no code implementations • Findings (EMNLP) 2021 • Ping Yu, Yang Zhao, Chunyuan Li, Changyou Chen
To overcome this issue, we propose a graph-based method to extract attribute content and attribute-independent content from input sentences in the YELP dataset and IMDB dataset.
no code implementations • Findings (NAACL) 2022 • Yang Zhao, Hua Qin, Wang Zhenyu, Changxi Zhu, Shihan Wang
It supports evaluating the difficulty of dialogue tasks only using the learning experiences of dialogue policy and skip-level selection according to their learning needs to maximize the learning efficiency.
no code implementations • CCL 2022 • Yang Zhao, Zhang Yuanzhe, Jiang Zhongtao, Ju Yiming, Zhao Jun, Liu Kang
“Explanations can increase the transparency of neural networks and make them more trustworthy.
no code implementations • LREC 2022 • Yang Zhao, Hiroshi Kanayama, Issei Yoshida, Masayasu Muraoka, Akiko Aizawa
To remedy this shortcoming, we present a dependency-tree-based method to construct a Chinese corpus with 151k pairs of sentences and compression based on Chinese language-specific characteristics.
no code implementations • ECCV 2020 • Haoxian Zhang, Yang Zhao, Ronggang Wang
Inspired by classical pyramid energy minimization optical flow algorithms, this paper proposes a recurrent residual pyramid network (RRPN) for video frame interpolation.
2 code implementations • 10 Apr 2024 • Hongru Du, Jianan Zhao, Yang Zhao, Shaochong Xu, Xihong Lin, Yiran Chen, Lauren M. Gardner, Hao, Yang
Forecasting the short-term spread of an ongoing disease outbreak is a formidable challenge due to the complexity of contributing factors, some of which can be characterized through interlinked, multi-modality variables such as epidemiological time series data, viral biology, population demographics, and the intersection of public policy and human behavior.
no code implementations • 5 Mar 2024 • Zhen Gong, Lvyin Niu, Yang Zhao, Miao Xu, Zhenzhe Zheng, Haoqi Zhang, Zhilin Zhang, Fan Wu, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng
Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a 7. 01% lift in Gross Merchandise Volume, a 7. 42% lift in Return on Investment, and a 3. 26% lift in ad buy count.
no code implementations • 29 Feb 2024 • Xiaozheng Zheng, Chao Wen, Zhuo Su, Zeran Xu, Zhaohu Li, Yang Zhao, Zhou Xue
In this paper, we delve into the creation of one-shot hand avatars, attaining high-fidelity and drivable hand representations swiftly from a single image.
no code implementations • 18 Feb 2024 • Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Jun Shi, Ting Liu, Bing Qin
Through pretraining on a corpus with various sources, Large Language Models (LLMs) have gained impressive performance.
no code implementations • 11 Feb 2024 • Jie Ren, Yang Zhao, Weichuan Zhang, Changming Sun
The proposed SFDNet has the ability to effectively extract spatial-frequency feature representation from input images, improve the accuracy of image classification, and fundamentally alleviate catastrophic forgetting.
1 code implementation • 3 Feb 2024 • Lixu Wang, Yang Zhao, Jiahua Dong, Ating Yin, Qinbin Li, Xiao Wang, Dusit Niyato, Qi Zhu
Federated Learning (FL) is a privacy-preserving distributed learning approach that is rapidly developing in an era where privacy protection is increasingly valued.
no code implementations • 24 Jan 2024 • Pengcheng Zhao, Yanxiang Chen, Yang Zhao, Wei Jia, Zhao Zhang, Ronggang Wang, Richang Hong
Second, the natural co-occurrence of audio and video is utilized to learn the color semantic correlations between audio and visual scenes.
1 code implementation • 15 Jan 2024 • Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang
AI for drug discovery has been a research hotspot in recent years, and SMILES-based language models has been increasingly applied in drug molecular design.
no code implementations • 3 Jan 2024 • Hexiang Hu, Kelvin C. K. Chan, Yu-Chuan Su, Wenhu Chen, Yandong Li, Kihyuk Sohn, Yang Zhao, Xue Ben, Boqing Gong, William Cohen, Ming-Wei Chang, Xuhui Jia
We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision.
no code implementations • 29 Dec 2023 • Lei Fan, Yang Zhao
Terrain surface roughness, often described abstractly, poses challenges in quantitative characterisation with various descriptors found in the literature.
1 code implementation • NeurIPS 2023 • Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang
A central challenge in this field is to generate molecules with specific properties while also producing a wide range of diverse candidates.
no code implementations • 21 Dec 2023 • Haifeng Huang, Yang Zhao, Zehan Wang, Yan Xia, Zhou Zhao
Thus, to address this issue and enhance model performance on new scenes, we explore the TVG task in an unsupervised domain adaptation (UDA) setting across scenes for the first time, where the video-query pairs in the source scene (domain) are labeled with temporal boundaries, while those in the target scene are not.
