Search Results for author: Wei Zhou

Found 192 papers, 66 papers with code

Intra-class Feature Variation Distillation for Semantic Segmentation

1 code implementation ECCV 2020 Yukang Wang, Wei Zhou, Tao Jiang, Xiang Bai, Yongchao Xu

In this paper, different from previous methods performing knowledge distillation for densely pairwise relations, we propose a novel intra-class feature variation distillation (IFVD) to transfer the intra-class feature variation (IFV) of the cumbersome model (teacher) to the compact model (student).

Knowledge Distillation Segmentation +1

Uncertainty-aware Propagation Structure Reconstruction for Fake News Detection

no code implementations COLING 2022 Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu

In this paper, we propose a novel dual graph-based model, Uncertainty-aware Propagation Structure Reconstruction (UPSR) for improving fake news detection.

Fake News Detection

Distance-aware Self-adaptive Graph Convolution for Fine-grained Hierarchical Recommendation

1 code implementation14 May 2025 Tao Huang, Yihong Chen, Wei Fan, Wei Zhou, Junhao Wen

Graph Convolutional Networks (GCNs) are widely used to improve recommendation accuracy and performance by effectively learning the representations of user and item nodes.

Segment Any RGB-Thermal Model with Language-aided Distillation

no code implementations4 May 2025 Dong Xing, Xianxun Zhu, Wei Zhou, Qika Lin, Hang Yang, Yuqing Wang

Given that RGB-T provides a robust solution for scene understanding in adverse weather and lighting conditions, such as low light and overexposure, we propose a novel framework, SARTM, which customizes the powerful SAM for RGB-T semantic segmentation.

Instance Segmentation Knowledge Distillation +3

LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning

1 code implementation28 Apr 2025 Biqing Duan, Qing Wang, Di Liu, Wei Zhou, Zhenli He, Shengfa Miao

During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead.

Incremental Learning

Behavioral Universe Network (BUN): A Behavioral Information-Based Framework for Complex Systems

no code implementations21 Apr 2025 Wei Zhou, Ailiya Borjigin, Cong He

Modern digital ecosystems feature complex, dynamic interactions among autonomous entities across diverse domains.

Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction

no code implementations19 Apr 2025 Li Yu, Xuanzhe Sun, Wei Zhou, Moncef Gabbouj

Therefore, we attempt to simultaneously analyze visual, auditory, and textual modalities in this paper, and propose TAVDiff, a Text-Audio-Visual-conditioned Diffusion Model for video saliency prediction.

Denoising Image Generation +4

DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment

no code implementations16 Apr 2025 Li Yu, Situo Wang, Wei Zhou, Moncef Gabbouj

Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an increasing number of video quality assessment (VQA) works built upon this framework are proposed.

Language Modeling Language Modelling +3

A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future

1 code implementation12 Apr 2025 Jialun Zhong, Wei Shen, Yanzeng Li, Songyang Gao, Hua Lu, Yicheng Chen, Yang Zhang, Wei Zhou, Jinjie Gu, Lei Zou

Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks.

FeatInsight: An Online ML Feature Management System on 4Paradigm Sage-Studio Platform

1 code implementation1 Apr 2025 Xin Tong, Xuanhe Zhou, Bingsheng He, Guoliang Li, Zirui Tang, Wei Zhou, Fan Wu, Mian Lu, Yuqiang Chen

Feature management is essential for many online machine learning applications and can often become the performance bottleneck (e. g., taking up to 70% of the overall latency in sales prediction service).

Fraud Detection Management +1

CrackSQL: A Hybrid SQL Dialect Translation System Powered by Large Language Models

1 code implementation1 Apr 2025 Wei Zhou, Yuyang Gao, Xuanhe Zhou, Guoliang Li

Dialect translation plays a key role in enabling seamless interaction across heterogeneous database systems.

Large Language Model Translation

Feature Calibration enhanced Parameter Synthesis for CLIP-based Class-incremental Learning

no code implementations24 Mar 2025 Juncen Guo, Yang Liu, Xiaoguang Zhu, Lianlong Sun, Liangyu Teng, Jingyi Wu, Di Li, Wei Zhou, Liang Song

Specifically, FCPS introduces a dynamic parameter adjustment mechanism that iteratively calibrates the contribution of original visual features to the final class decision, thus preserving the model's intrinsic generalization capability across modalities.

class-incremental learning Class Incremental Learning +2

InteractEdit: Zero-Shot Editing of Human-Object Interactions in Images

no code implementations12 Mar 2025 Jiun Tian Hoe, Weipeng Hu, Wei Zhou, Chao Xie, Ziwei Wang, Chee Seng Chan, Xudong Jiang, Yap-Peng Tan

This paper presents InteractEdit, a novel framework for zero-shot Human-Object Interaction (HOI) editing, addressing the challenging task of transforming an existing interaction in an image into a new, desired interaction while preserving the identities of the subject and object.

Attribute Human-Object Interaction Detection +2

An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding

1 code implementation6 Mar 2025 Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

Firstly, a shared information maximization principle is proposed to learn more sufficient shared representations for all target tasks.

Natural Language Understanding Representation Learning

Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions

no code implementations1 Mar 2025 Wei Zhou, Hadi Amirpour, Christian Timmerer, Guangtao Zhai, Patrick Le Callet, Alan C. Bovik

Thus, perceptual visual quality assessment (PVQA), which focuses on evaluating the quality of multimedia content based on human perception, is essential for optimizing user experiences in advanced communication systems.

CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP

no code implementations3 Feb 2025 Yirui Zeng, Jun Fu, Hadi Amirpour, Huasheng Wang, Guanghui Yue, Hantao Liu, Ying Chen, Wei Zhou

Blind dehazed image quality assessment (BDQA), which aims to accurately predict the visual quality of dehazed images without any reference information, is essential for the evaluation, comparison, and optimization of image dehazing algorithms.

Image Dehazing Image Quality Assessment +1

OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML

no code implementations15 Jan 2025 Xuanhe Zhou, Wei Zhou, Liguo Qi, Hao Zhang, Dihao Chen, Bingsheng He, Mian Lu, Guoliang Li, Fan Wu, Yuqiang Chen

Efficient and consistent feature computation is crucial for a wide range of online ML applications.

Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering

no code implementations28 Dec 2024 Wei Zhou, Mohsen Mesgar, Annemarie Friedrich, Heike Adel

In this paper, we propose Multi-Agent Collaboration with Tool use (MACT), a framework that requires neither closed-source models nor fine-tuning.

Question Answering

D-Judge: How Far Are We? Evaluating the Discrepancies Between AI-synthesized Images and Natural Images through Multimodal Guidance

no code implementations23 Dec 2024 Renyang Liu, Ziyu Lyu, Wei Zhou, See-Kiong Ng

In Artificial Intelligence Generated Content (AIGC), distinguishing AI-synthesized images from natural ones remains a key challenge.

multimodal generation

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

no code implementations22 Dec 2024 Haoran You, Connelly Barnes, Yuqian Zhou, Yan Kang, Zhenbang Du, Wei Zhou, Lingzhi Zhang, Yotam Nitzan, Xiaoyang Liu, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Yingyan Celine Lin

To address this, we propose DiffCR, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically route computation across layers and timesteps for each image token, resulting in efficient DiTs.

Denoising Image Generation

Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey

no code implementations30 Nov 2024 Wei Zhou, Lei Zhao, Runyu Zhang, Yifan Cui, Hongpu Huang, Kun Qie, Chen Wang

This review provides a unified framework bridging low-level and high-level perception tasks, systematically analyzes current limitations and solutions, and presents a structured roadmap for integrating emerging technologies, particularly foundation models, to enhance TSS capabilities.

Anomaly Detection object-detection +4

CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR

no code implementations12 Nov 2024 Wei Zhou, Junteng Jia, Leda Sari, Jay Mahadeokar, Ozlem Kalinli

CTC compressor can be an effective approach to integrate audio encoders to decoder-only models, which has gained growing interest for different speech applications.

Decoder

No-Reference Point Cloud Quality Assessment via Graph Convolutional Network

1 code implementation12 Nov 2024 Wu Chen, Qiuping Jiang, Wei Zhou, Feng Shao, Guangtao Zhai, Weisi Lin

Finally, reasoning on the constructed graph is performed by GCN to characterize the mutual dependencies and interactions between different projected images, and aggregate feature information of multi-view projected images for final quality prediction.

graph construction Point Cloud Quality Assessment

A Unified Solution to Diverse Heterogeneities in One-shot Federated Learning

no code implementations28 Oct 2024 Jun Bai, Yiliao Song, Di wu, Atul Sajjanhar, Yong Xiang, Wei Zhou, Xiaohui Tao, Yan Li, Yue Li

To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity.

Federated Learning

Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech

no code implementations2 Oct 2024 Wonjune Kang, Junteng Jia, Chunyang Wu, Wei Zhou, Egor Lakomkin, Yashesh Gaur, Leda Sari, Suyoun Kim, Ke Li, Jay Mahadeokar, Ozlem Kalinli

This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights.

Language Modeling Language Modelling +1

Efficient Streaming LLM for Speech Recognition

no code implementations2 Oct 2024 Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli

Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities.

Decoder speech-recognition +1

Perceptual Depth Quality Assessment of Stereoscopic Omnidirectional Images

no code implementations19 Aug 2024 Wei Zhou, Zhou Wang

Experimental results demonstrate that the proposed method outperforms state-of-the-art image quality assessment (IQA) and depth quality assessment (DQA) approaches in predicting the perceptual depth quality when tested using both single-viewport and omnidirectional stereoscopic image databases.

Image Quality Assessment

Data-Guided Physics-Informed Neural Networks for Solving Inverse Problems in Partial Differential Equations

1 code implementation15 Jul 2024 Wei Zhou, Y. F. Xu

In the pre-training phase, a loss function with only the data loss is minimized in a neural network.

Transferring Structure Knowledge: A New Task to Fake news Detection Towards Cold-Start Propagation

no code implementations13 Jul 2024 Lingwei Wei, Dou Hu, Wei Zhou, Songlin Hu

To achieve the task, we design a simple but effective Structure Adversarial Net (SAN) framework to learn transferable features from available propagation to boost the detection of content-only samples.

Fake News Detection

Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition

no code implementations10 Jul 2024 Jingjing Xu, Wei Zhou, Zijian Yang, Eugen Beck, Ralf Schlueter

Varying-size models are often required to deploy ASR systems under different hardware and/or application constraints such as memory and latency.

speech-recognition Speech Recognition

Token-Weighted RNN-T for Learning from Flawed Data

no code implementations26 Jun 2024 Gil Keren, Wei Zhou, Ozlem Kalinli

ASR models are commonly trained with the cross-entropy criterion to increase the probability of a target token sequence.

Vision-Language Consistency Guided Multi-modal Prompt Learning for Blind AI Generated Image Quality Assessment

1 code implementation24 Jun 2024 Jun Fu, Wei Zhou, Qiuping Jiang, Hantao Liu, Guangtao Zhai

This is not enough for adapting CLIP models to AI generated image quality assessment (AGIQA) since AGIs visually differ from natural images.

Image Quality Assessment Prompt Learning

LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection

no code implementations11 Jun 2024 Jiahua Xu, Si Zuo, Chenfeng Wei, Wei Zhou

It is worth noting that LiSD achieves the state-of-the-art performance of 83. 3% mIoU on the nuScenes segmentation benchmark for lidar-only methods.

3D Semantic Segmentation Autonomous Driving +5

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

1 code implementation10 Jun 2024 Haoran You, Yipin Guo, Yichao Fu, Wei Zhou, Huihong Shi, Xiaofan Zhang, Souvik Kundu, Amir Yazdanbakhsh, Yingyan Celine Lin

Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM, achieving average perplexity improvements of 5. 6 and 22. 7 points at comparable or lower latency compared to the most competitive quantized LLMs at 3 and 2 bits, respectively, and more than 80% memory and energy reductions over the original LLMs.

Representation Learning with Conditional Information Flow Maximization

1 code implementation8 Jun 2024 Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task.

