no code implementations • 4 May 2024 • Siyuan Yan, Cheng Luo, Zhen Yu, ZongYuan Ge
To address this, we propose a plug-and-play feature augmentation method called LDFS (Language-Guided Diverse Feature Synthesis) to synthesize new domain features and improve existing CLIP fine-tuning strategies.
1 code implementation • 17 Apr 2024 • Xin Li, Kun Yuan, Yajing Pei, Yiting Lu, Ming Sun, Chao Zhou, Zhibo Chen, Radu Timofte, Wei Sun, HaoNing Wu, ZiCheng Zhang, Jun Jia, Zhichao Zhang, Linhan Cao, Qiubo Chen, Xiongkuo Min, Weisi Lin, Guangtao Zhai, Jianhui Sun, Tianyi Wang, Lei LI, Han Kong, Wenxuan Wang, Bing Li, Cheng Luo, Haiqiang Wang, Xiangguang Chen, Wenhui Meng, Xiang Pan, Huiying Shi, Han Zhu, Xiaozhong Xu, Lei Sun, Zhenzhong Chen, Shan Liu, Fangyuan Kong, Haotian Fan, Yifang Xu, Haoran Xu, Mengduo Yang, Jie zhou, Jiaze Li, Shijie Wen, Mai Xu, Da Li, Shunyu Yao, Jiazhi Du, WangMeng Zuo, Zhibo Li, Shuai He, Anlong Ming, Huiyuan Fu, Huadong Ma, Yong Wu, Fie Xue, Guozhi Zhao, Lina Du, Jie Guo, Yu Zhang, huimin zheng, JunHao Chen, Yue Liu, Dulan Zhou, Kele Xu, Qisheng Xu, Tao Sun, Zhixiang Ding, Yuhang Hu
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
1 code implementation • 9 Apr 2024 • Zihan Wang, Siyang Song, Cheng Luo, Songhe Deng, Weicheng Xie, Linlin Shen
Human facial action units (AUs) are mutually related in a hierarchical manner, as not only they are associated with each other in both spatial and temporal domains but also AUs located in the same/close facial regions show stronger relationships than those of different facial regions.
1 code implementation • 4 Apr 2024 • Zhoujian Sun, Cheng Luo, Ziyi Liu, Zhengxing Huang
By utilizing real patient electronic medical record data, we constructed simulated dialogues between virtual patients and doctors and evaluated the diagnostic abilities of our system.
no code implementations • 8 Mar 2024 • Jian Zhu, YuPing Ruan, Jingfei Chang, Cheng Luo
To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection.
2 code implementations • 6 Feb 2024 • Qinliang Lin, Cheng Luo, Zenghao Niu, Xilin He, Weicheng Xie, Yuanbo Hou, Linlin Shen, Siyang Song
Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems.
1 code implementation • 10 Jan 2024 • Siyang Song, Micol Spitale, Cheng Luo, Cristina Palmero, German Barquero, Hengde Zhu, Sergio Escalera, Michel Valstar, Tobias Baur, Fabien Ringeval, Elisabeth Andre, Hatice Gunes
In dyadic interactions, humans communicate their intentions and state of mind using verbal and non-verbal cues, where multiple different facial reactions might be appropriate in response to a specific speaker behaviour.
no code implementations • 21 Nov 2023 • Cheng Luo, Qin Li, Zhao Yan, Mengliang Rao, Yunbo Cao
In this paper, we propose an incorporation external keywords matrices model (IEKM) to address these challenges.
no code implementations • 15 Nov 2023 • Cheng Luo, Jie Hu, Luping Xiang, Kun Yang, Kai-Kit Wong
Intelligent Reflecting Surface (IRS) utilizes low-cost, passive reflecting elements to enhance the passive beam gain, improve Wireless Energy Transfer (WET) efficiency, and enable its deployment for numerous Internet of Things (IoT) devices.
1 code implementation • 2 Nov 2023 • Cheng Luo, Tianle Zhong, Geoffrey Fox
In the evolving landscape of neural network models, one prominent challenge stand out: the significant memory overheads associated with training expansive models.