2 code implementations • 13 Dec 2023 • Haifeng Huang, Zehan Wang, Rongjie Huang, Luping Liu, Xize Cheng, Yang Zhao, Tao Jin, Zhou Zhao
These tokens capture the object's attributes and spatial relationships with surrounding objects in the 3D scene.
1 code implementation • 13 Dec 2023 • Huaiyuan Ying, Zhengyun Zhao, Yang Zhao, Sihang Zeng, Sheng Yu
Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms.
no code implementations • 8 Dec 2023 • Yang Zhao, Yuxiang Zhang, Yanni Dong, Bo Du
Most change detection models based on vision transformers currently follow a "pretraining then fine-tuning" strategy.
no code implementations • 5 Dec 2023 • Shaoan Xie, Yang Zhao, Zhisheng Xiao, Kelvin C. K. Chan, Yandong Li, Yanwu Xu, Kun Zhang, Tingbo Hou
Our extensive experiments demonstrate the superior performance of our method in terms of visual quality, identity preservation, and text control, showcasing its effectiveness in the context of text-guided subject-driven image inpainting.
no code implementations • 30 Nov 2023 • Zhonghao Wang, Wei Wei, Yang Zhao, Zhisheng Xiao, Mark Hasegawa-Johnson, Humphrey Shi, Tingbo Hou
We further extend our method to a novel image editing task: substituting the subject in an image through textual manipulations.
no code implementations • 28 Nov 2023 • Yang Zhao, Yanwu Xu, Zhisheng Xiao, Tingbo Hou
The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed.
no code implementations • 20 Nov 2023 • Zhichao Zuo, Zhao Zhang, Yan Luo, Yang Zhao, Haijun Zhang, Yi Yang, Meng Wang
This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image.
no code implementations • 14 Nov 2023 • Yanwu Xu, Yang Zhao, Zhisheng Xiao, Tingbo Hou
Text-to-image diffusion models have demonstrated remarkable capabilities in transforming textual prompts into coherent images, yet the computational cost of their inference remains a persistent challenge.
1 code implementation • 30 Oct 2023 • Yang Zhao, Jiaxi Yang, Yiling Tao, Lixu Wang, Xiaoxiao Li, Dusit Niyato
Achieving an optimal equilibrium among these facets is crucial for maintaining the effectiveness and usability of FL systems while adhering to privacy and security standards.
1 code implementation • 13 Oct 2023 • Zehan Wang, Ziang Zhang, Luping Liu, Yang Zhao, Haifeng Huang, Tao Jin, Zhou Zhao
Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for more than three modalities by integrating the knowledge of existing MCR spaces.
no code implementations • 29 Sep 2023 • Yang Zhao, Jiaxi Yang, Wenbo Wang, Helin Yang, Dusit Niyato
Industrial systems demand reliable predictive maintenance strategies to enhance operational efficiency and reduce downtime.
no code implementations • 26 Sep 2023 • Yuan Chen, Zhiliang Ma, Yang Zhao
First, many individual models based on popular and state-of-the-art (SOTA) Swin-Transformer (SwinT) are trained on different real-world BIQA datasets respectively.
1 code implementation • 31 Aug 2023 • Qiang Huang, Jiawei Jiang, Xi Susie Rao, Ce Zhang, Zhichao Han, Zitao Zhang, Xin Wang, Yongjun He, Quanqing Xu, Yang Zhao, Chuang Hu, Shuo Shang, Bo Du
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
1 code implementation • 17 Aug 2023 • Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, Zhou Zhao
This paper presents Chat-3D, which combines the 3D visual perceptual ability of pre-trained 3D representations and the impressive reasoning and conversation capabilities of advanced LLMs to achieve the first universal dialogue systems for 3D scenes.
no code implementations • ICCV 2023 • Lei Shen, Jianlong Jin, Ruixin Zhang, Huaen Li, Kai Zhao, Yingyi Zhang, Jingyun Zhang, Shouhong Ding, Yang Zhao, Wei Jia
Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric.
no code implementations • 25 Jul 2023 • Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao
3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description.
no code implementations • ICCV 2023 • Yang Zhao, Tingbo Hou, Yu-Chuan Su, Xuhui Jia. Yandong Li, Matthias Grundmann
An authentic face restoration system is becoming increasingly demanding in many computer vision applications, e. g., image enhancement, video communication, and taking portrait.
1 code implementation • ICCV 2023 • Zehan Wang, Haifeng Huang, Yang Zhao, Linjun Li, Xize Cheng, Yichen Zhu, Aoxiong Yin, Zhou Zhao
To accomplish this, we design a novel semantic matching model that analyzes the semantic similarity between object proposals and sentences in a coarse-to-fine manner.
