Search Results for author: Xiaoqi Wang

Found 15 papers, 4 papers with code

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

no code implementations4 Dec 2024 Shouwei Ruan, Hanqing Liu, Yao Huang, Xiaoqi Wang, Caixin Kang, Hang Su, Yinpeng Dong, Xingxing Wei

To systematically evaluate VLMs' robustness to real-world 3D variations, we propose AdvDreamer, the first framework that generates physically reproducible adversarial 3D transformation (Adv-3DT) samples from single-view images.

Benchmarking Visual Question Answering (VQA)

DT-JRD: Deep Transformer based Just Recognizable Difference Prediction Model for Video Coding for Machines

no code implementations14 Nov 2024 Junqi Liu, Yun Zhang, Xiaoqi Wang, Xu Long, Sam Kwong

Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision, which can be exploited to promote machine vision oriented visual signal processing.

Multi-class Classification object-detection +2

FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction

no code implementations17 Sep 2024 Ziwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao

Federated learning (FL) has rapidly evolved as a promising paradigm that enables collaborative model training across distributed participants without exchanging their local data.

Dimensionality Reduction Federated Learning +1

Global-Local Progressive Integration Network for Blind Image Quality Assessment

no code implementations7 Aug 2024 Xiaoqi Wang, Yun Zhang

Moreover, our model and its counterpart pre-trained on the proposed dataset respectively exhibited 5. 40% and 13. 23% improvements on across-synthetic datasets evaluation.

Blind Image Quality Assessment Inductive Bias

Symmetric Multi-Similarity Loss for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2024

1 code implementation18 Jun 2024 Xiaoqi Wang, Yi Wang, Lap-Pui Chau

In this report, we present our champion solution for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge in CVPR 2024.

Ensemble Learning Multi-Instance Retrieval +1

Regression-free Blind Image Quality Assessment with Content-Distortion Consistency

1 code implementation18 Jul 2023 Xiaoqi Wang, Jian Xiong, Hao Gao, Weisi Lin

Finally, quality prediction is obtained by aggregating the subjective scores of the retrieved instances.

regression Semantic Similarity +1

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

1 code implementation15 Sep 2022 Xiaoqi Wang, Han-Wei Shen

In this paper, we propose a model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model.

Decision Making

SmartGD: A GAN-Based Graph Drawing Framework for Diverse Aesthetic Goals

no code implementations13 Jun 2022 Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen

There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria.

Deep Learning Generative Adversarial Network

PrEF: Percolation-based Evolutionary Framework for the diffusion-source-localization problem in large networks

no code implementations16 May 2022 Yang Liu, Xiaoqi Wang, Xi Wang, Zhen Wang, Jürgen Kurths

We assume that the state of a number of nodes in a network could be investigated if necessary, and study what configuration of those nodes could facilitate a better solution for the diffusion-source-localization (DSL) problem.

Multi-task Joint Strategies of Self-supervised Representation Learning on Biomedical Networks for Drug Discovery

2 code implementations12 Jan 2022 Xiaoqi Wang, Yingjie Cheng, Yaning Yang, Yue Yu, Fei Li, Shaoliang Peng

Therefore, we conjecture that the multimodal and local-global combination strategies can be treated as the guideline of multi-task SSL for drug discovery.

Drug Discovery Graph Attention +2

DeepGD: A Deep Learning Framework for Graph Drawing Using GNN

no code implementations27 Jun 2021 Xiaoqi Wang, Kevin Yen, Yifan Hu, Han-Wei Shen

In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained.

Deep Learning Graph Neural Network

A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification

no code implementations2 Apr 2018 Weicheng Cai, Zexin Cai, Xiang Zhang, Xiaoqi Wang, Ming Li

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification.

Language Identification

Insights into End-to-End Learning Scheme for Language Identification

no code implementations2 Apr 2018 Weicheng Cai, Zexin Cai, Wenbo Liu, Xiaoqi Wang, Ming Li

After comparing with the state-of-the-art GMM i-vector methods, we give insights into CNN, and reveal its role and effect in the whole pipeline.

Language Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.