32 Result(s)
within
Conference Paper
Ziwei **a
Computer Science
Machine Learning
-
Chapter and Conference Paper
HPAN: A Hybrid Pose Attention Network for Person Re-Identification
To address the difficulty in expressing the correlation between different local features extracted by the current person re-identification feature extraction methods, and the challenge of effectively integrati...
-
Chapter and Conference Paper
Preserving Potential Neighbors for Low-Degree Nodes via Reweighting in Link Prediction
Link prediction is an important task for graph data. Methods based on graph neural networks achieve high accuracy by simultaneously modeling the node attributes and structure of the observed graph. However, th...
-
Chapter and Conference Paper
Federated Conversational Recommender Systems
Conversational Recommender Systems (CRSs) have become increasingly popular as a powerful tool for providing personalized recommendation experiences. By directly engaging with users in a conversational manner ...
-
Chapter and Conference Paper
Countering Mainstream Bias via End-to-End Adaptive Local Learning
Collaborative filtering (CF) based recommendations suffer from mainstream bias – where mainstream users are favored over niche users, leading to poor recommendation quality for many long-tail users. In this pa...
-
Chapter and Conference Paper
SALSA: Salience-Based Switching Attack for Adversarial Perturbations in Fake News Detection Models
Despite advances in fake news detection algorithms, recent research reveals that machine learning-based fake news detection models are still vulnerable to carefully crafted adversarial attacks. In this landsca...
-
Chapter and Conference Paper
Make-A-Volume: Leveraging Latent Diffusion Models for Cross-Modality 3D Brain MRI Synthesis
Cross-modality medical image synthesis is a critical topic and has the potential to facilitate numerous applications in the medical imaging field. Despite recent successes in deep-learning-based generative mod...
-
Chapter and Conference Paper
Evolution of Filter Bubbles and Polarization in News Recommendation
Recent work in news recommendation has demonstrated that recommenders can over-expose users to articles that support their pre-existing opinions. However, most existing work focuses on a static setting or over...
-
Chapter and Conference Paper
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
Deep learning-based single image super-resolution (SISR) approaches have drawn much attention and achieved remarkable success on modern advanced GPUs. However, most state-of-the-art methods require a huge numb...
-
Chapter and Conference Paper
Mining Negative Temporal Contexts for False Positive Suppression in Real-Time Ultrasound Lesion Detection
During ultrasonic scanning processes, real-time lesion detection can assist radiologists in accurate cancer diagnosis. However, this essential task remains challenging and underexplored. General-purpose real-t...
-
Chapter and Conference Paper
Learned Bloom Filter for Multi-key Membership Testing
Multi-key membership testing refers to checking whether a queried element exists in a given set of multi-key elements, which is a fundamental operation for computing systems and networking applications such as...
-
Chapter and Conference Paper
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 Challenge: Report
Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this prob...
-
Chapter and Conference Paper
Few-Shot Link Prediction for Event-Based Social Networks via Meta-learning
With the thriving of social network analysis, large efforts have been made on link prediction for event-based social networks (EBSNs). Unfortunately, since society is evolving with constantly emerging social e...
-
Chapter and Conference Paper
Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-Aware Connection Classifier
Automatic labeling of coronary arteries is an essential task in the practical diagnosis process of cardiovascular diseases. For experienced radiologists, the anatomically predetermined connections are importan...
-
Chapter and Conference Paper
Free Lunch for Surgical Video Understanding by Distilling Self-supervisions
Self-supervised learning has witnessed great progress in vision and NLP; recently, it also attracted much attention to various medical imaging modalities such as X-ray, CT, and MRI. Existing methods mostly foc...
-
Chapter and Conference Paper
StyleSwap: Style-Based Generator Empowers Robust Face Swap**
Numerous attempts have been made to the task of person-agnostic face swap** given its wide applications. While existing methods mostly rely on tedious network and loss designs, they still struggle in the inf...
-
Chapter and Conference Paper
StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
We present a new lighting estimation and editing framework to generate high-dynamic-range (HDR) indoor panorama lighting from a single limited field-of-view (LFOV) image captured by low-dynamic-range (LDR) cam...
-
Chapter and Conference Paper
Relighting4D: Neural Relightable Human from Videos
Human relighting is a highly desirable yet challenging task. Existing works either require expensive one-light-at-a-time (OLAT) captured data using light stage or cannot freely change the viewpoints of the ren...
-
Chapter and Conference Paper
Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis
Video-to-Video synthesis (Vid2Vid) has achieved remarkable results in generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long i...
-
Chapter and Conference Paper
Shap-CAM: Visual Explanations for Convolutional Neural Networks Based on Shapley Value
Explaining deep convolutional neural networks has been recently drawing increasing attention since it helps to understand the networks’ internal operations and why they make certain decisions. Saliency maps, w...
-
Chapter and Conference Paper
StyleGAN-Human: A Data-Centric Odyssey of Human Generation
Unconditional human image generation is an important task in vision and graphics, enabling various applications in the creative industry. Existing studies in this field mainly focus on “network engineering” su...