1 code implementation • 17 Jul 2023 • Yang Zhao, Zhijie Lin, Daquan Zhou, Zilong Huang, Jiashi Feng, Bingyi Kang
Our experiments show that BuboGPT achieves impressive multi-modality understanding and visual grounding abilities during the interaction with human.
no code implementations • 2 Jun 2023 • Ziyang Zhang, Yang Zhao, Huan Li, Changyao Lin, Jie Liu
Due to limited resources on edge and different characteristics of deep neural network (DNN) models, it is a big challenge to optimize DNN inference performance in terms of energy consumption and end-to-end latency on edge devices.
no code implementations • 25 May 2023 • Ming Gao, Yanwu Xu, Yang Zhao, Tingbo Hou, Chenkai Zhao, Mingming Gong
In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler).
no code implementations • NeurIPS 2023 • Zehan Wang, Yang Zhao, Xize Cheng, Haifeng Huang, Jiageng Liu, Li Tang, Linjun Li, Yongqi Wang, Aoxiong Yin, Ziang Zhang, Zhou Zhao
This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR).
no code implementations • 18 May 2023 • Liangchen Song, Liangliang Cao, Hongyu Xu, Kai Kang, Feng Tang, Junsong Yuan, Yang Zhao
The proposed framework consists of two significant components: Geometry Guided Diffusion and Mesh Optimization.
no code implementations • 16 May 2023 • Di Xu, Yang Zhao, Xiang Hao, Xin Meng
We introduce a novel dataset consisting of images depicting pink eggs that have been identified as Pomacea canaliculata eggs, accompanied by corresponding bounding box annotations.
1 code implementation • 9 May 2023 • Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong
Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.
no code implementations • 9 May 2023 • Yang Zhao, Shang Wu, Jingqun Zhang, Sixu Li, Chaojian Li, Yingyan Lin
Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive training time.
no code implementations • 9 May 2023 • Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong
Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence.
no code implementations • 1 May 2023 • Ziyang Zhang, Huan Li, Yang Zhao, Changyao Lin, Jie Liu
As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time.
no code implementations • 14 Apr 2023 • Yu-Chuan Su, Kelvin C. K. Chan, Yandong Li, Yang Zhao, Han Zhang, Boqing Gong, Huisheng Wang, Xuhui Jia
Our approach greatly reduces the overhead for personalized image generation and is more applicable in many potential applications.
no code implementations • CVPR 2023 • Haoyuan Li, Hao Jiang, Tao Jin, Mengyan Li, Yan Chen, Zhijie Lin, Yang Zhao, Zhou Zhao
Then, we present two cooperative seekers to simultaneously search the image for PR and localize the product for PG.
no code implementations • 5 Apr 2023 • Xuhui Jia, Yang Zhao, Kelvin C. K. Chan, Yandong Li, Han Zhang, Boqing Gong, Tingbo Hou, Huisheng Wang, Yu-Chuan Su
This paper proposes a method for generating images of customized objects specified by users.
1 code implementation • 24 Mar 2023 • Weide Liu, Zhonghua Wu, Yang Zhao, Yuming Fang, Chuan-Sheng Foo, Jun Cheng, Guosheng Lin
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes.
no code implementations • 21 Mar 2023 • Yang Zhao, Jianwen Xie, Ping Li
The proposed algorithm consists of two learning stages: (i) Cooperative initialization stage: The discriminator of GAN is treated as an energy-based model (EBM) and is optimized via maximum likelihood estimation (MLE), with the help of the GAN's generator to provide synthetic data to approximate the learning gradients.
no code implementations • 12 Jan 2023 • Yang Zhao, Lei Fan, Hyungjoon Seo
Retaining walls are often built to prevent excessive lateral movements of the ground surrounding an excavation site.
no code implementations • CVPR 2023 • Ning Zhang, Yuyao Ye, Yang Zhao, Ronggang Wang
In this paper, we revisit the stack-based ITM approaches and propose a novel method to reconstruct HDR radiance from a single image, which only needs to estimate two exposure images.
1 code implementation • 13 Dec 2022 • Bin Wang, Yan Song, Fanming Wang, Yang Zhao, Xiangbo Shu, Yan Rui
To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization.
no code implementations • 6 Dec 2022 • Yang Zhao, Junnan Zhu, Lu Xiang, Jiajun Zhang, Yu Zhou, FeiFei Zhai, Chengqing Zong
To alleviate the CF, we investigate knowledge distillation based life-long learning methods.
no code implementations • 18 Nov 2022 • Yanyan Wei, Zhao Zhang, ZhongQiu Zhao, Yang Zhao, Richang Hong, Yi Yang
Stereo images, containing left and right view images with disparity, are utilized in solving low-vision tasks recently, e. g., rain removal and super-resolution.
no code implementations • 14 Nov 2022 • Xiaopei Wu, Yang Zhao, Liang Peng, Hua Chen, Xiaoshui Huang, Binbin Lin, Haifeng Liu, Deng Cai, Wanli Ouyang
When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them.
2 code implementations • 24 Oct 2022 • Huihong Shi, Haoran You, Yang Zhao, Zhongfeng Wang, Yingyan Lin
Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications.
