1 code implementation • ACL 2022 • Zheng Gong, Kun Zhou, Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen
In this paper, we study how to continually pre-train language models for improving the understanding of math problems.
1 code implementation • Findings (NAACL) 2022 • Jinhao Jiang, Kun Zhou, Ji-Rong Wen, Xin Zhao
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems.
1 code implementation • 13 May 2024 • Qi Chen, Xiubo Geng, Corby Rosset, Carolyn Buractaon, Jingwen Lu, Tao Shen, Kun Zhou, Chenyan Xiong, Yeyun Gong, Paul Bennett, Nick Craswell, Xing Xie, Fan Yang, Bryan Tower, Nikhil Rao, Anlei Dong, Wenqi Jiang, Zheng Liu, Mingqin Li, Chuanjie Liu, Zengzhong Li, Rangan Majumder, Jennifer Neville, Andy Oakley, Knut Magne Risvik, Harsha Vardhan Simhadri, Manik Varma, Yujing Wang, Linjun Yang, Mao Yang, Ce Zhang
Recent breakthroughs in large models have highlighted the critical significance of data scale, labels and modals.
no code implementations • 2 May 2024 • Zongyang Du, Junchen Lu, Kun Zhou, Lakshmish Kaushik, Berrak Sisman
A major challenge of expressive VC lies in emotion prosody modeling.
no code implementations • 30 Apr 2024 • Shengjie Ma, Yanlin Weng, Tianjia Shao, Kun Zhou
We introduce 3D Gaussian blendshapes for modeling photorealistic head avatars.
no code implementations • 30 Apr 2024 • Zhexi Peng, Tianjia Shao, Yong liu, Jingke Zhou, Yin Yang, Jingdong Wang, Kun Zhou
We present Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting.
no code implementations • 29 Apr 2024 • Keyang Ye, Qiming Hou, Kun Zhou
We present a deferred shading method to effectively render specular reflection with Gaussian splatting.
no code implementations • 27 Mar 2024 • Keyu Wu, Lingchen Yang, Zhiyi Kuang, Yao Feng, Xutao Han, Yuefan Shen, Hongbo Fu, Kun Zhou, Youyi Zheng
For the interior, we employ a data-driven, multi-view 3D hair reconstruction method.
1 code implementation • 14 Mar 2024 • YiFan Li, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs).
no code implementations • 14 Mar 2024 • Zikang Liu, Kun Zhou, Wayne Xin Zhao, Dawei Gao, Yaliang Li, Ji-Rong Wen
To investigate this issue, we conduct a series of empirical studies, which reveal a significant redundancy within the visual instruction datasets, and show that greatly reducing the amount of several instruction dataset even do not affect the performance.
no code implementations • 17 Feb 2024 • Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang song, Chen Zhu, HengShu Zhu, Ji-Rong Wen
To guarantee the effectiveness, we leverage program language to formulate the multi-hop reasoning process over the KG, and synthesize a code-based instruction dataset to fine-tune the base LLM.
no code implementations • 27 Jan 2024 • Yutao Feng, Xiang Feng, Yintong Shang, Ying Jiang, Chang Yu, Zeshun Zong, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, Yin Yang
We demonstrate the feasibility of integrating physics-based animations of solids and fluids with 3D Gaussian Splatting (3DGS) to create novel effects in virtual scenes reconstructed using 3DGS.
no code implementations • 27 Jan 2024 • Beijia Chen, Yuefan Shen, Qing Shuai, Xiaowei Zhou, Kun Zhou, Youyi Zheng
In this paper, we introduce AniDress, a novel method for generating animatable human avatars in loose clothes using very sparse multi-view videos (4-8 in our setting).