Representation Learning

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation

1 code implementation30 May 2024 Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Specifically, by restructuring the training objectives -- removing the answer from outputs and concatenating the question with the rationale as input -- CasCoD's two-step learning process ensures that students focus on learning rationales without interference from the preset answers, thus improving reasoning generalizability.

Diversity

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation

1 code implementation30 May 2024 Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Further analysis shows that EDIT can generate high-quality CoTs with more correct key reasoning steps.

Imitation Learning

Perceptual Crack Detection for Rendered 3D Textured Meshes

1 code implementation9 May 2024 Armin Shafiee Sarvestani, Wei Zhou, Zhou Wang

Extensive experiments on large-scale public datasets of 3D textured meshes demonstrate effectiveness and efficiency of the proposed PCD method in correct localization and detection of crack artifacts.

Image Quality Assessment

Exploring Correlations of Self-Supervised Tasks for Graphs

1 code implementation7 May 2024 Taoran Fang, Wei Zhou, Yifei Sun, Kaiqiao Han, Lvbin Ma, Yang Yang

Specifically, we evaluate the performance of the representations trained by one specific task on other tasks and define correlation values to quantify task correlations.

Multi-Task Learning Self-Supervised Learning

FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering

2 code implementations29 Apr 2024 Wei Zhou, Mohsen Mesgar, Heike Adel, Annemarie Friedrich

To investigate these aspects, we create and publish a novel TQA evaluation benchmark in English.

Question Answering

Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment

no code implementations23 Apr 2024 Tianwei Zhou, Songbai Tan, Wei Zhou, Yu Luo, Yuan-Gen Wang, Guanghui Yue

Specifically, inspired by the characteristics of the human visual system and motivated by the observation that "visual quality" and "authenticity" are characterized by both local and global aspects, AMFF-Net scales the image up and down and takes the scaled images and original-sized image as the inputs to obtain multi-scale features.

Blind Image Quality Assessment

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario

no code implementations30 Mar 2024 Renyang Liu, Kwok-Yan Lam, Wei Zhou, Sixing Wu, Jun Zhao, Dongting Hu, Mingming Gong

Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness.

Explaining Pre-Trained Language Models with Attribution Scores: An Analysis in Low-Resource Settings

no code implementations8 Mar 2024 Wei Zhou, Heike Adel, Hendrik Schuff, Ngoc Thang Vu

Attribution scores indicate the importance of different input parts and can, thus, explain model behaviour.

Decoder

Multi-view Intent Learning and Alignment with Large Language Models for Session-based Recommendation

1 code implementation21 Feb 2024 Shutong Qiao, Wei Zhou, Junhao Wen, Chen Gao, Qun Luo, Peixuan Chen, Yong Li

To address the above challenges, we propose an LLM-enhanced SBR framework that integrates semantic and behavioral signals from multiple views.

Session-Based Recommendations

Towards Loose-Fitting Garment Animation via Generative Model of Deformation Decomposition

no code implementations22 Dec 2023 Yifu Liu, Xiaoxia Li, Zhiling Luo, Wei Zhou

Existing data-driven methods for garment animation, usually driven by linear skinning, although effective on tight garments, do not handle loose-fitting garments with complex deformations well.

Structured Probabilistic Coding

1 code implementation21 Dec 2023 Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu

It can enhance the generalization ability of pre-trained language models for better language understanding.

Natural Language Understanding Representation Learning

SSTA: Salient Spatially Transformed Attack

no code implementations12 Dec 2023 Renyang Liu, Wei Zhou, Sixin Wu, Jun Zhao, Kwok-Yan Lam

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.

DTA: Distribution Transform-based Attack for Query-Limited Scenario

no code implementations12 Dec 2023 Renyang Liu, Wei Zhou, Xin Jin, Song Gao, Yuanyu Wang, Ruxin Wang

In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials during an attack.

Hard-label Attack

Are Large Language Models Good Fact Checkers: A Preliminary Study

no code implementations29 Nov 2023 Han Cao, Lingwei Wei, Mengyang Chen, Wei Zhou, Songlin Hu

However, they encounter challenges in effectively handling Chinese fact verification and the entirety of the fact-checking pipeline due to language inconsistencies and hallucinations.

Fact Checking Fact Verification

Double-Flow-based Steganography without Embedding for Image-to-Image Hiding

no code implementations25 Nov 2023 Bingbing Song, Derui Wang, Tianwei Zhang, Renyang Liu, Yu Lin, Wei Zhou

Hence, it provides a way to directly generate stego images from secret images without a cover image.

Steganalysis

Explore the Potential of LLMs in Misinformation Detection: An Empirical Study

no code implementations21 Nov 2023 Mengyang Chen, Lingwei Wei, Han Cao, Wei Zhou, Songlin Hu

Our empirical studies on eight misinformation detection datasets show that LLM-based detectors can achieve comparable performance in text-based misinformation detection but exhibit notably constrained capabilities in comprehending propagation structure compared to existing models in propagation-based misinformation detection.

Misinformation Natural Language Understanding

CT-GAT: Cross-Task Generative Adversarial Attack based on Transferability

1 code implementation22 Oct 2023 Minxuan Lv, Chengwei Dai, Kun Li, Wei Zhou, Songlin Hu

Neural network models are vulnerable to adversarial examples, and adversarial transferability further increases the risk of adversarial attacks.

Adversarial Attack

MeaeQ: Mount Model Extraction Attacks with Efficient Queries

1 code implementation21 Oct 2023 Chengwei Dai, Minxuan Lv, Kun Li, Wei Zhou

We study model extraction attacks in natural language processing (NLP) where attackers aim to steal victim models by repeatedly querying the open Application Programming Interfaces (APIs).

Active Learning Diversity +1

Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networks

no code implementations15 Oct 2023 Renyang Liu, Wei Zhou, Jinhong Zhang, Xiaoyuan Liu, Peiyuan Si, Haoran Li

Inspired by this, we propose a novel model inversion attack method on HomoGNNs and HeteGNNs, namely HomoGMI and HeteGMI.

SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack

no code implementations15 Oct 2023 Renyang Liu, Jinhong Zhang, Kwok-Yan Lam, Jun Zhao, Wei Zhou

However, the distribution of these fake data lacks diversity and cannot detect the decision boundary of the target model well, resulting in the dissatisfactory simulation effect.

Diversity Model extraction

Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?

no code implementations15 Oct 2023 Renyang Liu, Jun Zhao, Xing Chu, Yu Liang, Wei Zhou, Jing He

With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms.

AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings

no code implementations15 Oct 2023 Renyang Liu, Jinhong Zhang, Haoran Li, Jin Zhang, Yuanyu Wang, Wei Zhou

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks.

Investigating the Effect of Language Models in Sequence Discriminative Training for Neural Transducers

no code implementations11 Oct 2023 Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney

In this work, we investigate the effect of language models (LMs) with different context lengths and label units (phoneme vs. word) used in sequence discriminative training for phoneme-based neural transducers.

Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models

1 code implementation11 Oct 2023 Renyang Liu, Wei Zhou, Tianwei Zhang, Kangjie Chen, Jun Zhao, Kwok-Yan Lam

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models.

Adversarial Attack Denoising

On the Relation between Internal Language Model and Sequence Discriminative Training for Neural Transducers

no code implementations25 Sep 2023 Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney

Empirically, we show that ILM subtraction and sequence discriminative training achieve similar effects across a wide range of experiments on Librispeech, including both MMI and minimum Bayes risk (MBR) criteria, as well as neural transducers and LMs of both full and limited context.

Language Modeling Language Modelling +3

HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison Corpus

1 code implementation6 Sep 2023 Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, Songlin Hu

In this paper, we demonstrate that detecting model-generated text in semantic-invariant tasks is more challenging.

Question Answering

E$^3$-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles

no code implementations9 Aug 2023 Jiashun Suo, Xingzhou Zhang, Weisong Shi, Wei Zhou

We first present an effective evaluation metric for actual tasks and construct a transparent energy consumption model based on hundreds of actual flight data to formalize the relationship between energy consumption and flight parameters.

Fire Detection Object +2

Dialogue Shaping: Empowering Agents through NPC Interaction

no code implementations28 Jul 2023 Wei Zhou, Xiangyu Peng, Mark Riedl

One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive.

Knowledge Graphs reinforcement-learning +1

CASEIN: Cascading Explicit and Implicit Control for Fine-grained Emotion Intensity Regulation

no code implementations27 Jun 2023 Yuhao Cui, Xiongwei Wang, Zhongzhou Zhao, Wei Zhou, Haiqing Chen

However, these high-level semantic probabilities are often inaccurate and unsmooth at the phoneme level, leading to bias in learning.

Disentanglement

Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations

1 code implementation2 Jun 2023 Dou Hu, Yinan Bao, Lingwei Wei, Wei Zhou, Songlin Hu

To address this, we propose a supervised adversarial contrastive learning (SACL) framework for learning class-spread structured representations in a supervised manner.

Contrastive Learning Emotion Recognition in Conversation

RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition

no code implementations28 May 2023 Wei Zhou, Eugen Beck, Simon Berger, Ralf Schlüter, Hermann Ney

Modern public ASR tools usually provide rich support for training various sequence-to-sequence (S2S) models, but rather simple support for decoding open-vocabulary scenarios only.

Decoder Sequence-To-Sequence Speech Recognition +1

GTNet: Graph Transformer Network for 3D Point Cloud Classification and Semantic Segmentation

no code implementations24 May 2023 Wei Zhou, Qian Wang, Weiwei Jin, Xinzhe Shi, Ying He

Local Transformer uses a dynamic graph to calculate all neighboring point weights by intra-domain cross-attention with dynamically updated graph relations, so that every neighboring point could affect the features of centroid with different weights; Global Transformer enlarges the receptive field of Local Transformer by a global self-attention.

3D Point Cloud Classification Point Cloud Classification +1

VTPNet for 3D deep learning on point cloud

no code implementations10 May 2023 Wei Zhou, Weiwei Jin, Qian Wang, Yifan Wang, Dekui Wang, Xingxing Hao, Yongxiang Yu

Recently, Transformer-based methods for point cloud learning have achieved good results on various point cloud learning benchmarks.

Deep Learning Semantic Segmentation

Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain

no code implementations5 May 2023 Liqiang Jing, Xuemeng Song, Xuming Lin, Zhongzhou Zhao, Wei Zhou, Liqiang Nie

This task is non-trivial, due to three challenges: the logic of the generated text, unstructured style reference, and biased training samples.

Attribute Data-to-Text Generation +1

JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization

no code implementations30 Mar 2023 Yifu Liu, Xiaoxia Li, Zhiling Luo, Wei Zhou

These different actions are defined as conjoint actions, whose rest parts are definite phases, e. g., leaping over the bar in a HighJump.

Multiple Instance Learning Weakly-supervised Learning +2

BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding

1 code implementation25 Feb 2023 Yulong Liu, Yongqiang Ma, Wei Zhou, Guibo Zhu, Nanning Zheng

Our experiments show that this combination can boost the decoding model's performance on certain tasks like fMRI-text matching and fMRI-to-image generation.

Brain Decoding Image Generation +3

Blind Omnidirectional Image Quality Assessment: Integrating Local Statistics and Global Semantics

no code implementations24 Feb 2023 Wei Zhou, Zhou Wang

Omnidirectional image quality assessment (OIQA) aims to predict the perceptual quality of omnidirectional images that cover the whole 180$\times$360$^{\circ}$ viewing range of the visual environment.

Image Quality Assessment

Efficient 3D Object Reconstruction using Visual Transformers

no code implementations16 Feb 2023 Rohan Agarwal, Wei Zhou, Xiaofeng Wu, Yuhan Li

Reconstructing a 3D object from a 2D image is a well-researched vision problem, with many kinds of deep learning techniques having been tried.