1 code implementation • 18 Oct 2022 • Haoran You, Zhanyi Sun, Huihong Shi, Zhongzhi Yu, Yang Zhao, Yongan Zhang, Chaojian Li, Baopu Li, Yingyan Lin
Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations.
no code implementations • 13 Oct 2022 • Hang Yin, Zitao Zhang, Zhurong Wang, Yilmazcan Ozyurt, Weiming Liang, Wenyu Dong, Yang Zhao, Yinan Shan
Our experiments show that embedding features learned from similarity based behavioral graph have achieved significant performance increase to the baseline fraud detection model in various business scenarios.
no code implementations • 9 Oct 2022 • Khoa D. Doan, Jianwen Xie, Yaxuan Zhu, Yang Zhao, Ping Li
Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data.
1 code implementation • 8 Oct 2022 • Cong Ma, Yaping Zhang, Mei Tu, Xu Han, Linghui Wu, Yang Zhao, Yu Zhou
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research.
1 code implementation • 1 Sep 2022 • Yan Xia, Zhou Zhao, Shangwei Ye, Yang Zhao, Haoyuan Li, Yi Ren
To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise.
1 code implementation • 23 Aug 2022 • Dewang Hou, Yuanyuan Du, Kai Zhao, Yang Zhao
With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems.
1 code implementation • 21 Aug 2022 • Yang Zhao, Peng Guo, Han Gao, Xiuwan Chen
Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e. g., cross-domain semantic segmentation.
no code implementations • 20 Aug 2022 • Yang Zhao, Wenqiang Xu, Xuan Lin, Jingjing Huo, Hong Chen, Zhou Zhao
The task of argument mining aims to detect all possible argumentative components and identify their relationships automatically.
no code implementations • 24 Jul 2022 • Yang Zhao, Yongan Zhang, Yonggan Fu, Xu Ouyang, Cheng Wan, Shang Wu, Anton Banta, Mathews M. John, Allison Post, Mehdi Razavi, Joseph Cavallaro, Behnaam Aazhang, Yingyan Lin
This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation.
no code implementations • 2 Jul 2022 • Yang Zhao, Yan Song
To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels iteratively based on the output of a segmentation model and the timestamp annotations.
no code implementations • 10 Jun 2022 • Yang Zhao, Xuan Lin, Wenqiang Xu, Maozong Zheng, Zhengyong Liu, Zhou Zhao
In recent days, streaming technology has greatly promoted the development in the field of livestream.
no code implementations • 25 May 2022 • Mingxuan Lu, Zhichao Han, Susie Xi Rao, Zitao Zhang, Yang Zhao, Yinan Shan, Ramesh Raghunathan, Ce Zhang, Jiawei Jiang
Apart from rule-based and machine learning filters that are already deployed in production, we want to enable efficient real-time inference with graph neural networks (GNNs), which is useful to catch multihop risk propagation in a transaction graph.
no code implementations • 6 May 2022 • Wanting Lyu, Yue Xiu, Yang Zhao, Chadi Assi, Zhongpei Zhang
In this paper, we investigate an outdoor and indoor wireless communication network with the assistance of a novel relay-aided double-sided reconfigurable intelligent surface (RIS).
no code implementations • 23 Apr 2022 • Yang Zhao, Kai Zhang, Haotian Yu, Yi Zhang, Dongliang Zheng, Jing Han
Simultaneous Localization and Mapping (SLAM) plays an important role in outdoor and indoor applications ranging from autonomous driving to indoor robotics.
1 code implementation • 22 Apr 2022 • Susie Xi Rao, Clémence Lanfranchi, Shuai Zhang, Zhichao Han, Zitao Zhang, Wei Min, Mo Cheng, Yinan Shan, Yang Zhao, Ce Zhang
At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions.
no code implementations • 18 Mar 2022 • Yang Zhao, Hao Zhang, Xiuyuan Hu
Optimizers in RST would perform a Bernoulli trial at each iteration to choose randomly from base algorithms (SGD) and sharpness-aware algorithms (SAM) with a probability arranged by a predefined scheduling function.
no code implementations • 7 Mar 2022 • Yifan Chen, Yang Zhao, Xuelong Li
In this paper, we try to enhance the discrimination of spatio-temporal gait features from two aspects: effective extraction of spatio-temporal gait features and reasonable refinement of extracted features.
1 code implementation • 8 Feb 2022 • Yang Zhao, Hao Zhang, Xiuyuan Hu
In this paper, we propose an effective method to improve the model generalization by additionally penalizing the gradient norm of loss function during optimization.
1 code implementation • 27 Jan 2022 • Yang Zhao, Peng Guo, Zihao Sun, Xiuwan Chen, Han Gao
The performance of a semantic segmentation model for remote sensing (RS) images pretrained on an annotated dataset would greatly decrease when testing on another unannotated dataset because of the domain gap.
no code implementations • 16 Jan 2022 • Yang Zhao, Hao Zhang
NRS leverages the finding that models would benefit from converging to flat minima, and tries to regularize the neighborhood region in weight space to yield approximate outputs.
no code implementations • 26 Nov 2021 • Yang Zhao, Junbin Qiu, Mingshan Xie, Haiping Huang
Binary perceptron is a fundamental model of supervised learning for the non-convex optimization, which is a root of the popular deep learning.