1 code implementation • 11 Jan 2024 • Zhipeng Chen, Kun Zhou, Wayne Xin Zhao, Junchen Wan, Fuzheng Zhang, Di Zhang, Ji-Rong Wen
To address it, we propose a new RL method named \textbf{RLMEC} that incorporates a generative model as the reward model, which is trained by the erroneous solution rewriting task under the minimum editing constraint, and can produce token-level rewards for RL training.
no code implementations • 7 Jan 2024 • Yingqian Min, Kun Zhou, Dawei Gao, Wayne Xin Zhao, He Hu, Yaliang Li
Recently, multi-task instruction tuning has been applied into sentence representation learning, which endows the capability of generating specific representations with the guidance of task instruction, exhibiting strong generalization ability on new tasks.
no code implementations • 30 Dec 2023 • Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen
To better perform reasoning on KG, recent work typically adopts a pre-trained language model~(PLM) to model the question, and a graph neural network~(GNN) based module to perform multi-hop reasoning on the KG.
no code implementations • 2 Dec 2023 • Yumeng Li, YaoXiang Ding, Zhong Ren, Kun Zhou
Explicit pose prior models compress human poses into latent representations for using in pose-related downstream tasks.
no code implementations • 1 Dec 2023 • Yunjie Wu, Yapeng Meng, Zhipeng Hu, Lincheng Li, Haoqian Wu, Kun Zhou, Weiwei Xu, Xin Yu
In the editing stage, we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts.
no code implementations • 22 Nov 2023 • Keyang Ye, Tianjia Shao, Kun Zhou
The learnable code serves as a pose-dependent appearance embedding for refining the erroneous appearance caused by geometric transformation of Gaussians, based on which an appearance refinement model is learned to produce residual Gaussian properties to match the appearance in target pose.
no code implementations • 3 Nov 2023 • Kun Zhou, Yutao Zhu, Zhipeng Chen, Wentong Chen, Wayne Xin Zhao, Xu Chen, Yankai Lin, Ji-Rong Wen, Jiawei Han
Large language models~(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity.
1 code implementation • 2 Nov 2023 • Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen
By conducting a comprehensive empirical study, we find that instructions focused on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs on evaluation benchmarks.
1 code implementation • 26 Oct 2023 • Yifei Peng, Yu Jin, Zhexu Luo, Yao-Xiang Ding, Wang-Zhou Dai, Zhong Ren, Kun Zhou
There are two levels of symbol grounding problems among the core challenges: the first is symbol assignment, i. e. mapping latent factors of neural visual generators to semantic-meaningful symbolic factors from the reasoning systems by learning from limited labeled data.
no code implementations • 9 Oct 2023 • Keyang Ye, Hongzhi Wu, Xin Tong, Kun Zhou
We present the first real-time method for inserting a rigid virtual object into a neural radiance field, which produces realistic lighting and shadowing effects, as well as allows interactive manipulation of the object.
1 code implementation • 22 Sep 2023 • Jia Qi Yip, Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Dianwen Ng, Eng Siong Chng, Bin Ma
Dual-path is a popular architecture for speech separation models (e. g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships.
Ranked #5 on Speech Separation on WSJ0-2mix
1 code implementation • 1 Sep 2023 • Xiaoyu Pan, Bowen Zheng, Xinwei Jiang, Guanglong Xu, Xianli Gu, Jingxiang Li, Qilong Kou, He Wang, Tianjia Shao, Kun Zhou, Xiaogang Jin
Finally, we propose a training regime based on representation learning and data augmentation, by training the model on data with masking.
no code implementations • 7 Aug 2023 • Xiang Feng, Kaizhang Kang, Fan Pei, Huakeng Ding, Jinjiang You, Ping Tan, Kun Zhou, Hongzhi Wu
We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are fed to a multi-view stereo method to enhance 3D reconstruction.
1 code implementation • 21 Jul 2023 • Zhipeng Zhao, Kun Zhou, Xiaolei Wang, Wayne Xin Zhao, Fan Pan, Zhao Cao, Ji-Rong Wen
Conversational recommender systems (CRS) aim to provide the recommendation service via natural language conversations.
