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).
no code implementations • Findings (ACL) 2022 • Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
no code implementations • COLING 2022 • Lingwei Wei, Dou Hu, Yantong Lai, Wei Zhou, Songlin Hu
Fake news’s quick propagation on social media brings severe social ramifications and economic damage.
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.
1 code implementation • 9 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.
no code implementations • 7 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.
1 code implementation • 29 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.
no code implementations • 23 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.
no code implementations • 30 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.
no code implementations • 8 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.
no code implementations • 21 Feb 2024 • Shutong Qiao, Chen Gao, Junhao Wen, Wei Zhou, Qun Luo, Peixuan Chen, Yong Li
However, constrained by high time and space costs, as well as the brief and anonymous nature of session data, the first LLM recommendation framework suitable for industrial deployment has yet to emerge in the field of SBR.
no code implementations • 22 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.
1 code implementation • 21 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.
no code implementations • 12 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.
no code implementations • 12 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.
no code implementations • 29 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.
no code implementations • 25 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.
no code implementations • 21 Nov 2023 • Mengyang Chen, Lingwei Wei, Han Cao, Wei Zhou, Songlin Hu
In this paper, we present a comprehensive empirical study to explore the performance of LLMs on misinformation detection tasks.
no code implementations • 4 Nov 2023 • Wei Zhou
The study will include real-life observations and experiments from the previous research.
1 code implementation • 30 Oct 2023 • Zhenpeng Su, Xing Wu, Xue Bai, Zijia Lin, Hui Chen, Guiguang Ding, Wei Zhou, Songlin Hu
Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
Ranked #89 on Multi-task Language Understanding on MMLU
1 code implementation • 22 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.
1 code implementation • 21 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).
no code implementations • 15 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.
no code implementations • 15 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.
no code implementations • 15 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.
no code implementations • 15 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.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 25 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.
1 code implementation • 6 Sep 2023 • Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, Songlin Hu
ChatGPT has gained significant interest due to its impressive performance, but people are increasingly concerned about its potential risks, particularly around the detection of AI-generated content (AIGC), which is often difficult for untrained humans to identify.
no code implementations • 9 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.
no code implementations • 28 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.
no code implementations • 27 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.
1 code implementation • 7 Jun 2023 • Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma, Songlin Hu
Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history.
Ranked #1 on Conversational Response Selection on E-commerce
1 code implementation • 2 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.
Ranked #4 on Emotion Recognition in Conversation on EmoryNLP
1 code implementation • 1 Jun 2023 • Dou Hu, Lingwei Wei, Yaxin Liu, Wei Zhou, Songlin Hu
To alleviate these, we propose a generalized multilingual system SACL-XLMR for sentiment analysis on low-resource languages.
Ranked #1 on Zero-shot Sentiment Classification on AfriSenti
no code implementations • 28 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.
no code implementations • 24 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.
no code implementations • 10 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.
no code implementations • 5 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.
no code implementations • 18 Apr 2023 • Haolan Zhan, Xuming Lin, Shaobo Cui, Zhongzhou Zhao, Wei Zhou, Haiqing Chen
Specifically, tabular data and persona information are firstly represented as latent variables separately.
no code implementations • 30 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.
1 code implementation • 25 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.
no code implementations • 24 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.
no code implementations • 16 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.
no code implementations • 24 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.
1 code implementation • 18 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.
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.
no code implementations • 7 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
no code implementations • 22 Nov 2022 • Wei Zhou, Ruizeng Zhang, Leida Li, Hantao Liu, Huiyan Chen
Image dehazing aims to restore spatial details from hazy images.
1 code implementation • 12 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.
no code implementations • 11 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.
1 code implementation • 7 Nov 2022 • Andrey Ignatov, Radu Timofte, Shuai Liu, Chaoyu Feng, Furui Bai, Xiaotao Wang, Lei Lei, Ziyao Yi, Yan Xiang, Zibin Liu, Shaoqing Li, Keming Shi, Dehui Kong, Ke Xu, Minsu Kwon, Yaqi Wu, Jiesi Zheng, Zhihao Fan, Xun Wu, Feng Zhang, Albert No, Minhyeok Cho, Zewen Chen, Xiaze Zhang, Ran Li, Juan Wang, Zhiming Wang, Marcos V. Conde, Ui-Jin Choi, Georgy Perevozchikov, Egor Ershov, Zheng Hui, Mengchuan Dong, Xin Lou, Wei Zhou, Cong Pang, Haina Qin, Mingxuan Cai
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing.
1 code implementation • 26 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
no code implementations • SemTab@ISWC 2022 • Xinhe Li, Shuxin Wang, Wei Zhou, Gongrui Zhang, Chenghuan Jiang, Tianyu Hong and Peng Wang
This paper presents the results of KGCODE-Tab in the tabular data to knowledge graph matching contest SemTab 2022.
Ranked #1 on Column Type Annotation on ToughTables-DBP
no code implementations • 6 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.
3 code implementations • 28 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.
no code implementations • 7 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.
no code implementations • 31 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.
1 code implementation • 15 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.
no code implementations • 13 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.
no code implementations • 7 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.
no code implementations • 12 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.
no code implementations • 4 May 2022 • Yinan Bao, Qianwen Ma, Lingwei Wei, Wei Zhou, Songlin Hu
Besides, a clause graph is also established to model coarse-grained semantic relations between clauses.
no code implementations • 22 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.