no code implementations • 9 Oct 2021 • Mingxuan Lu, Zhichao Han, Zitao Zhang, Yang Zhao, Yinan Shan
Transaction checkout fraud detection is an essential risk control components for E-commerce marketplaces.
no code implementations • 29 Sep 2021 • Yuan Chai, Liang He, Yang Zhao, Xueyan Li, Zhenxin Wang
The model was evaluated across a wide range of the tasks in time series, which are commonly used to the benchmark of TCN and recurrent networks.
no code implementations • CVPR 2022 • Yang Zhao, Yu-Chuan Su, Chun-Te Chu, Yandong Li, Marius Renn, Yukun Zhu, Changyou Chen, Xuhui Jia
While existing approaches for face restoration make significant progress in generating high-quality faces, they often fail to preserve facial features and cannot authentically reconstruct the faces.
no code implementations • 29 Sep 2021 • Chaojian Li, Xu Ouyang, Yang Zhao, Haoran You, Yonggan Fu, Yuchen Gu, Haonan Liu, Siyuan Miao, Yingyan Lin
Graph Convolutional Networks (GCNs) have gained an increasing attention thanks to their state-of-the-art (SOTA) performance in graph-based learning tasks.
no code implementations • 29 Sep 2021 • Yang Zhao, Yanbo Ma, Yuan Chen, Wei Jia, Ronggang Wang, Xiaoping Liu
Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality.
Ranked #1 on Video Deinterlacing on MSU Deinterlacer Benchmark
no code implementations • 11 Sep 2021 • Yonggan Fu, Yang Zhao, Qixuan Yu, Chaojian Li, Yingyan Lin
The recent breakthroughs of deep neural networks (DNNs) and the advent of billions of Internet of Things (IoT) devices have excited an explosive demand for intelligent IoT devices equipped with domain-specific DNN accelerators.
1 code implementation • 3 Jul 2021 • Jun Wang, Yang Zhao, Linglong Qian, Xiaohan Yu, Yongsheng Gao
The precise detection of blood vessels in retinal images is crucial to the early diagnosis of the retinal vascular diseases, e. g., diabetic, hypertensive and solar retinopathies.
no code implementations • CVPR 2021 • Yang Zhao, Zhou Zhao, Zhu Zhang, Zhijie Lin
Temporal video grounding aims to localize the target segment which is semantically aligned with the given sentence in an untrimmed video.
1 code implementation • 6 Apr 2021 • Xin Wang, Yang Zhao, Tangwen Yang, Qiuqi Ruan
In this paper, we propose a multi-scale context aggregation network (MSCANet) based on single-column encoder-decoder architecture for crowd counting, which consists of an encoder based on a dense context-aware module (DCAM) and a hierarchical attention-guided decoder.
no code implementations • 2 Apr 2021 • Yang Zhao, Hao Zhang
By training DNNs with a wide range of generalization gap on popular datasets, we show that our key quantities and linear model could be efficient tools for estimating the generalization gap of DNNs.
no code implementations • 26 Mar 2021 • Dewang Hou, Yang Zhao, Yuyao Ye, Jiayu Yang, Jian Zhang, Ronggang Wang
Scaling and lossy coding are widely used in video transmission and storage.
1 code implementation • 19 Mar 2021 • Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Yingyan Lin
To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).
Hardware Aware Neural Architecture Search Neural Architecture Search
no code implementations • ICLR 2022 • Yang Zhao, Hao Zhang
We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.
no code implementations • 19 Jan 2021 • Xianlin Song, Ao Teng, Jianshuang Wei, Hao Chen, Yang Zhao, Jianheng Chen, Fangwei Liu, Qianxiang Wan, Guoning Huang, Lingfang Song, Aojie Zhao, Bo Li, Zihao Li, Qiming He, Jinhong Zhang
As a non-destructive biological tissue imaging technology, photoacoustic imaging has important application value in the field of biomedicine.
Biological Physics
no code implementations • 7 Jan 2021 • Zhenyuan Feng, Bruno Clerckx, Yang Zhao
This paper highlights the fact that IRS can provide an extra passive beamforming gain on output DC power over conventional WPT designs and significantly influence the waveform design by leveraging the benefit of passive beamforming, frequency diversity and energy harvester nonlinearity.
Information Theory Signal Processing Information Theory
1 code implementation • 4 Jan 2021 • Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang
Results show that: 1) applied to inference, SD achieves up to 2. 44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10. 56x and 4. 48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines.
no code implementations • 2 Jan 2021 • Ping Yu, Ruiyi Zhang, Yang Zhao, Yizhe Zhang, Chunyuan Li, Changyou Chen
Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision.
no code implementations • ICLR 2021 • Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin
To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e. g., energy cost and latency) of all the networks in the search space of both NAS-Bench-201 and FBNet, considering six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).