3D Object Reconstruction Decoder +1

Story Shaping: Teaching Agents Human-like Behavior with Stories

no code implementations24 Jan 2023 Xiangyu Peng, Christopher Cui, Wei Zhou, Renee Jia, Mark Riedl

We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge from an exemplar story of how to accomplish a task and intrinsically rewards itself for performing actions that make its current environment adhere to that of the inferred story world.

reinforcement-learning Reinforcement Learning +2

Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection

1 code implementation18 Jan 2023 Wei Zhou, Guanghui Yue, Ruizeng Zhang, Yipeng Qin, Hantao Liu

Many dense 3D point clouds have been exploited to represent visual objects instead of traditional images or videos.

COOP: Decoupling and Coupling of Whole-Body Grasping Pose Generation

1 code implementation ICCV 2023 Yanzhao Zheng, Yunzhou Shi, Yuhao Cui, Zhongzhou Zhao, Zhiling Luo, Wei Zhou

To address this issue, we propose a novel framework called COOP (DeCOupling and COupling of Whole-Body GrasPing Pose Generation) to synthesize life-like whole-body poses that cover the widest range of human grasping capabilities.

Motion Generation

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers

no code implementations7 Dec 2022 Zijian Yang, Wei Zhou, Ralf Schlüter, Hermann Ney

Compared to the N-best-list based minimum Bayes risk objectives, lattice-free methods gain 40% - 70% relative training time speedup with a small degradation in performance.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

1 code implementation12 Nov 2022 Tianyi Shi, Xiaohuan Ding, Wei Zhou, Feng Pan, Zengqiang Yan, Xiang Bai, Xin Yang

Vessel segmentation is crucial in many medical image applications, such as detecting coronary stenoses, retinal vessel diseases and brain aneurysms.

Enhancing and Adversarial: Improve ASR with Speaker Labels

no code implementations11 Nov 2022 Wei Zhou, Haotian Wu, Jingjing Xu, Mohammad Zeineldeen, Christoph Lüscher, Ralf Schlüter, Hermann Ney

Detailed analysis and experimental verification are conducted to show the optimal positions in the ASR neural network (NN) to apply speaker enhancing and adversarial training.

Multi-Task Learning

Monotonic segmental attention for automatic speech recognition

1 code implementation26 Oct 2022 Albert Zeyer, Robin Schmitt, Wei Zhou, Ralf Schlüter, Hermann Ney

We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning

no code implementations6 Oct 2022 Xiong Junwu, Xiaoyun Feng, Yunzhou Shi, James Zhang, Zhongzhou Zhao, Wei Zhou

Our proposed framework learns through real-time interactions between the digital human and customers dynamically through the state-of-art RL algorithms, combined with multimodal embedding and graph embedding, to improve the accuracy of personalization and thus enable the digital human agent to timely catch the attention of the customer.

Decision Making Graph Embedding +4

An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

3 code implementations28 Sep 2022 Xiu-Shen Wei, He-Yang Xu, Faen Zhang, Yuxin Peng, Wei Zhou

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data.

Few-Shot Learning

FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications

no code implementations7 Sep 2022 Wei Zhou, Xuanlin Min, Rui Hu, Yiwen Long, Huan Luo, JunYi

Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes.

object-detection Real-Time Object Detection

Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling

no code implementations31 Aug 2022 Wei Zhou, Qi Yang, Qiuping Jiang, Guangtao Zhai, Weisi Lin

Objective quality assessment of 3D point clouds is essential for the development of immersive multimedia systems in real-world applications.

Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity

1 code implementation15 Jul 2022 Wei Zhou, Zhou Wang

There has been a growing interest in developing image super-resolution (SR) algorithms that convert low-resolution (LR) to higher resolution images, but automatically evaluating the visual quality of super-resolved images remains a challenging problem.

Generative Adversarial Network Image Quality Assessment +1

RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment

no code implementations13 Jul 2022 Yiting Lu, Jun Fu, Xin Li, Wei Zhou, Sen Liu, Xinxin Zhang, Congfu Jia, Ying Liu, Zhibo Chen

Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.

Image Quality Assessment Multiple Instance Learning

Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in Conversation

no code implementations7 Jun 2022 Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu

Since the dependencies between speakers are complex and dynamic, which consist of intra- and inter-speaker dependencies, the modeling of speaker-specific information is a vital role in ERC.

Decoder Emotion Recognition in Conversation

Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation

no code implementations12 May 2022 Qiuping Jiang, Jiawu Xu, Yudong Mao, Wei Zhou, Xiongkuo Min, Guangtao Zhai

The DDB-Net contains three modules, i. e., an image decomposition module, a feature encoding module, and a bilinear pooling module.

Blind Image Quality Assessment

Efficient Training of Neural Transducer for Speech Recognition

no code implementations22 Apr 2022 Wei Zhou, Wilfried Michel, Ralf Schlüter, Hermann Ney

In this work, we propose an efficient 3-stage progressive training pipeline to build highly-performing neural transducer models from scratch with very limited computation resources in a reasonable short time period.

speech-recognition Speech Recognition

HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection

1 code implementation7 Apr 2022 Jiashun Suo, Tianyi Wang, Xingzhou Zhang, Haiyang Chen, Wei Zhou, Weisong Shi

We present the HIT-UAV dataset, a high-altitude infrared thermal dataset for object detection applications on Unmanned Aerial Vehicles (UAVs).

Object object-detection +1

Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech

no code implementations31 Mar 2022 Guangyan Zhang, Kaitao Song, Xu Tan, Daxin Tan, Yuzi Yan, Yanqing Liu, Gang Wang, Wei Zhou, Tao Qin, Tan Lee, Sheng Zhao

However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is inconsistent with the TTS fine-tuning that takes phonemes as input.

text-to-speech Text to Speech

Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic

no code implementations11 Nov 2021 Wei Zhou, Dong Chen, Jun Yan, Zhaojian Li, Huilin Yin, Wanchen Ge

In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs.

Autonomous Driving Decision Making +4

Efficient Learning of Quadratic Variance Function Directed Acyclic Graphs via Topological Layers

no code implementations1 Nov 2021 Wei Zhou, Xin He, Wei Zhong, Junhui Wang

Directed acyclic graph (DAG) models are widely used to represent causal relationships among random variables in many application domains.

Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design

no code implementations25 Oct 2021 Wei Zhou, Xiangyu Zhang, Hongyu Wang, Shenghua Gao, Xin Lou

It is shown that by adding another transformation, the proposed method is able to synthesize high-quality RAW Bayer images with arbitrary size.