1 code implementation • 7 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).
no code implementations • 31 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.
no code implementations • 25 Feb 2022 • Wei Zhou, Xiongkuo Min, Hong Li, Qiuping Jiang
In this paper, we provide a brief overview of adaptive video streaming quality assessment.
no code implementations • 13 Nov 2021 • Yu Qiao, Sourabh Zanwar, Rishab Bhattacharyya, Daniel Wiechmann, Wei Zhou, Elma Kerz, Ralf Schlüter
One of the key communicative competencies is the ability to maintain fluency in monologic speech and the ability to produce sophisticated language to argue a position convincingly.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 11 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.
no code implementations • 1 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.
no code implementations • 25 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.
no code implementations • 13 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.
no code implementations • 13 Sep 2021 • Guohai Xu, Hehong Chen, Feng-Lin Li, Fu Sun, Yunzhou Shi, Zhixiong Zeng, Wei Zhou, Zhongzhou Zhao, Ji Zhang
Live streaming is becoming an increasingly popular trend of sales in E-commerce.
no code implementations • 18 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.
no code implementations • 17 Aug 2021 • Shaobo Cui, Xintong Bao, Xuming Lin, Zhongzhou Zhao, Ji Zhang, Wei Zhou, Haiqing Chen
Each one-to-one mapping is associated with a conditional generation pattern and is modeled with an expert in SPMoE.
no code implementations • 1 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.
no code implementations • ACL 2021 • Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu
Multi-label text classification is one of the fundamental tasks in natural language processing.
no code implementations • 28 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.
no code implementations • 28 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.
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.
no code implementations • 7 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.
1 code implementation • 17 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.
Ranked #1 on Session-Based Recommendations on Last.FM
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.
no code implementations • 19 May 2021 • Jun Fu, Chen Hou, Wei Zhou, Jiahua Xu, Zhibo Chen
In the hypergraph construction, we build a location-based hyperedge and a content-based hyperedge for each viewport.
1 code implementation • 15 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.
no code implementations • 10 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.
no code implementations • 30 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.
no code implementations • 19 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
no code implementations • 17 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.
no code implementations • 13 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
no code implementations • 1 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.
no code implementations • 22 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.
no code implementations • 27 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.
no code implementations • 18 Jan 2021 • Xiangzhuo Xing, Yue Sun, Xiaolei Yi, Meng Li, Jiajia Feng, Yan Meng, Yufeng Zhang, Wenchong Li, Nan Zhou, Xiude He, Jun-Yi Ge, Wei Zhou, Tsuyoshi Tamegai, Zhixiang Shi
FeSe$_{1-x}$Te$_{x}$ superconductors manifest some intriguing electronic properties depending on the value of $x$.
Superconductivity Materials Science
no code implementations • 1 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.
1 code implementation • COLING 2020 • Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu
In this way, we can explicitly exploit the credibility of publishers and users for early fake news detection.
no code implementations • 1 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.
1 code implementation • 1 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.
no code implementations • 30 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.
no code implementations • 15 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.
Ranked #2 on Traffic Prediction on SZ-Taxi
1 code implementation • 26 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.
1 code implementation • 18 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.
no code implementations • 17 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.
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.
no code implementations • 10 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.
no code implementations • ECCV 2020 • Xin Li, Xin Jin, Jianxin Lin, Tao Yu, Sen Liu, Yaojun Wu, Wei Zhou, Zhibo Chen
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions.
1 code implementation • 16 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.
no code implementations • 23 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.
no code implementations • 9 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.
1 code implementation • 25 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.
1 code implementation • 19 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
no code implementations • 13 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.
2 code implementations • 7 Apr 2020 • Changlu Guo, Márton Szemenyei, Yugen Yi, Ying Xue, Wei Zhou, Yangyuan Li
But for other retinal imaging modalities, more research is needed to explore vascular extraction.
2 code implementations • 7 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.
no code implementations • 6 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.
no code implementations • 2 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.
1 code implementation • NeurIPS 2020 • Wei Zhou, Yiying Li, Yongxin Yang, Huaimin Wang, Timothy M. Hospedales
Off-Policy Actor-Critic (Off-PAC) methods have proven successful in a variety of continuous control tasks.
1 code implementation • 9 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.
1 code implementation • 7 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.
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.
Ranked #5 on Conversational Response Selection on RRS
1 code implementation • 18 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.
no code implementations • 28 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.
no code implementations • 10 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.
1 code implementation • 10 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.
no code implementations • 5 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.
1 code implementation • 4 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 code implementations • 17 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.
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.
no code implementations • 1 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.
no code implementations • 12 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.
no code implementations • 31 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.
2 code implementations • 25 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.
1 code implementation • 27 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.
2 code implementations • 31 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.
Ranked #111 on Domain Generalization on PACS
no code implementations • 23 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.
1 code implementation • 4 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.
Ranked #22 on Scene Text Detection on Total-Text
no code implementations • 21 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.
no code implementations • 24 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.
1 code implementation • 1 Oct 2018 • Ye Yuan, Xiuchuan Tang, Wei Pan, Xiuting Li, Wei Zhou, Hai-Tao Zhang, Han Ding, Jorge Goncalves
Cyber-physical systems (CPSs) embed software into the physical world.
no code implementations • 13 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.
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.
no code implementations • ACL 2018 • Minghui Qiu, Liu Yang, Feng Ji, Weipeng Zhao, Wei Zhou, Jun Huang, Haiqing Chen, W. Bruce Croft, Wei. Lin
Building multi-turn information-seeking conversation systems is an important and challenging research topic.
no code implementations • 19 Jun 2017 • Wei Zhou, Caiwen Ma, Arjan Kuijper
Especially in cluttered scenes there are many feature mismatches between scenes and models.
no code implementations • 1 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.