Hardware Aware Neural Architecture Search Neural Architecture Search
1 code implementation • ICCV 2021 • Xiaohan Yu, Yang Zhao, Yongsheng Gao, Xiaohui Yuan, Shengwu Xiong
The proposed UFG image dataset and evaluation protocols is intended to serve as a benchmark platform that can advance research of visual classification from approaching human performance to beyond human ability, via facilitating benchmark data of artificial intelligence (AI) not to be limited by the labels of human intelligence (HI).
no code implementations • ICLR 2021 • Yang Zhao, Jianwen Xie, Ping Li
Energy-based models (EBMs) for generative modeling parametrize a single net and can be directly trained by maximum likelihood estimation.
1 code implementation • NeurIPS 2020 • Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources available at the edge and the required massive training costs for state-of-the-art (SOTA) DNNs.
no code implementations • 21 Dec 2020 • Yang Zhao, Wenchao Zhai, Jun Zhao, Tinghao Zhang, Sumei Sun, Dusit Niyato, Kwok-Yan Lam
First, we give an overview of 6G from perspectives of technologies, security and privacy, and applications.
no code implementations • 20 Dec 2020 • Susie Xi Rao, Shuai Zhang, Zhichao Han, Zitao Zhang, Wei Min, Mo Cheng, Yinan Shan, Yang Zhao, Ce Zhang
Massive account registration has raised concerns on risk management in e-commerce companies, especially when registration increases rapidly within a short time frame.
1 code implementation • 10 Dec 2020 • Yang Zhao, Bruno Clerckx, Zhenyuan Feng
To facilitate practical implementation, we also propose a low-complexity design based on closed-form adaptive waveform schemes.
Information Theory Signal Processing Information Theory
no code implementations • 2 Dec 2020 • Yang Zhao, Chunyuan Li, Ping Yu, Changyou Chen
Few-shot learning features the capability of generalizing from a few examples.
no code implementations • COLING 2020 • Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang, Yu Zhou, Chengqing Zong
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized.
1 code implementation • CVPR 2021 • Yang Zhao, Changyou Chen
Instead of explicitly extracting the two codes and applying adaptive instance normalization to combine them, our latent EBM can implicitly learn to transport the source style code to the target style code while preserving the content code, an advantage over existing image translation methods.
no code implementations • 27 Nov 2020 • Yang Zhao, Wei Jia, Ronggang Wang
Traditional deinterlacing approaches are mainly focused on early interlacing scanning systems and thus cannot handle the complex and complicated artifacts in real-world early interlaced videos.
1 code implementation • 24 Nov 2020 • Susie Xi Rao, Shuai Zhang, Zhichao Han, Zitao Zhang, Wei Min, Zhiyao Chen, Yinan Shan, Yang Zhao, Ce Zhang
At online retail platforms, it is crucial to actively detect the risks of transactions to improve customer experience and minimize financial loss.
no code implementations • 2 Nov 2020 • Yang Zhao, Hao Zhang, Xiuyuan Hu
Identifying the role of network units in deep neural networks (DNNs) is critical in many aspects including giving understandings on the mechanisms of DNNs and building basic connections between deep learning and neuroscience.
1 code implementation • COLING 2020 • Vitou Phy, Yang Zhao, Akiko Aizawa
For instance, specificity is mandatory in a food-ordering dialogue task, whereas fluency is preferred in a language-teaching dialogue system.
no code implementations • EMNLP 2020 • Xiaomian Kang, Yang Zhao, Jiajun Zhang, Chengqing Zong
Specifically, we introduce a selection module that is independent of the translation module to score each candidate context sentence.
1 code implementation • EMNLP 2020 • Ryosuke Kohita, Akifumi Wachi, Yang Zhao, Ryuki Tachibana
Q-learning is leveraged to train the agent to produce proper edit actions.
1 code implementation • 5 Oct 2020 • Rishikesh Magar, Lalit Ghule, Junhan Li, Yang Zhao, Amir Barati Farimani
In this work, we analyze vibration signal data of mechanical systems with bearings by combining different signal processing methods and coupling them with machine learning techniques to classify different types of bearing faults.
Ranked #2 on Classification on CWRU Bearing Dataset (using extra training data)
1 code implementation • ECCV 2020 • Ping Yu, Yang Zhao, Chunyuan Li, Junsong Yuan, Changyou Chen
Generating long-range skeleton-based human actions has been a challenging problem since small deviations of one frame can cause a malformed action sequence.
Ranked #2 on Human action generation on NTU RGB+D 2D
no code implementations • WS 2020 • Qian Wang, Yuchen Liu, Cong Ma, Yu Lu, Yining Wang, Long Zhou, Yang Zhao, Jiajun Zhang, Cheng-qing Zong
This paper describes the CASIA{'}s system for the IWSLT 2020 open domain translation task.
no code implementations • 8 Jun 2020 • Hans Albert Lianto, Yang Zhao, Jun Zhao
In a case where the aggregator is untrusted and LDP is not applied to each user gradient, the aggregator can recover sensitive user data from these gradients.
no code implementations • 7 May 2020 • Yang Zhao, Xiaohan Chen, Yue Wang, Chaojian Li, Haoran You, Yonggan Fu, Yuan Xie, Zhangyang Wang, Yingyan Lin
We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs).
no code implementations • 3 May 2020 • Weitao Li, Pengfei Xu, Yang Zhao, Haitong Li, Yuan Xie, Yingyan Lin
Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost.