1 code implementation • 23 Aug 2023 • Yuanbo Hou, Siyang Song, Cheng Luo, Andrew Mitchell, Qiaoqiao Ren, Weicheng Xie, Jian Kang, Wenwu Wang, Dick Botteldooren
Sound events in daily life carry rich information about the objective world.
1 code implementation • 18 Aug 2023 • Zhoujian Sun, Wenzhuo Zhang, Zhengxing Huang, Nai Ding, Cheng Luo
The CTP model combines trajectory prediction and causal discovery to enable accurate prediction of disease progression trajectories and uncover causal relationships between features.
no code implementations • 5 Jul 2023 • Jiaqi Xu, Cheng Luo, Weicheng Xie, Linlin Shen, Xiaofeng Liu, Lu Liu, Hatice Gunes, Siyang Song
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour.
1 code implementation • 11 Jun 2023 • Siyang Song, Micol Spitale, Cheng Luo, German Barquero, Cristina Palmero, Sergio Escalera, Michel Valstar, Tobias Baur, Fabien Ringeval, Elisabeth Andre, Hatice Gunes
The Multi-modal Multiple Appropriate Facial Reaction Generation Challenge (REACT2023) is the first competition event focused on evaluating multimedia processing and machine learning techniques for generating human-appropriate facial reactions in various dyadic interaction scenarios, with all participants competing strictly under the same conditions.
1 code implementation • 25 May 2023 • Cheng Luo, Siyang Song, Weicheng Xie, Micol Spitale, Linlin Shen, Hatice Gunes
ReactFace generates multiple different but appropriate photo-realistic human facial reactions by (i) learning an appropriate facial reaction distribution representing multiple appropriate facial reactions; and (ii) synchronizing the generated facial reactions with the speaker's verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences.
no code implementations • 28 Apr 2023 • Weidong Wang, Cheng Luo, Jiancheng An, Lu Gan, Hongshu Liao, Chau Yuen
As a promising non-password authentication technology, radio frequency (RF) fingerprinting can greatly improve wireless security.
1 code implementation • 31 Mar 2023 • Cheng Zhu, Ying Tan, Shuqi Yang, Jiaqing Miao, JiaYi Zhu, Huan Huang, Dezhong Yao, Cheng Luo
The available evidence suggests that dynamic functional connectivity (dFC) can capture time-varying abnormalities in brain activity in resting-state cerebral functional magnetic resonance imaging (rs-fMRI) data and has a natural advantage in uncovering mechanisms of abnormal brain activity in schizophrenia(SZ) patients.
1 code implementation • 19 Mar 2023 • Zihan Wang, Siyang Song, Cheng Luo, Yuzhi Zhou, shiling Wu, Weicheng Xie, Linlin Shen
This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW).
no code implementations • ICCV 2023 • Xilin He, Qinliang Lin, Cheng Luo, Weicheng Xie, Siyang Song, Feng Liu, Linlin Shen
Recent studies have shown the vulnerability of CNNs under perturbation noises, which is partially caused by the reason that the well-trained CNNs are too biased toward the object texture, i. e., they make predictions mainly based on texture cues.
1 code implementation • 19 Nov 2022 • Siyang Song, Yuxin Song, Cheng Luo, Zhiyuan Song, Selim Kuzucu, Xi Jia, Zhijiang Guo, Weicheng Xie, Linlin Shen, Hatice Gunes
Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data.
1 code implementation • 10 Nov 2022 • Wenwen Liu, Cheng Luo, Hecheng Wang, Fanwang Meng
Conclusions: To the best of our knowledge, this is the largest dataset for VDss, which can be used as the benchmark for computational studies of VDss.
1 code implementation • 26 Oct 2022 • Junliang Chen, Xiaodong Zhao, Cheng Luo, Linlin Shen
Recent mainstream weakly supervised semantic segmentation (WSSS) approaches are mainly based on Class Activation Map (CAM) generated by a CNN (Convolutional Neural Network) based image classifier.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 12 Aug 2022 • Xiangbo Gao, Cheng Luo, Qinliang Lin, Weicheng Xie, Minmin Liu, Linlin Shen, Keerthy Kusumam, Siyang Song
\noindent Traditional L_p norm-restricted image attack algorithms suffer from poor transferability to black box scenarios and poor robustness to defense algorithms.
no code implementations • 7 May 2022 • Chengdong Lan, Hao Yan, Cheng Luo, Tiesong Zhao
At the decoder side, we combine the SI and adjacent viewpoints to reconstruct intermediate views using the GAN generator.