1 code implementation • 17 Jul 2023 • Hui Ying, Tianjia Shao, He Wang, Yin Yang, Kun Zhou
Quantitative and qualitative experiments demonstrate that our method outperforms the state-of-the-art methods in shape completion, detail preservation, generalization to unseen geometries, and computational cost.
no code implementations • 19 Jun 2023 • Wayne Xin Zhao, Kun Zhou, Beichen Zhang, Zheng Gong, Zhipeng Chen, Yuanhang Zhou, Ji-Rong Wen, Jing Sha, Shijin Wang, Cong Liu, Guoping Hu
Specially, we construct a Mixture-of-Experts~(MoE) architecture for modeling mathematical text, so as to capture the common mathematical knowledge across tasks.
1 code implementation • 10 Jun 2023 • Kun Zhou, Wenbo Li, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu
To address this, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm that learns a degradation-driven inter-viewpoint mixer.
Ranked #1 on Novel View Synthesis on Tanks and Temples
1 code implementation • 5 Jun 2023 • Xiaolei Wang, Kun Zhou, Xinyu Tang, Wayne Xin Zhao, Fan Pan, Zhao Cao, Ji-Rong Wen
To develop our approach, we characterize user preference and organize the conversation flow by the entities involved in the dialogue, and design a multi-stage recommendation dialogue simulator based on a conversation flow language model.
1 code implementation • NeurIPS 2023 • Beichen Zhang, Kun Zhou, Xilin Wei, Wayne Xin Zhao, Jing Sha, Shijin Wang, Ji-Rong Wen
Based on this finding, we propose a new approach that can deliberate the reasoning steps with tool interfaces, namely \textbf{DELI}.
1 code implementation • 23 May 2023 • Zhipeng Chen, Kun Zhou, Beichen Zhang, Zheng Gong, Wayne Xin Zhao, Ji-Rong Wen
Although large language models (LLMs) have achieved excellent performance in a variety of evaluation benchmarks, they still struggle in complex reasoning tasks which require specific knowledge and multi-hop reasoning.
2 code implementations • 17 May 2023 • YiFan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, Ji-Rong Wen
Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i. e. they tend to generate objects that are inconsistent with the target images in the descriptions.
1 code implementation • 16 May 2023 • Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, Ji-Rong Wen
Specially, we propose an \emph{invoking-linearization-generation} procedure to support LLMs in reasoning on the structured data with the help of the external interfaces.
no code implementations • 6 May 2023 • Kun Zhou, YiFan Li, Wayne Xin Zhao, Ji-Rong Wen
To solve it, we propose Diffusion-NAT, which introduces discrete diffusion models~(DDM) into NAR text-to-text generation and integrates BART to improve the performance.
5 code implementations • 31 Mar 2023 • Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Zhipeng Chen, Jinhao Jiang, Ruiyang Ren, YiFan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jian-Yun Nie, Ji-Rong Wen
To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size.
1 code implementation • CVPR 2023 • Kun Zhou, Wenbo Li, Yi Wang, Tao Hu, Nianjuan Jiang, Xiaoguang Han, Jiangbo Lu
Neural radiance fields (NeRF) show great success in novel view synthesis.
Ranked #1 on Novel View Synthesis on LLFF
1 code implementation • 12 Mar 2023 • YiFan Li, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
In this survey, we review the recent progress in diffusion models for NAR text generation.
no code implementations • CVPR 2023 • Xianmin Xu, Yuxin Lin, Haoyang Zhou, Chong Zeng, Yaxin Yu, Kun Zhou, Hongzhi Wu
We propose a unified structured light, consisting of an LED array and an LCD mask, for high-quality acquisition of both shape and reflectance from a single view.
1 code implementation • 15 Dec 2022 • Kun Zhou, Xiao Liu, Yeyun Gong, Wayne Xin Zhao, Daxin Jiang, Nan Duan, Ji-Rong Wen
Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense vectors.
1 code implementation • 15 Dec 2022 • Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Qinyu Zhang, Ji-Rong Wen
Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense.
2 code implementations • 6 Dec 2022 • Wenbo Li, Xin Yu, Kun Zhou, Yibing Song, Zhe Lin, Jiaya Jia
To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models.