1 code implementation • ICLR 2020 • Zhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen
Specifically, we propose a Bayesian meta sampling framework consisting of two main components: a meta sampler and a sample adapter.
no code implementations • 22 Apr 2020 • Yang Zhao, Ping Yu, Suchismit Mahapatra, Qinliang Su, Changyou Chen
Variational autoencoders (VAEs) are essential tools in end-to-end representation learning.
no code implementations • 19 Apr 2020 • Yang Zhao, Jun Zhao, Mengmeng Yang, Teng Wang, Ning Wang, Lingjuan Lyu, Dusit Niyato, Kwok-Yan Lam
To avoid the privacy threat and reduce the communication cost, in this paper, we propose to integrate federated learning and local differential privacy (LDP) to facilitate the crowdsourcing applications to achieve the machine learning model.
2 code implementations • ICML 2020 • Yang Zhao, Chunyuan Li, Ping Yu, Jianfeng Gao, Changyou Chen
The instability in GAN training has been a long-standing problem despite remarkable research efforts.
Ranked #1 on Conditional Image Generation on CIFAR-100
no code implementations • 20 Mar 2020 • Xin-Yu Zhang, Yang Zhao, Hao Zhang
A wealth of angle problems occur when facial recognition is performed: At present, the feature extraction network presents eigenvectors with large differences between the frontal face and profile face recognition of the same person in many cases.
no code implementations • 2 Mar 2020 • Hongjie Wang, Yang Zhao, Chaojian Li, Yue Wang, Yingyan Lin
The excellent performance of modern deep neural networks (DNNs) comes at an often prohibitive training cost, limiting the rapid development of DNN innovations and raising various environmental concerns.
no code implementations • 26 Feb 2020 • Yang Zhao, Chaojian Li, Yue Wang, Pengfei Xu, Yongan Zhang, Yingyan Lin
The recent breakthroughs in deep neural networks (DNNs) have spurred a tremendously increased demand for DNN accelerators.
1 code implementation • CVPR 2020 • Zhu Zhang, Zhou Zhao, Yang Zhao, Qi. Wang, Huasheng Liu, Lianli Gao
In this paper, we consider a novel task, Spatio-Temporal Video Grounding for Multi-Form Sentences (STVG).
1 code implementation • 6 Jan 2020 • Pengfei Xu, Xiaofan Zhang, Cong Hao, Yang Zhao, Yongan Zhang, Yue Wang, Chaojian Li, Zetong Guan, Deming Chen, Yingyan Lin
Specifically, AutoDNNchip consists of two integrated enablers: (1) a Chip Predictor, built on top of a graph-based accelerator representation, which can accurately and efficiently predict a DNN accelerator's energy, throughput, and area based on the DNN model parameters, hardware configuration, technology-based IPs, and platform constraints; and (2) a Chip Builder, which can automatically explore the design space of DNN chips (including IP selection, block configuration, resource balancing, etc.
1 code implementation • AAAI 2019 • Zhenyi Wang, Ping Yu, Yang Zhao, Ruiyi Zhang, Yufan Zhou, Junsong Yuan, Changyou Chen
In this paper, we focus on skeleton-based action generation and propose to model smooth and diverse transitions on a latent space of action sequences with much lower dimensionality.
Ranked #4 on Human action generation on NTU RGB+D 2D
1 code implementation • 2 Dec 2019 • Xiaohan Yu, Yang Zhao, Yongsheng Gao, Shengwu Xiong, Xiaohui Yuan
To address above limitations, this paper proposes a novel Multi-Orientation Region Transform (MORT), which can effectively characterize both contour and structure features simultaneously, for patchy image structure classification.
no code implementations • 5 Nov 2019 • Qing Liu, Beiji Zou, Yang Zhao, Yixiong Liang
To build connections among prediction branches, this paper introduces gradient boosting framework to deep classification model and proposes a gradient boosting network called BoostNet.
no code implementations • IJCNLP 2019 • Xiaoyu Shen, Yang Zhao, Hui Su, Dietrich Klakow
Pointer Generators have been the de facto standard for modern summarization systems.
no code implementations • NeurIPS 2019 • Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang
Extensive simulations and ablation studies, with real energy measurements from an FPGA board, confirm the superiority of our proposed strategies and demonstrate remarkable energy savings for training.
no code implementations • 10 Oct 2019 • Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, Zhichao Han, Bo Li, Wei Min, Xi Rao, Hansheng Ren, Yinan Shan, Yingxia Shao, Yujie Wang, Fan Wu, Hui Xue, Yaming Yang, Zitao Zhang, Yang Zhao, Shuai Zhang, Yujing Wang, Bin Cui, Ce Zhang
Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.
