efficient virtual identity verification has become paramount. Traditional methods often fail to balance security, speed, and usability, leaving gaps in user authentication…
View article: Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE Open
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language understanding evaluation (GLUE) benchmark, containing eight…
View article: Path-Restore: Learning Network Path Selection for Image Restoration
Path-Restore: Learning Network Path Selection for Image Restoration Open
Very deep Convolutional Neural Networks (CNNs) have greatly improved the performance on various image restoration tasks. However, this comes at a price of increasing computational burden, hence limiting their practical usages. We observe t…
View article: InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs
InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs Open
Although Generative Adversarial Networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a random code to a photo-realistic image. In t…
View article: Interpreting the Latent Space of GANs for Semantic Face Editing
Interpreting the Latent Space of GANs for Semantic Face Editing Open
Despite the recent advance of Generative Adversarial Networks (GANs) in high-fidelity image synthesis, there lacks enough understanding of how GANs are able to map a latent code sampled from a random distribution to a photo-realistic image…
View article: Switchable Whitening for Deep Representation Learning
Switchable Whitening for Deep Representation Learning Open
Normalization methods are essential components in convolutional neural networks (CNNs). They either standardize or whiten data using statistics estimated in predefined sets of pixels. Unlike existing works that design normalization techniq…
View article: A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization
A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization Open
Over four decades, the majority addresses the problem of optical flow estimation using variational methods. With the advance of machine learning, some recent works have attempted to address the problem using convolutional neural network (C…
View article: DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images Open
Understanding fashion images has been advanced by benchmarks with rich annotations such as DeepFashion, whose labels include clothing categories, landmarks, and consumer-commercial image pairs. However, DeepFashion has nonnegligible issues…
View article: Deep Network Interpolation for Continuous Imagery Effect Transition
Deep Network Interpolation for Continuous Imagery Effect Transition Open
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect. However, the large variety of user flavors motivates the possibility of continuous transition among diffe…
View article: Temporal Segment Networks for Action Recognition in Videos
Temporal Segment Networks for Action Recognition in Videos Open
We present a general and flexible video-level framework for learning action models in videos. This method, called temporal segment network (TSN), aims to model long-range temporal structure with a new segment-based sampling and aggregation…
View article: Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net Open
Convolutional neural networks (CNNs) have achieved great successes in many computer vision problems. Unlike existing works that designed CNN architectures to improve performance on a single task of a single domain and not generalizable, we…
View article: Deep Imbalanced Learning for Face Recognition and Attribute Prediction
Deep Imbalanced Learning for Face Recognition and Attribute Prediction Open
Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep learni…
View article: LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation Open
FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper we present an alternative network that outperforms FlowNet2 on …
View article: Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
Mix-and-Match Tuning for Self-Supervised Semantic Segmentation Open
Deep convolutional networks for semantic image segmentation typically require large-scale labeled data, e.g., ImageNet and MS COCO, for network pre-training. To reduce annotation efforts, self-supervised semantic segmentation is recently p…
View article: Spatial as Deep: Spatial CNN for Traffic Scene Understanding
Spatial as Deep: Spatial CNN for Traffic Scene Understanding Open
Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pix…
View article: Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping Open
Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is…
View article: Learning to Disambiguate by Asking Discriminative Questions
Learning to Disambiguate by Asking Discriminative Questions Open
The ability to ask questions is a powerful tool to gather information in order to learn about the world and resolve ambiguities. In this paper, we explore a novel problem of generating discriminative questions to help disambiguate visual i…
View article: Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks
Unconstrained Fashion Landmark Detection via Hierarchical Recurrent Transformer Networks Open
Fashion landmarks are functional key points defined on clothes, such as corners of neckline, hemline, and cuff. They have been recently introduced as an effective visual representation for fashion image understanding. However, detecting fa…
View article: Recurrent Scale Approximation for Object Detection in CNN
Recurrent Scale Approximation for Object Detection in CNN Open
Since convolutional neural network (CNN) lacks an inherent mechanism to handle large scale variations, we always need to compute feature maps multiple times for multi-scale object detection, which has the bottleneck of computational cost i…
View article: Aesthetic-Driven Image Enhancement by Adversarial Learning
Aesthetic-Driven Image Enhancement by Adversarial Learning Open
We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive annota…
View article: Temporal Segment Networks for Action Recognition in Videos
Temporal Segment Networks for Action Recognition in Videos Open
Deep convolutional networks have achieved great success for image recognition. However, for action recognition in videos, their advantage over traditional methods is not so evident. We present a general and flexible video-level framework f…
View article: Residual Attention Network for Image Classification
Residual Attention Network for Image Classification Open
In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Atten…
View article: Temporal Action Detection with Structured Segment Networks
Temporal Action Detection with Structured Segment Networks Open
Detecting actions in untrimmed videos is an important yet challenging task. In this paper, we present the structured segment network (SSN), a novel framework which models the temporal structure of each action instance via a structured temp…
View article: ViP-CNN: Visual Phrase Guided Convolutional Neural Network
ViP-CNN: Visual Phrase Guided Convolutional Neural Network Open
As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers' attention because of its descriptive power and clear structure. It detects the objects and capture…
View article: Video Frame Synthesis using Deep Voxel Flow
Video Frame Synthesis using Deep Voxel Flow Open
We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be …
View article: Faceness-Net: Face Detection through Deep Facial Part Responses
Faceness-Net: Face Detection through Deep Facial Part Responses Open
We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face ima…