Demosaicking Image Generation +3

On Language Model Integration for RNN Transducer based Speech Recognition

no code implementations13 Oct 2021 Wei Zhou, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

In this work, we study various ILM correction-based LM integration methods formulated in a common RNN-T framework.

Language Modeling Language Modelling +2

GGP: A Graph-based Grouping Planner for Explicit Control of Long Text Generation

no code implementations18 Aug 2021 Xuming Lin, Shaobo Cui, Zhongzhou Zhao, Wei Zhou, Ji Zhang, Haiqing Chen

With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text.

Story Generation

Transformer-Encoder-GRU (T-E-GRU) for Chinese Sentiment Analysis on Chinese Comment Text

no code implementations1 Aug 2021 Binlong Zhang, Wei Zhou

Chinese sentiment analysis (CSA) has always been one of the challenges in natural language processing due to its complexity and uncertainty.

Chinese Sentiment Analysis Position +3

Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds

no code implementations28 Jul 2021 Wei Zhou, Xin Cao, Xiaodan Zhang, Xingxing Hao, Dekui Wang, Ying He

Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MPVConv improves the accuracy of the backbone (PointNet) by up to \textbf{36\%}, and achieves higher accuracy than the voxel-based model with up to \textbf{34}$\times$ speedups.

Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN(SRG-Net)

no code implementations28 Jul 2021 Yao Hu, Guohua Geng, Kang Li, Wei Zhou, Xingxing Hao, Xin Cao

Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds.

Segmentation

Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection

1 code implementation ACL 2021 Lingwei Wei, Dou Hu, Wei Zhou, Zhaojuan Yue, Songlin Hu

Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc.

A Fixed Version of Quadratic Program in Gradient Episodic Memory

no code implementations7 Jul 2021 Wei Zhou, Yiying Li

Gradient Episodic Memory is indeed a novel method for continual learning, which solves new problems quickly without forgetting previously acquired knowledge.

Continual Learning

PEN4Rec: Preference Evolution Networks for Session-based Recommendation

1 code implementation17 Jun 2021 Dou Hu, Lingwei Wei, Wei Zhou, Xiaoyong Huai, Zhiqi Fang, Songlin Hu

The process can strengthen the effect of relevant sequential behaviors during the preference evolution and weaken the disturbance from preference drifting.

Retrieval Session-Based Recommendations

Challenging distributional models with a conceptual network of philosophical terms

1 code implementation NAACL 2021 Yvette Oortwijn, Jelke Bloem, Pia Sommerauer, Francois Meyer, Wei Zhou, Antske Fokkens

We investigate the possibilities and limitations of using distributional semantic models for analyzing philosophical data by means of a realistic use-case.

Philosophy

Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness

1 code implementation15 May 2021 Wei Zhou, Zhou Wang, Zhibo Chen

In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness.

Generative Adversarial Network Image Quality Assessment +1

SRLF: A Stance-aware Reinforcement Learning Framework for Content-based Rumor Detection on Social Media

no code implementations10 May 2021 Chunyuan Yuan, Wanhui Qian, Qianwen Ma, Wei Zhou, Songlin Hu

The rapid development of social media changes the lifestyle of people and simultaneously provides an ideal place for publishing and disseminating rumors, which severely exacerbates social panic and triggers a crisis of social trust.

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

no code implementations30 Apr 2021 Wei Zhou, Xin Cao, Xiaodan Zhang, Xingxing Hao, Dekui Wang, Ying He

Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34 times speedup.

Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition

no code implementations19 Apr 2021 Wei Zhou, Mohammad Zeineldeen, Zuoyun Zheng, Ralf Schlüter, Hermann Ney

Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech

no code implementations17 Apr 2021 Yu Qiao, Wei Zhou, Elma Kerz, Ralf Schlüter

In recent years, automated approaches to assessing linguistic complexity in second language (L2) writing have made significant progress in gauging learner performance, predicting human ratings of the quality of learner productions, and benchmarking L2 development.

Benchmarking

Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept

no code implementations13 Apr 2021 Wei Zhou, Albert Zeyer, André Merboldt, Ralf Schlüter, Hermann Ney

With the advent of direct models in automatic speech recognition (ASR), the formerly prevalent frame-wise acoustic modeling based on hidden Markov models (HMM) diversified into a number of modeling architectures like encoder-decoder attention models, transducer models and segmental models (direct HMM).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Bayesian Graph Convolutional Network for Traffic Prediction

no code implementations1 Apr 2021 Jun Fu, Wei Zhou, Zhibo Chen

Under this framework, the graph structure is viewed as a random realization from a parametric generative model, and its posterior is inferred using the observed topology of the road network and traffic data.

Prediction Traffic Prediction

No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness

no code implementations22 Feb 2021 Wei Zhou, Jiahua Xu, Qiuping Jiang, Zhibo Chen

To our knowledge, the proposed model is the first no-reference quality assessment method for 360-degreee images that combines multi-frequency information and image naturalness.

ERP Image Quality Assessment

FedH2L: Federated Learning with Model and Statistical Heterogeneity

no code implementations27 Jan 2021 Yiying Li, Wei Zhou, Huaimin Wang, Haibo Mi, Timothy M. Hospedales

Federated learning (FL) enables distributed participants to collectively learn a strong global model without sacrificing their individual data privacy.

Federated Learning model

Improving robustness of softmax corss-entropy loss via inference information

no code implementations1 Jan 2021 Bingbing Song, wei he, Renyang Liu, Shui Yu, Ruxin Wang, Mingming Gong, Tongliang Liu, Wei Zhou

Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.

Deep Multi-Scale Features Learning for Distorted Image Quality Assessment

no code implementations1 Dec 2020 Wei Zhou, Zhibo Chen

In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction.

Image Quality Assessment

Unsupervised Segmentation for Terracotta Warrior Point Cloud (SRG-Net)

1 code implementation1 Dec 2020 Yao Hu, Guohua Geng, Kang Li, Wei Zhou

Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds.

Clustering Segmentation

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

no code implementations30 Oct 2020 Wei Zhou, Simon Berger, Ralf Schlüter, Hermann Ney

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling.