42 code implementations • 20 Aug 2019 • Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
Ranked #1 on Object Detection on COCO test-dev (Hardware Burden metric)
no code implementations • 11 Aug 2019 • Yang Zhao, Yifan Liu, Chunhua Shen, Yongsheng Gao, Shengwu Xiong
To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder.
no code implementations • ACL 2019 • Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa
First, the word graph approach that simply concatenates fragments from multiple sentences may yield non-fluent or ungrammatical compression.
no code implementations • 26 Jun 2019 • Yang Zhao, Jun Zhao, Linshan Jiang, Rui Tan, Dusit Niyato, Zengxiang Li, Lingjuan Lyu, Yingbo Liu
To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging the reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers' data.
39 code implementations • 9 Apr 2019 • Ke Sun, Yang Zhao, Borui Jiang, Tianheng Cheng, Bin Xiao, Dong Liu, Yadong Mu, Xinggang Wang, Wenyu Liu, Jingdong Wang
The proposed approach achieves superior results to existing single-model networks on COCO object detection.
Ranked #7 on Semantic Segmentation on LIP val
2 code implementations • 22 Mar 2019 • Xiaoguang Tu, Jian Zhao, Zi-Hang Jiang, Yao Luo, Mei Xie, Yang Zhao, Linxiao He, Zheng Ma, Jiashi Feng
3D face reconstruction from a single 2D image is a challenging problem with broad applications.
Ranked #7 on Face Alignment on AFLW2000-3D
1 code implementation • 24 Feb 2019 • Jiajun Zhang, Long Zhou, Yang Zhao, Cheng-qing Zong
In this work, we propose a synchronous bidirectional inference model to generate outputs using both left-to-right and right-to-left decoding simultaneously and interactively.
no code implementations • 21 Nov 2018 • Yang Zhao, Jianyi Zhang, Changyou Chen
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models.
no code implementations • ICML 2020 • Jianyi Zhang, Yang Zhao, Changyou Chen
Stochastic particle-optimization sampling (SPOS) is a recently-developed scalable Bayesian sampling framework that unifies stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) algorithms based on Wasserstein gradient flows.
no code implementations • NIPS Workshop CDNNRIA 2018 • Yue Wang, Tan Nguyen, Yang Zhao, Zhangyang Wang, Yingyan Lin, Richard Baraniuk
The prohibitive energy cost of running high-performance Convolutional Neural Networks (CNNs) has been limiting their deployment on resource-constrained platforms including mobile and wearable devices.
no code implementations • EMNLP 2018 • Yang Zhao, Jiajun Zhang, Zhongjun He, Cheng-qing Zong, Hua Wu
One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words.
no code implementations • 26 Sep 2018 • Di Wu, Kun Zhang, Fei Cheng, Yang Zhao, Qi Liu, Chang-An Yuan, De-Shuang Huang
As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.
no code implementations • ACL 2018 • Yang Zhao, Zhiyuan Luo, Akiko Aizawa
We herein present a language-model-based evaluator for deletion-based sentence compression and view this task as a series of deletion-and-evaluation operations using the evaluator.
Ranked #2 on Sentence Compression on Google Dataset
no code implementations • CVPR 2018 • Qian Huang, Weixin Zhu, Yang Zhao, Linsen Chen, Yao Wang, Tao Yue, Xun Cao
In this paper, a new Multispectral Image Intrinsic Decomposition model (MIID) is presented to decompose the shading and reflectance from a single multispectral image.
no code implementations • 25 May 2018 • Yang Zhao, Yining Wang, Jiajun Zhang, Cheng-qing Zong
Neural Machine Translation (NMT) has drawn much attention due to its promising translation performance recently.
no code implementations • 24 Feb 2018 • Qian Huang, Weixin Zhu, Yang Zhao, Linsen Chen, Yao Wang, Tao Yue, Xun Cao
In this paper, a Low Rank Multispectral Image Intrinsic Decomposition model (LRIID) is presented to decompose the shading and reflectance from a single multispectral image.
no code implementations • IJCNLP 2017 • Yining Wang, Yang Zhao, Jiajun Zhang, Cheng-qing Zong, Zhengshan Xue
While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs.
1 code implementation • ICCV 2017 • Xintong Han, Zuxuan Wu, Phoenix X. Huang, Xiao Zhang, Menglong Zhu, Yuan Li, Yang Zhao, Larry S. Davis
This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites.
no code implementations • ACL 2017 • Xiaoyu Shen, Hui Su, Yan-ran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.
no code implementations • 13 Mar 2017 • Yang Zhao, Guoqing Li, Wenjun Xie, Wei Jia, Hai Min, Xiaoping Liu
The GUN consists of an input layer, multiple upsampling and convolutional layers, and an output layer.
no code implementations • 12 Mar 2017 • Yang Zhao, Ronggang Wang, Wei Jia, Jianchao Yang, Wenmin Wang, Wen Gao
The proposed method consists of a learning stage and a reconstructing stage.
no code implementations • 31 May 2015 • Yajun Cui, Yang Zhao, Kafei Xiao, Chenglong Zhang, Lei Wang
Spectral clustering and cloud computing is emerging branch of computer science or related discipline.