1 code implementation • 2 Dec 2022 • Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
Multi-hop Question Answering over Knowledge Graph~(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question on a large-scale Knowledge Graph (KG).
no code implementations • 25 Nov 2022 • Kun Zhou, Kenkun Liu, Wenbo Li, Xiaoguang Han, Jiangbo Lu
To address those issues, we propose a novel mutual guidance network (MGN) to perform effective bidirectional global-local information exchange while keeping a compact architecture.
4 code implementations • 21 Nov 2022 • Yunfeng Diao, He Wang, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg, Meng Wang
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
no code implementations • 25 Oct 2022 • Kun Zhou, Berrak Sisman, Carlos Busso, Bin Ma, Haizhou Li
To achieve this, we propose a novel EVC framework, Mixed-EVC, which only leverages discrete emotion training labels.
1 code implementation • 21 Oct 2022 • Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan, Weizhu Chen
Thus, we propose a simple ambiguous negatives sampling method, SimANS, which incorporates a new sampling probability distribution to sample more ambiguous negatives.
no code implementations • 11 Aug 2022 • Kun Zhou, Berrak Sisman, Rajib Rana, B. W. Schuller, Haizhou Li
We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework.
1 code implementation • 19 Jun 2022 • Xiaolei Wang, Kun Zhou, Ji-Rong Wen, Wayne Xin Zhao
Our approach unifies the recommendation and conversation subtasks into the prompt learning paradigm, and utilizes knowledge-enhanced prompts based on a fixed pre-trained language model (PLM) to fulfill both subtasks in a unified approach.
Ranked #1 on Text Generation on ReDial
1 code implementation • 13 Jun 2022 • Wayne Xin Zhao, Kun Zhou, Zheng Gong, Beichen Zhang, Yuanhang Zhou, Jing Sha, Zhigang Chen, Shijin Wang, Cong Liu, Ji-Rong Wen
Considering the complex nature of mathematical texts, we design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
no code implementations • CVPR 2022 • Keyu Wu, Yifan Ye, Lingchen Yang, Hongbo Fu, Kun Zhou, Youyi Zheng
To improve the efficiency of a traditional hair growth algorithm, we adopt a local neural implicit function to grow strands based on the estimated 3D hair geometric features.
1 code implementation • 4 May 2022 • Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems.
1 code implementation • 3 May 2022 • Xiaoyu Pan, Jiaming Mai, Xinwei Jiang, Dongxue Tang, Jingxiang Li, Tianjia Shao, Kun Zhou, Xiaogang Jin, Dinesh Manocha
We present a learning algorithm that uses bone-driven motion networks to predict the deformation of loose-fitting garment meshes at interactive rates.
1 code implementation • ACL 2022 • Kun Zhou, Beichen Zhang, Wayne Xin Zhao, Ji-Rong Wen
In DCLR, we design an instance weighting method to punish false negatives and generate noise-based negatives to guarantee the uniformity of the representation space.
1 code implementation • CVPR 2022 • Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang, Jiaya Jia
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem.
Ranked #1 on Image Inpainting on CelebA-HQ
no code implementations • 29 Mar 2022 • Xiaohe Ma, Yaxin Yu, Hongzhi Wu, Kun Zhou
A common, pre-trained latent transform module is also appended to each decoder, to offset the burden of the increased number of decoders.
no code implementations • 20 Mar 2022 • Beijia Chen, Yuefan Shen, Hongbo Fu, Xiang Chen, Kun Zhou, Youyi Zheng
In this paper, we present NeuralReshaper, a novel method for semantic reshaping of human bodies in single images using deep generative networks.
no code implementations • CVPR 2023 • Kun Zhou, Wenbo Li, Xiaoguang Han, Jiangbo Lu
Without the bells and whistles, our plug-and-play TCL is capable of improving the performance of existing VFI frameworks.
