no code implementations • ACL 2022 • Kunyuan Pang, Haoyu Zhang, Jie zhou, Ting Wang
In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems.
no code implementations • 19 Jan 2024 • Yichen Chen, Yiqi Pan, Ruyu Liu, Haoyu Zhang, Guodao Zhang, Bo Sun, Jianhua Zhang
To enhance the performance and effect of AR/VR applications and visual assistance and inspection systems, visual simultaneous localization and mapping (vSLAM) is a fundamental task in computer vision and robotics.
no code implementations • 5 Nov 2023 • Huan Cui, Jie Cao, Qun Hao, Haoyu Zhang, Chang Zhou
At a sampling ratio of 0. 0084 referring to HR FSI with 1024*768 pixels, experimentally, by UFFSI with 255*341 cells of 89% reduction in data redundancy, the ROI has a significantly better imaging quality to meet imaging needs.
no code implementations • 11 Oct 2023 • Haoyu Zhang, Meng Liu, YaoWei Wang, Da Cao, Weili Guan, Liqiang Nie
In response to this gap, we present an iterative tracking and reasoning strategy that amalgamates a textual encoder, a visual encoder, and a generator.
1 code implementation • 9 Oct 2023 • Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu
Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e. g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.
Ranked #1 on Multimodal Sentiment Analysis on CMU-MOSEI (Acc-7 metric)
1 code implementation • 28 Sep 2023 • Yangyang Guo, Haoyu Zhang, Yongkang Wong, Liqiang Nie, Mohan Kankanhalli
Learning a versatile language-image model is computationally prohibitive under a limited computing budget.
no code implementations • 25 Sep 2023 • Qiaoling Yang, Linkai Luo, Haoyu Zhang, Hong Peng, Ziyang Chen
To address this, we propose a sample attention memory network (SAMN) that effectively combines SVM and NN by incorporating sample attention module, class prototypes, and memory block to NN.
no code implementations • 9 Aug 2023 • Zhang-Hua Fu, Sipeng Sun, Jintong Ren, Tianshu Yu, Haoyu Zhang, Yuanyuan Liu, Lingxiao Huang, Xiang Yan, Pinyan Lu
Fair comparisons based on nineteen famous large-scale instances (with 10, 000 to 10, 000, 000 cities) show that HDR is highly competitive against existing state-of-the-art TSP algorithms, in terms of both efficiency and solution quality.
no code implementations • 12 Jul 2023 • Yipeng Leng, Qiangjuan Huang, Zhiyuan Wang, Yangyang Liu, Haoyu Zhang
To further explore the latent space of Diff-AE and achieve a generic editing pipeline, we proposed a module called Group-supervised AutoEncoder(dubbed GAE) for Diff-AE to achieve better disentanglement on the latent code.
no code implementations • 27 Jun 2023 • Yahuan Cong, Haoyu Zhang, Haopeng Lin, Shichao Liu, Chunfeng Wang, Yi Ren, Xiang Yin, Zejun Ma
Cross-lingual timbre and style generalizable text-to-speech (TTS) aims to synthesize speech with a specific reference timbre or style that is never trained in the target language.
no code implementations • 20 Jun 2023 • Yu Zhang, Long Cheng, Xiuze Xia, Haoyu Zhang
The proposed approach involves the estimation of full stiffness matrices from human demonstrations, which are then combined with sensed forces and motion information to create a model using the non-parametric method.
no code implementations • 4 May 2023 • Yuanyuan Liu, Haoyu Zhang, Yibing Zhan, Zijing Chen, Guanghao Yin, Lin Wei, Zhe Chen
To this end, we present a novel paradigm that attempts to extract noise-resistant features in its pipeline and introduces a noise-aware learning scheme to effectively improve the robustness of multimodal emotion understanding.
no code implementations • 2 Mar 2023 • Chunfeng Wang, Peisong Huang, Yuxiang Zou, Haoyu Zhang, Shichao Liu, Xiang Yin, Zejun Ma
As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations.
no code implementations • 17 Aug 2022 • Marcel Grimmer, Haoyu Zhang, Raghavendra Ramachandra, Kiran Raja, Christoph Busch
The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism.
no code implementations • 3 Jun 2022 • Shiqing Liu, Haoyu Zhang, Yaochu Jin
Neural architecture search (NAS) has become increasingly popular in the deep learning community recently, mainly because it can provide an opportunity to allow interested users without rich expertise to benefit from the success of deep neural networks (DNNs).
no code implementations • 5 May 2022 • Dong Zhou, Jie Cao, Huan Cui, Li-Xing Lin, Haoyu Zhang, Yingqiang Zhang, Qun Hao
For the same number of measurements, the method using temporally variable-resolution illumination patterns has better imaging quality than CGI, but it is less robust to noise.
no code implementations • ACL 2022 • Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, ShiLiang Pu, Fei Wu
To achieve effective grounding under a limited annotation budget, we investigate one-shot video grounding, and learn to ground natural language in all video frames with solely one frame labeled, in an end-to-end manner.
no code implementations • 7 Dec 2021 • Marcel Grimmer, Haoyu Zhang, Raghavendra Ramachandra, Kiran Raja, Christoph Busch
Mated samples are generated by manipulating latent vectors, and more precisely, we exploit Principal Component Analysis (PCA) to define semantically meaningful directions in the latent space and control the similarity between the original and the mated samples using a pre-trained face recognition system.