Language Modeling Language Modelling +2

Bayesian Spatio-Temporal Graph Convolutional Network for Traffic Forecasting

no code implementations15 Oct 2020 Jun Fu, Wei Zhou, Zhibo Chen

The graph structure in our network is learned from the physical topology of the road network and traffic data in an end-to-end manner, which discovers a more accurate description of the relationship among traffic flows.

Traffic Prediction

Affinity Space Adaptation for Semantic Segmentation Across Domains

1 code implementation26 Sep 2020 Wei Zhou, Yukang Wang, Jiajia Chu, Jiehua Yang, Xiang Bai, Yongchao Xu

Specifically, we perform domain adaptation on the affinity relationship between adjacent pixels termed affinity space of source and target domain.

Segmentation Semantic Segmentation +1

Residual Spatial Attention Network for Retinal Vessel Segmentation

1 code implementation18 Sep 2020 Changlu Guo, Márton Szemenyei, Yugen Yi, Wei Zhou, Haodong Bian

In this work, we propose the Residual Spatial Attention Network (RSAN) for retinal vessel segmentation.

Retinal Vessel Segmentation Segmentation

Empirical Fourier Decomposition: An Accurate Adaptive Signal Decomposition Method

no code implementations17 Sep 2020 Wei Zhou, Zhongren Feng, Y. F. Xu, Xiongjiang Wang, Hao Lv

An accurate adaptive signal decomposition method, called the empirical Fourier decomposition (EFD), is proposed to solve the problems in this work.

Computational Efficiency

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

no code implementations ECCV 2020 Jianzhao Liu, Jianxin Lin, Xin Li, Wei Zhou, Sen Liu, Zhibo Chen

Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task.

Image Restoration SSIM

Adaptive support driven Bayesian reweighted algorithm for sparse signal recovery

no code implementations10 Aug 2020 Junlin Li, Wei Zhou, Cheng Cheng

For example, sparse Bayesian learning (SBL) was proposed to learn major features from a dictionary of basis functions, which makes identified models interpretable.

feature selection Sparse Learning

Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis

1 code implementation16 Jul 2020 Lingwei Wei, Dou Hu, Wei Zhou, Xuehai Tang, Xiaodan Zhang, Xin Wang, Jizhong Han, Songlin Hu

Furthermore, we design a Sentiment-based Rethinking mechanism (SR) by refining the HIN with sentiment label information to learn a more sentiment-aware document representation.

Sentiment Analysis Sentiment Classification +1

Rethinking Distributional Matching Based Domain Adaptation

no code implementations23 Jun 2020 Bo Li, Yezhen Wang, Tong Che, Shanghang Zhang, Sicheng Zhao, Pengfei Xu, Wei Zhou, Yoshua Bengio, Kurt Keutzer

In this paper, in order to devise robust DA algorithms, we first systematically analyze the limitations of DM based methods, and then build new benchmarks with more realistic domain shifts to evaluate the well-accepted DM methods.

Domain Adaptation

DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction

no code implementations9 Jun 2020 Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu

For one thing, previous works cannot jointly utilize both the social network and diffusion graph for prediction, which is insufficient to model the complexity of the diffusion process and results in unsatisfactory prediction performance.

Misinformation Prediction

AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization

1 code implementation25 May 2020 Dongjun Wei, Yaxin Liu, Fuqing Zhu, Liangjun Zang, Wei Zhou, Yijun Lu, Songlin Hu

In this paper, a novel integration method called AutoSUM is proposed for automatic feature extraction and multi-user preference simulation to overcome the drawbacks of previous methods.

feature selection Word Embeddings

A systematic comparison of grapheme-based vs. phoneme-based label units for encoder-decoder-attention models

1 code implementation19 May 2020 Mohammad Zeineldeen, Albert Zeyer, Wei Zhou, Thomas Ng, Ralf Schlüter, Hermann Ney

Following the rationale of end-to-end modeling, CTC, RNN-T or encoder-decoder-attention models for automatic speech recognition (ASR) use graphemes or grapheme-based subword units based on e. g. byte-pair encoding (BPE).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks

no code implementations13 Apr 2020 Wei Zhou, Qiuping Jiang, Yuwang Wang, Zhibo Chen, Weiping Li

Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions.

Image Quality Assessment

Channel Attention Residual U-Net for Retinal Vessel Segmentation

2 code implementations7 Apr 2020 Changlu Guo, Márton Szemenyei, Yangtao Hu, Wenle Wang, Wei Zhou, Yugen Yi

Retinal vessel segmentation is a vital step for the diagnosis of many early eye-related diseases.

Retinal Vessel Segmentation

Gradient-based Feature Extraction From Raw Bayer Pattern Images

no code implementations6 Apr 2020 Wei Zhou, Ling Zhang, Shengyu Gao, Xin Lou

In this paper, the impact of demosaicing on gradient extraction is studied and a gradient-based feature extraction pipeline based on raw Bayer pattern images is proposed.

Demosaicking Pedestrian Detection

The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment

no code implementations2 Apr 2020 Wei Zhou, Wilfried Michel, Kazuki Irie, Markus Kitza, Ralf Schlüter, Hermann Ney

We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus.

Data Augmentation

Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification

1 code implementation9 Nov 2019 Qianwen Ma, Chunyuan Yuan, Wei Zhou, Jizhong Han, Songlin Hu

Based on the two types of relations, we use a graph convolutional network to learn the deep correlations between styles automatically.

General Classification

Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce

1 code implementation7 Nov 2019 Zhenxin Fu, Feng Ji, Wenpeng Hu, Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan

Information-seeking conversation system aims at satisfying the information needs of users through conversations.

Text Matching

Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots

1 code implementation IJCNLP 2019 Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, Songlin Hu

Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information.

Conversational Response Selection Retrieval

ALOHA: Artificial Learning of Human Attributes for Dialogue Agents

1 code implementation18 Oct 2019 Aaron W. Li, Veronica Jiang, Steven Y. Feng, Julia Sprague, Wei Zhou, Jesse Hoey

We propose Human Level Attributes (HLAs) based on tropes as the basis of a method for learning dialogue agents that can imitate the personalities of fictional characters.