Ranked #1 on Video Frame Interpolation on Middlebury (PSNR metric)
no code implementations • 16 Mar 2022 • Kaizhang Kang, Chong Zeng, Hongzhi Wu, Kun Zhou
We present a novel framework to automatically learn to transform the differential cues from a stack of images densely captured with a rotational motion into spatially discriminative and view-invariant per-pixel features at each view.
2 code implementations • 28 Feb 2022 • Kun Zhou, Hui Yu, Wayne Xin Zhao, Ji-Rong Wen
Recently, deep neural networks such as RNN, CNN and Transformer have been applied in the task of sequential recommendation, which aims to capture the dynamic preference characteristics from logged user behavior data for accurate recommendation.
no code implementations • 2 Feb 2022 • Jiawei Lu, He Wang, Tianjia Shao, Yin Yang, Kun Zhou
However, as source images are often misaligned due to the large disparities among the camera settings, strong assumptions have been made in the past with respect to the camera(s) or/and the object in interest, limiting the application of such techniques.
no code implementations • 10 Jan 2022 • Kun Zhou, Berrak Sisman, Rajib Rana, Björn W. Schuller, Haizhou Li
As desired, the proposed network controls the fine-grained emotion intensity in the output speech.
1 code implementation • 4 Jan 2022 • Yuanhang Zhou, Kun Zhou, Wayne Xin Zhao, Cheng Wang, Peng Jiang, He Hu
To implement this framework, we design both coarse-grained and fine-grained procedures for modeling user preference, where the former focuses on more general, coarse-grained semantic fusion and the latter focuses on more specific, fine-grained semantic fusion.
Ranked #1 on Recommendation Systems on ReDial
no code implementations • 27 Dec 2021 • Yuan YAO, Qingxiu Dong, Jian Guan, Boxi Cao, Zhengyan Zhang, Chaojun Xiao, Xiaozhi Wang, Fanchao Qi, Junwei Bao, Jinran Nie, Zheni Zeng, Yuxian Gu, Kun Zhou, Xuancheng Huang, Wenhao Li, Shuhuai Ren, Jinliang Lu, Chengqiang Xu, Huadong Wang, Guoyang Zeng, Zile Zhou, Jiajun Zhang, Juanzi Li, Minlie Huang, Rui Yan, Xiaodong He, Xiaojun Wan, Xin Zhao, Xu sun, Yang Liu, Zhiyuan Liu, Xianpei Han, Erhong Yang, Zhifang Sui, Maosong Sun
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
no code implementations • 23 Dec 2021 • Guangming Yao, Hongzhi Wu, Yi Yuan, Lincheng Li, Kun Zhou, Xin Yu
In this paper, we present a novel double diffusion based neural radiance field, dubbed DD-NeRF, to reconstruct human body geometry and render the human body appearance in novel views from a sparse set of images.
1 code implementation • CVPR 2022 • Kun Zhou, Wenbo Li, Liying Lu, Xiaoguang Han, Jiangbo Lu
Long-range temporal alignment is critical yet challenging for video restoration tasks.
Ranked #1 on Video Super-Resolution on Vimeo-90K
no code implementations • 20 Oct 2021 • Zongyang Du, Berrak Sisman, Kun Zhou, Haizhou Li
Expressive voice conversion performs identity conversion for emotional speakers by jointly converting speaker identity and emotional style.
1 code implementation • EMNLP 2021 • Kun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen
To solve this issue, various data augmentation techniques are proposed to improve the robustness of PLMs.
1 code implementation • ICCV 2021 • Hui Ying, He Wang, Tianjia Shao, Yin Yang, Kun Zhou
Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision.
1 code implementation • 18 Jul 2021 • Yutao Zhu, Jian-Yun Nie, Kun Zhou, Pan Du, Hao Jiang, Zhicheng Dou
The final response is selected according to the predicted knowledge, the goal to achieve, and the context.
no code implementations • 8 Jul 2021 • Zongyang Du, Berrak Sisman, Kun Zhou, Haizhou Li
Traditional voice conversion(VC) has been focused on speaker identity conversion for speech with a neutral expression.
no code implementations • 12 Jun 2021 • Hui Wang, Kun Zhou, Wayne Xin Zhao, Jingyuan Wang, Ji-Rong Wen
Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in top-$N$ recommender systems, called \emph{HIN-based recommendation}.