no code implementations • 20 Nov 2021 • Xipei Wang, Haoyu Zhang, Yuanbo Zhang, Meng Wang, Jiarui Song, Tin Lai, Matloob Khushi
Our results show that our model can predict 4-hour future trends with high accuracy in the Forex dataset, which is crucial in realistic scenarios to assist foreign exchange trading decision making.
no code implementations • 17 Sep 2021 • Yuanyuan Liu, Wenbin Wang, Chuanxu Feng, Haoyu Zhang, Zhe Chen, Yibing Zhan
To this end, we propose to decompose each video into a series of expression snippets, each of which contains a small number of facial movements, and attempt to augment the Transformer's ability for modeling intra-snippet and inter-snippet visual relations, respectively, obtaining the Expression snippet Transformer (EST).
Ranked #14 on Dynamic Facial Expression Recognition on DFEW
Dynamic Facial Expression Recognition Facial Expression Recognition +1
no code implementations • 6 Apr 2021 • Haoyu Zhang, Marcel Grimmer, Raghavendra Ramachandra, Kiran Raja, Christoph Busch
Face verification has come into increasing focus in various applications including the European Entry/Exit System, which integrates face recognition mechanisms.
no code implementations • 24 Oct 2020 • Haoyu Zhang, Dingkun Long, Guangwei Xu, Pengjun Xie, Fei Huang, Ji Wang
Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document.
no code implementations • 20 Sep 2020 • Andrew Or, Haoyu Zhang, Michael J. Freedman
In our evaluation, our implementation of VirtualFlow for TensorFlow achieved strong convergence guarantees across different hardware with out-of-the-box hyperparameters, up to 48% lower job completion times with resource elasticity, and up to 42% higher throughput with heterogeneous training.
no code implementations • 12 Sep 2020 • Hangyu Zhu, Haoyu Zhang, Yaochu Jin
Federated learning is a recently proposed distributed machine learning paradigm for privacy preservation, which has found a wide range of applications where data privacy is of primary concern.
Distributed, Parallel, and Cluster Computing
no code implementations • 3 Sep 2020 • Haoyu Zhang, Sushma Venkatesh, Raghavendra Ramachandra, Kiran Raja, Naser Damer, Christoph Busch
Extensive experiments are carried out to assess the FRS's vulnerability against the proposed morphed face generation technique on three types of data such as digital images, re-digitized (printed and scanned) images, and compressed images after re-digitization from newly generated MIPGAN Face Morph Dataset.
no code implementations • 26 Aug 2020 • Mohamed Wahib, Haoyu Zhang, Truong Thao Nguyen, Aleksandr Drozd, Jens Domke, Lingqi Zhang, Ryousei Takano, Satoshi Matsuoka
An alternative solution is to use out-of-core methods instead of, or in addition to, data parallelism.
no code implementations • 7 Jul 2020 • Sushma Venkatesh, Haoyu Zhang, Raghavendra Ramachandra, Kiran Raja, Naser Damer, Christoph Busch
\textit{(i) Can GAN generated morphs threaten Face Recognition Systems (FRS) equally as Landmark based morphs?}
no code implementations • ACL 2020 • Jie Zhou, Chunping Ma, Dingkun Long, Guangwei Xu, Ning Ding, Haoyu Zhang, Pengjun Xie, Gongshen Liu
Hierarchical text classification is an essential yet challenging subtask of multi-label text classification with a taxonomic hierarchy.
General Classification Hierarchical Multi-label Classification +3
no code implementations • 7 Mar 2020 • Haoyu Zhang, Yaochu Jin, Ran Cheng, Kuangrong Hao
Recently, evolutionary neural architecture search (ENAS) has received increasing attention due to the attractive global optimization capability of evolutionary algorithms.
no code implementations • 6 Mar 2020 • Yong Huang, Haoyu Zhang, Hui Li, Stephen Wu
We develop a recovery framework for automatic crack segmentation of compressed crack images based on this new CS method and demonstrate the remarkable performance of the method taking advantage of the strong capability of generative models to capture the necessary features required in the crack segmentation task even the backgrounds of the generated images are not well reconstructed.
1 code implementation • ACL 2019 • Haoyu Zhang, Jingjing Cai, Jianjun Xu, Ji Wang
We conduct experiments on COMPLEXWEBQUESTIONS which is a large scale complex question semantic parsing dataset, results show that our model achieves significant improvement compared to state-of-the-art methods.
Ranked #1 on Semantic Parsing on complexWebQuestions-V1.0
4 code implementations • CONLL 2019 • Haoyu Zhang, Jianjun Xu, Ji Wang
For the decoder, there are two stages in our model, in the first stage, we use a Transformer-based decoder to generate a draft output sequence.
Ranked #30 on Abstractive Text Summarization on CNN / Daily Mail
1 code implementation • 1 Feb 2017 • Haoyu Zhang, Qin Zhang
Edit similarity join is a fundamental problem in data cleaning/integration, bioinformatics, collaborative filtering and natural language processing, and has been identified as a primitive operator for database systems.
Databases