2 code implementations • 2 May 2022 • Cheng Luo, Siyang Song, Weicheng Xie, Linlin Shen, Hatice Gunes
While the relationship between a pair of AUs can be complex and unique, existing approaches fail to specifically and explicitly represent such cues for each pair of AUs in each facial display.
Ranked #3 on Facial Action Unit Detection on DISFA
no code implementations • 18 Apr 2022 • Xun Wang, Bingqing Ke, Xuanping Li, Fangyu Liu, Mingyu Zhang, Xiao Liang, Qiushi Xiao, Cheng Luo, Yue Yu
This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching.
1 code implementation • CVPR 2022 • Cheng Luo, Qinliang Lin, Weicheng Xie, Bizhu Wu, Jinheng Xie, Linlin Shen
Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations.
1 code implementation • ICCV 2021 • Jinheng Xie, Cheng Luo, Xiangping Zhu, Ziqi Jin, Weizeng Lu, Linlin Shen
In the first stage, an activation map generator produces activation maps based on the low-level feature maps in the classifier, such that rich contextual object information is included in an online manner.
no code implementations • 23 Jun 2021 • Jiajie Zou, Yuran Zhang, Peiqing Jin, Cheng Luo, Xunyi Pan, Nai Ding
Each passage was read by at least 26 human readers, who labeled their rationales to answer the question.
no code implementations • 23 Apr 2021 • Cheng Luo, Dayiheng Liu, Chanjuan Li, Li Lu, Jiancheng Lv
The system includes modules such as dialogue topic prediction, knowledge matching and dialogue generation.
no code implementations • 14 Mar 2021 • Cheng Luo, Lei Qu, Youshan Miao, Peng Cheng, Yongqiang Xiong
Distributed deep learning workloads include throughput-intensive training tasks on the GPU clusters, where the Distributed Stochastic Gradient Descent (SGD) incurs significant communication delays after backward propagation, forces workers to wait for the gradient synchronization via a centralized parameter server or directly in decentralized workers.
no code implementations • ACL 2020 • Hang Zhang, Dayiheng Liu, Jiancheng Lv, Cheng Luo
To our knowledge, this is the first attempt to generate punchlines with knowledge enhanced model.
1 code implementation • 14 Apr 2020 • Tuanfei Zhu, Cheng Luo, Jing Li, Siqi Ren, Zhihong Zhang
Many important real-world applications involve time-series data with skewed distribution.
1 code implementation • 8 Aug 2019 • Yue Yin, Chenyan Xiong, Cheng Luo, Zhiyuan Liu
This paper presents a neural document expansion approach (NeuDEF) that enriches document representations for neural ranking models.
3 code implementations • 25 Sep 2018 • Fuli Feng, Xiangnan He, Xiang Wang, Cheng Luo, Yiqun Liu, Tat-Seng Chua
Our RSR method advances existing solutions in two major aspects: 1) tailoring the deep learning models for stock ranking, and 2) capturing the stock relations in a time-sensitive manner.
1 code implementation • 16 Apr 2018 • Qingyao Ai, Keping Bi, Cheng Luo, Jiafeng Guo, W. Bruce Croft
We find that the problem of estimating a propensity model from click data is a dual problem of unbiased learning to rank.
no code implementations • 27 Jun 2016 • Cheng Luo, Richard Yi Da Xu, Yang Xiang
One of the propositions of the dependent random measures is that the atoms of the posterior distribution are shared amongst groups, and hence groups can borrow information from each other.
no code implementations • 16 Apr 2016 • Cheng Luo, Yang Xiang, Richard Yi Da Xu
The key novelty of this model is that we place a temporal constraint amongst the nearby discrete measures $\{G_j\}$ in the form of symmetric Kullback-Leibler (KL) Divergence with a fixed bound $B$.