1 code implementation • 31 May 2021 • Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li
In this paper, we first provide a review of the state-of-the-art emotional voice conversion research, and the existing emotional speech databases.
2 code implementations • NeurIPS 2020 • Wenbo Li, Kun Zhou, Lu Qi, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
2 code implementations • 31 Mar 2021 • Kun Zhou, Berrak Sisman, Haizhou Li
In stage 2, we perform emotion training with a limited amount of emotional speech data, to learn how to disentangle emotional style and linguistic information from the speech.
2 code implementations • 29 Mar 2021 • Wenbo Li, Kun Zhou, Lu Qi, Liying Lu, Nianjuan Jiang, Jiangbo Lu, Jiaya Jia
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
no code implementations • ICCV 2021 • Kaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma, Ping Tan, Hongzhi Wu, Kun Zhou
We present a novel framework to learn to convert the perpixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced 3D reconstruction.
no code implementations • 25 Mar 2021 • Yutao Zhu, Jian-Yun Nie, Kun Zhou, Shengchao Liu, Yabo Ling, Pan Du
Sentence ordering aims to arrange the sentences of a given text in the correct order.
1 code implementation • CVPR 2021 • He Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yong-Liang Yang, Kun Zhou, David Hogg
In this paper, we examine the robustness of state-of-the-art action recognizers against adversarial attack, which has been rarely investigated so far.
1 code implementation • CVPR 2021 • Yunfeng Diao, Tianjia Shao, Yong-Liang Yang, Kun Zhou, He Wang
The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.
no code implementations • 19 Feb 2021 • Siyuan Shen, Yang Yin, Tianjia Shao, He Wang, Chenfanfu Jiang, Lei Lan, Kun Zhou
This paper provides a new avenue for exploiting deep neural networks to improve physics-based simulation.
no code implementations • 8 Feb 2021 • Lijuan Liu, Yin Yang, Yi Yuan, Tianjia Shao, He Wang, Kun Zhou
In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex.
no code implementations • 8 Feb 2021 • Guangming Yao, Yi Yuan, Tianjia Shao, Shuang Li, Shanqi Liu, Yong liu, Mengmeng Wang, Kun Zhou
The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance.
no code implementations • 5 Feb 2021 • Jilin Tang, Yi Yuan, Tianjia Shao, Yong liu, Mengmeng Wang, Kun Zhou
In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance.
1 code implementation • 27 Jan 2021 • Yutao Zhu, Kun Zhou, Jian-Yun Nie, Shengchao Liu, Zhicheng Dou
Our experiments on five benchmark datasets show that our method outperforms all the existing baselines significantly, achieving a new state-of-the-art performance.
1 code implementation • 21 Jan 2021 • Yutao Zhu, Jian-Yun Nie, Kun Zhou, Pan Du, Zhicheng Dou
It is thus crucial to select the part of document content relevant to the current conversation context.
1 code implementation • ACL 2021 • Kun Zhou, Xiaolei Wang, Yuanhang Zhou, Chenzhan Shang, Yuan Cheng, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen
In recent years, conversational recommender system (CRS) has received much attention in the research community.
no code implementations • COLING 2020 • Xuemiao Zhang, Kun Zhou, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Junfei Liu
Weakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise.
no code implementations • 3 Nov 2020 • Kun Zhou, Berrak Sisman, Haizhou Li
Emotional voice conversion (EVC) aims to convert the emotion of speech from one state to another while preserving the linguistic content and speaker identity.
2 code implementations • 28 Oct 2020 • Kun Zhou, Berrak Sisman, Rui Liu, Haizhou Li
Emotional voice conversion aims to transform emotional prosody in speech while preserving the linguistic content and speaker identity.
