25 citations · 111 across the 31 of their papers we have counts for
32 papers
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
Zheng Zhang, Ning Li, Qi Liu +6
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant document from external knowledge sources. By referencing this external knowledge,…
Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation
Zhiyao Ren, Yibing Zhan, Baosheng Yu +1
Text-to-image generation has become increasingly popular, but achieving the desired images often requires extensive prompt engineering. In this paper, we explore how to decode text…
Self-Supervised Learning for Detecting AI-Generated Faces as Anomalies
Mian Zou, Baosheng Yu, Yibing Zhan +1
The detection of AI-generated faces is commonly approached as a binary classification task. Nevertheless, the resulting detectors frequently struggle to adapt to novel AI face gene…
Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach
Mian Zou, Baosheng Yu, Yibing Zhan +2
In recent years, the multimedia forensics and security community has seen remarkable progress in multitask learning for DeepFake (i.e., face forgery) detection. The prevailing appr…
Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method
Mian Zou, Baosheng Yu, Yibing Zhan +2
In recent years, deep learning has greatly streamlined the process of manipulating photographic face images. Aware of the potential dangers, researchers have developed various tool…
Deep Learning-Based Point Cloud Registration: A Comprehensive Survey and Taxonomy
Yu-Xin Zhang, Jie Gui, Baosheng Yu +4
Point cloud registration involves determining a rigid transformation to align a source point cloud with a target point cloud. This alignment is fundamental in applications such as…
Healthcare Copilot: Eliciting the Power of General LLMs for Medical Consultation
Zhiyao Ren, Yibing Zhan, Baosheng Yu +2
The copilot framework, which aims to enhance and tailor large language models (LLMs) for specific complex tasks without requiring fine-tuning, is gaining increasing attention from…
PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation
Haibo Qiu, Baosheng Yu, Yixin Chen +1
Significant progress has been made recently in point cloud segmentation utilizing an encoder-decoder framework, which initially encodes point clouds into low-resolution representat…
ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Wenyuan Xue, Dapeng Chen, Baosheng Yu +3
Visual chart recognition systems are gaining increasing attention due to the growing demand for automatically identifying table headers and values from chart images. Current method…
Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach
Cheng Wen, Baosheng Yu, Rao Fu +1
A generative model for high-fidelity point clouds is of great importance in synthesizing 3d environments for applications such as autonomous driving and robotics. Despite the recen…
Free-Form Composition Networks for Egocentric Action Recognition
Haoran Wang, Qinghua Cheng, Baosheng Yu +4
Egocentric action recognition is gaining significant attention in the field of human action recognition. In this paper, we address data scarcity issue in egocentric action recognit…
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
Chuang Liu, Yibing Zhan, Baosheng Yu +4
A pooling operation is essential for effective graph-level representation learning, where the node drop pooling has become one mainstream graph pooling technology. However, current…
Collect-and-Distribute Transformer for 3D Point Cloud Analysis
Haibo Qiu, Baosheng Yu, Dacheng Tao
Remarkable advancements have been made recently in point cloud analysis through the exploration of transformer architecture, but it remains challenging to effectively learn local a…
Compositional 3D Human-Object Neural Animation
Zhi Hou, Baosheng Yu, Dacheng Tao
Human-object interactions (HOIs) are crucial for human-centric scene understanding applications such as human-centric visual generation, AR/VR, and robotics. Since existing methods…
Pseudo Contrastive Learning for Graph-based Semi-supervised Learning
Weigang Lu, Ziyu Guan, Wei Zhao +5
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions…
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Qihuang Zhong, Liang Ding, Yibing Zhan +11
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…
Responsible Active Learning via Human-in-the-loop Peer Study
Yu-Tong Cao, Jingya Wang, Baosheng Yu +1
Active learning has been proposed to reduce data annotation efforts by only manually labelling representative data samples for training. Meanwhile, recent active learning applicati…
Knowledge-Aware Federated Active Learning with Non-IID Data
Yu-Tong Cao, Ye Shi, Baosheng Yu +2
Federated learning enables multiple decentralized clients to learn collaboratively without sharing the local training data. However, the expensive annotation cost to acquire data l…
Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Yi-Fan Zhang, Jindong Wang, Jian Liang +5
Recent domain generalization (DG) approaches typically use the hypothesis learned on source domains for inference on the unseen target domain. However, such a hypothesis can be arb…
MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
Yaqian Liang, Shanshan Zhao, Baosheng Yu +2
Recently, self-supervised pre-training has advanced Vision Transformers on various tasks w.r.t. different data modalities, e.g., image and 3D point cloud data. In this paper, we ex…
GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
Haibo Qiu, Baosheng Yu, Dacheng Tao
Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different info…
BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning
Zhi Hou, Baosheng Yu, Chaoyue Wang +2
Attention mechanisms have been very popular in deep neural networks, where the Transformer architecture has achieved great success in not only natural language processing but also…
Exploring High-Order Structure for Robust Graph Structure Learning
Guangqian Yang, Yibing Zhan, Jinlong Li +3
Recent studies show that Graph Neural Networks (GNNs) are vulnerable to adversarial attack, i.e., an imperceptible structure perturbation can fool GNNs to make wrong predictions. S…
Contrastive Boundary Learning for Point Cloud Segmentation
Liyao Tang, Yibing Zhan, Zhe Chen +2
Point cloud segmentation is fundamental in understanding 3D environments. However, current 3D point cloud segmentation methods usually perform poorly on scene boundaries, which deg…