Community Detection Language Modelling +1

Feature Fusion Detector for Semantic Cognition of Remote Sensing

no code implementations28 Sep 2019 Wei Zhou, Yiying Li

Based on experiments on the remote sensing dataset from Google Earth, our LFFN has proved effective and practical for the semantic cognition of remote sensing, achieving 89% mAP which is 4. 1% higher than that of FPN.

Diversity

Jointly embedding the local and global relations of heterogeneous graph for rumor detection

1 code implementation10 Sep 2019 Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu

The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and spreading rumors.

Learning review representations from user and product level information for spam detection

no code implementations10 Sep 2019 Chunyuan Yuan, Wei Zhou, Qianwen Ma, Shangwen Lv, Jizhong Han, Songlin Hu

Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information.

Spam detection

Tensor Oriented No-Reference Light Field Image Quality Assessment

no code implementations5 Sep 2019 Wei Zhou, Likun Shi, Zhibo Chen, Jinglin Zhang

Light field image (LFI) quality assessment is becoming more and more important, which helps to better guide the acquisition, processing and application of immersive media.

Image Quality Assessment

Binocular Rivalry Oriented Predictive Auto-Encoding Network for Blind Stereoscopic Image Quality Measurement

1 code implementation4 Sep 2019 Jiahua Xu, Wei Zhou, Zhibo Chen, Suiyi Ling, Patrick Le Callet

Stereoscopic image quality measurement (SIQM) has become increasingly important for guiding stereo image processing and commutation systems due to the widespread usage of 3D contents.

Multimedia Image and Video Processing

No-Reference Light Field Image Quality Assessment Based on Spatial-Angular Measurement

no code implementations17 Aug 2019 Likun Shi, Wei Zhou, Zhibo Chen, Jinglin Zhang

In this paper, we propose a No-Reference Light Field image Quality Assessment (NR-LFQA) scheme, where the main idea is to quantify the LFI quality degradation through evaluating the spatial quality and angular consistency.

Image Quality Assessment

An Intelligent Testing Strategy for Vocabulary Assessment of Chinese Second Language Learners

no code implementations WS 2019 Wei Zhou, Renfen Hu, Feipeng Sun, Ronghuai Huang

In this paper, we propose a novel testing strategy by combining automatic item generation (AIG) and computerized adaptive testing (CAT) in vocabulary assessment for Chinese L2 learners.

LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring

no code implementations1 Jul 2019 Eugen Beck, Wei Zhou, Ralf Schlüter, Hermann Ney

LSTM based language models are an important part of modern LVCSR systems as they significantly improve performance over traditional backoff language models.

Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory

no code implementations12 Jun 2019 Zhibo Chen, Jiahua Xu, Chaoyi Lin, Wei Zhou

In this paper, based on the predictive coding theory of the human vision system (HVS), we propose a stereoscopic omnidirectional image quality evaluator (SOIQE) to cope with the characteristics of 3D 360-degree images.

Image Quality Assessment

Spectral Perturbation Meets Incomplete Multi-view Data

no code implementations31 May 2019 Hao Wang, Linlin Zong, Bing Liu, Yan Yang, Wei Zhou

In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering.

Clustering Incomplete multi-view clustering +1

ESA: Entity Summarization with Attention

2 code implementations25 May 2019 Dongjun Wei, Yaxin Liu, Fuqing Zhu, Liangjun Zang, Wei Zhou, Jizhong Han, Songlin Hu

Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs.

Clustering Knowledge Graphs

Review-Driven Answer Generation for Product-Related Questions in E-Commerce

1 code implementation27 Apr 2019 Shiqian Chen, Chenliang Li, Feng Ji, Wei Zhou, Haiqing Chen

Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation.

Answer Generation

Feature-Critic Networks for Heterogeneous Domain Generalization

2 code implementations31 Jan 2019 Yiying Li, Yongxin Yang, Wei Zhou, Timothy M. Hospedales

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training.

Domain Generalization

Hierarchical Reinforcement Learning for Multi-agent MOBA Game

no code implementations23 Jan 2019 Zhijian Zhang, Haozheng Li, Luo Zhang, Tianyin Zheng, Ting Zhang, Xiong Hao, Xiaoxin Chen, Min Chen, Fangxu Xiao, Wei Zhou

Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information.

Hierarchical Reinforcement Learning Imitation Learning +4

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection

1 code implementation4 Dec 2018 Yongchao Xu, Yukang Wang, Wei Zhou, Yongpan Wang, Zhibo Yang, Xiang Bai

Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500.

Scene Text Detection Text Detection

Unsupervised Single Image Deraining with Self-supervised Constraints

no code implementations21 Nov 2018 Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, Wei Zhou

Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications.

Benchmarking Generative Adversarial Network +1

Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving

no code implementations24 Oct 2018 Wei Zhou, Julie Stephany Berrio, Stewart Worrall, Eduardo Nebot

This paper presents a novel method for analysing the robustness of semantic segmentation models and provides a number of metrics to evaluate the classification performance over a variety of environmental conditions.

Autonomous Driving General Classification +2

Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective

no code implementations13 Sep 2018 Wei Zhou, Alex Zyner, Stewart Worrall, Eduardo Nebot

Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles.

Autonomous Vehicles Data Augmentation +2

A Deep Relevance Model for Zero-Shot Document Filtering

1 code implementation ACL 2018 Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen

In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.

Sentiment Analysis Text Classification +1

Histograms of Gaussian normal distribution for feature matching in clutter scenes

no code implementations19 Jun 2017 Wei Zhou, Caiwen Ma, Arjan Kuijper

Especially in cluttered scenes there are many feature mismatches between scenes and models.

CFAR Line Detector for Polarimetric SAR Images Using Wilks’ Test Statistic

no code implementations1 May 2016 Ruijin Jin, Wei Zhou, Junjun Yin, and Jian Yang

In this letter, a constant false-alarm rate line detector for polarimetric synthetic aperture radar (Pol-SAR) images is presented based on Wilks’ test statistic, which can be used to test the equality of two covariance matrices following the complex Wishart distribution.

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