2 code implementations • COLING 2020 • Kun Zhou, Yuanhang Zhou, Wayne Xin Zhao, Xiaoke Wang, Ji-Rong Wen
To develop an effective CRS, the support of high-quality datasets is essential.
no code implementations • 25 Sep 2020 • Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
no code implementations • 15 Sep 2020 • Siyuan Shen, Tianjia Shao, Kun Zhou, Chenfanfu Jiang, Feng Luo, Yin Yang
We believe our method will inspire a wide-range of new algorithms for deep learning and numerical optimization.
no code implementations • 25 Aug 2020 • Wenheng Chen, He Wang, Yi Yuan, Tianjia Shao, Kun Zhou
We evaluate our model on a wide range of motions and compare it with the state-of-the-art methods.
no code implementations • 19 Aug 2020 • Kun Zhou, Wayne Xin Zhao, Hui Wang, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Ji-Rong Wen
Most of the existing CRS methods focus on learning effective preference representations for users from conversation data alone.
2 code implementations • 18 Aug 2020 • Kun Zhou, Hui Wang, Wayne Xin Zhao, Yutao Zhu, Sirui Wang, Fuzheng Zhang, Zhongyuan Wang, Ji-Rong Wen
To tackle this problem, we propose the model S^3-Rec, which stands for Self-Supervised learning for Sequential Recommendation, based on the self-attentive neural architecture.
no code implementations • 18 Aug 2020 • Guangming Yao, Yi Yuan, Tianjia Shao, Kun Zhou
In this paper, we introduce a method for one-shot face reenactment, which uses the reconstructed 3D meshes (i. e., the source mesh and driving mesh) as guidance to learn the optical flow needed for the reenacted face synthesis.
no code implementations • 11 Aug 2020 • Zongyang Du, Kun Zhou, Berrak Sisman, Haizhou Li
It relies on non-parallel training data from two different languages, hence, is more challenging than mono-lingual voice conversion.
no code implementations • 10 Aug 2020 • Junchen Lu, Kun Zhou, Berrak Sisman, Haizhou Li
We train an encoder to disentangle singer identity and singing prosody (F0 contour) from phonetic content.
2 code implementations • 8 Jul 2020 • Kun Zhou, Wayne Xin Zhao, Shuqing Bian, Yuanhang Zhou, Ji-Rong Wen, Jingsong Yu
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations.
Ranked #3 on Text Generation on ReDial
1 code implementation • 27 May 2020 • Xin Chen, Yuwei Li, Xi Luo, Tianjia Shao, Jingyi Yu, Kun Zhou, Youyi Zheng
We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives.
1 code implementation • 13 May 2020 • Kun Zhou, Berrak Sisman, Mingyang Zhang, Haizhou Li
We consider that there is a common code between speakers for emotional expression in a spoken language, therefore, a speaker-independent mapping between emotional states is possible.
3 code implementations • CVPR 2020 • Jiangke Lin, Yi Yuan, Tianjia Shao, Kun Zhou
In this paper, we introduce a method to reconstruct 3D facial shapes with high-fidelity textures from single-view images in-the-wild, without the need to capture a large-scale face texture database.
1 code implementation • 10 Mar 2020 • Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
Estimating 3D human pose from a single image is a challenging task.
1 code implementation • 2 Mar 2020 • Lumin Yang, Jiajie Zhuang, Hongbo Fu, Xiangzhi Wei, Kun Zhou, Youyi Zheng
We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches.
no code implementations • 18 Feb 2020 • Kun Zhou, Wayne Xin Zhao, Yutao Zhu, Ji-Rong Wen, Jingsong Yu
Open-domain retrieval-based dialogue systems require a considerable amount of training data to learn their parameters.
1 code implementation • 1 Feb 2020 • Kun Zhou, Berrak Sisman, Haizhou Li
Many studies require parallel speech data between different emotional patterns, which is not practical in real life.
3 code implementations • 4 Dec 2019 • Hui Ying, Zhaojin Huang, Shu Liu, Tianjia Shao, Kun Zhou
The pixel-level clustering enables EmbedMask to generate high-resolution masks without missing details from repooling, and the existence of proposal embedding simplifies and strengthens the clustering procedure to achieve high speed with higher performance than segmentation-based methods.
Ranked #87 on Instance Segmentation on COCO test-dev
no code implementations • 16 Nov 2019 • He Wang, Feixiang He, Zhexi Peng, Yong-Liang Yang, Tianjia Shao, Kun Zhou, David Hogg
In this paper, we propose a method, SMART, to attack action recognizers which rely on 3D skeletal motions.
no code implementations • ICCV 2019 • Kun Zhou, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
Estimating 3D human pose from a single image is a challenging task.
Ranked #1 on Monocular 3D Human Pose Estimation on Human3.6M (Use Video Sequence metric, using extra training data)
no code implementations • IJCNLP 2019 • Kun Zhou, Kai Zhang, Yu Wu, Shujie Liu, Jingsong Yu
Context modeling has a pivotal role in open domain conversation.
1 code implementation • 20 Aug 2019 • Yuefan Shen, Changgeng Zhang, Hongbo Fu, Kun Zhou, Youyi Zheng
The key enablers of our system are two carefully designed neural networks, namely, S2ONet, which converts an input sketch to a dense 2D hair orientation field; and O2VNet, which maps the 2D orientation field to a 3D vector field.
Graphics
no code implementations • 21 Sep 2018 • Kun Zhou, Jinmiao Cai, Yao Li, Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image.
no code implementations • 24 Jul 2018 • Xiaoguang Han, Kangcheng Hou, Dong Du, Yuda Qiu, Yizhou Yu, Kun Zhou, Shuguang Cui
To construct the mapping between 2D sketches and a vertex-wise scaling field, a novel deep learning architecture is developed.
no code implementations • 25 Jun 2018 • Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kun Zhou, Kui Jia, Jiangbo Lu
Although significant advances have been made in the area of human poses estimation from images using deep Convolutional Neural Network (ConvNet), it remains a big challenge to perform 3D pose inference in-the-wild.
Ranked #227 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 24 Mar 2018 • Ran Luo, Tianjia Shao, Huamin Wang, Weiwei Xu, Kun Zhou, Yin Yang
DeepWarp is an efficient and highly re-usable deep neural network (DNN) based nonlinear deformable simulation framework.
Graphics
no code implementations • CVPR 2017 • Chen Li, Stephen Lin, Kun Zhou, Katsushi Ikeuchi
An important practical feature of the proposed method is that the skin color model is utilized in a way that does not require color calibration of the camera.
no code implementations • CVPR 2017 • Chen Li, Stephen Lin, Kun Zhou, Katsushi Ikeuchi
We present a method for radiometric calibration of cameras from a single image that contains a human face.
no code implementations • 15 Aug 2016 • Elena Garces, Jose I. Echevarria, Wen Zhang, Hongzhi Wu, Kun Zhou, Diego Gutierrez
We present a method to automatically decompose a light field into its intrinsic shading and albedo components.
no code implementations • 16 Feb 2016 • Junyan Wang, Sai-Kit Yeung, Jue Wang, Kun Zhou
Comprehensive experiments on both RGB and RGB-D data demonstrate that our simple and effective method significantly outperforms the segmentation propagation methods adopted in the state-of-the-art video cutout systems, and the results also suggest the potential usefulness of our method in image cutout system.
no code implementations • CVPR 2015 • Chen Li, Kun Zhou, Stephen Lin
We present a method for simulating makeup in a face image.
no code implementations • CVPR 2015 • Dongping Li, Kaiming He, Jian Sun, Kun Zhou
The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.
no code implementations • CVPR 2013 • Chen Li, Shuochen Su, Yasuyuki Matsushita, Kun Zhou, Stephen Lin
We present a method that enhances the performance of depth-from-defocus (DFD) through the use of shading information.