1 code implementation • Findings (NAACL) 2022 • Quanbin Wang, Xiexiong Lin, Feng Wang
The title generation task that summarizes article content in recapitulatory words relies heavily on utilizing the corresponding key context.
2 code implementations • 10 Jun 2025 • Zehong Ma, Longhui Wei, Feng Wang, Shiliang Zhang, Qi Tian
Existing acceleration techniques for video diffusion models often rely on uniform heuristics or time-embedding variants to skip timesteps and reuse cached features.
1 code implementation • 9 Jun 2025 • MiniCPM Team, Chaojun Xiao, YuXuan Li, Xu Han, Yuzhuo Bai, Jie Cai, Haotian Chen, Wentong Chen, Xin Cong, Ganqu Cui, Ning Ding, Shengdan Fan, Yewei Fang, Zixuan Fu, Wenyu Guan, Yitong Guan, Junshao Guo, Yufeng Han, Bingxiang He, Yuxiang Huang, Cunliang Kong, Qiuzuo Li, Siyuan Li, Wenhao Li, Yanghao Li, Yishan Li, Zhen Li, Dan Liu, Biyuan Lin, Yankai Lin, Xiang Long, Quanyu Lu, Yaxi Lu, Peiyan Luo, Hongya Lyu, Litu Ou, Yinxu Pan, Zekai Qu, Qundong Shi, Zijun Song, Jiayuan Su, Zhou Su, Ao Sun, Xianghui Sun, Peijun Tang, Fangzheng Wang, Feng Wang, Shuo Wang, Yudong Wang, Yesai Wu, Zhenyu Xiao, Jie Xie, Zihao Xie, Yukun Yan, Jiarui Yuan, Kaihuo Zhang, Lei Zhang, Linyue Zhang, Xueren Zhang, Yudi Zhang, Hengyu Zhao, Weilin Zhao, Weilun Zhao, Yuanqian Zhao, Zhi Zheng, Ge Zhou, Jie zhou, Wei Zhou, Zihan Zhou, Zixuan Zhou, Zhiyuan Liu, Guoyang Zeng, Chao Jia, Dahai Li, Maosong Sun
Specifically, in terms of model architecture, we propose InfLLM v2, a trainable sparse attention mechanism that accelerates both prefilling and decoding phases for long-context processing.
no code implementations • 18 May 2025 • Zhengyang Lu, Qian Xia, Weifan Wang, Feng Wang
This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-resolution.
no code implementations • 11 May 2025 • Zhengyang Lu, Bingjie Lu, Weifan Wang, Feng Wang
Addressing these limitations, we propose a differentiable NMS framework for fabric defect detection that achieves superior localization precision through end-to-end optimization.
no code implementations • 3 Mar 2025 • Feng Wang, Zesheng Shi, Bo wang, Nan Wang, Han Xiao
We present ReaderLM-v2, a compact 1. 5 billion parameter language model designed for efficient web content extraction.
1 code implementation • 4 Feb 2025 • Weiren Zhao, Feng Wang, Yanran Wang, Yutong Xie, Qi Wu, Yuyin Zhou
Recent advancements have highlighted the Mamba framework, a state-space model known for its efficiency in capturing long-range dependencies with linear computational complexity.
1 code implementation • 4 Feb 2025 • Feng Wang, Hong Qiu, Yingying Huang, Xiaozhe Gu, Renfang Wang, Bo Yang
Neural operators (NOs) have been effectively used for rapid MT forward modeling, demonstrating their promising performance in solving the MT forward modeling-related partial differential equations (PDEs).
1 code implementation • 27 Jan 2025 • Zhengyang Lu, Bingjie Lu, Feng Wang
We propose a novel counterfactual learning strategy that leverages semantic guidance to reason about hypothetical degradation scenarios, leading to theoretically-grounded representations that capture invariant features across different degradation conditions.
no code implementations • 14 Jan 2025 • Yuxue Yang, Lue Fan, Zuzeng Lin, Feng Wang, Zhaoxiang Zhang
In this paper, we introduce LayerAnimate, a novel architectural approach that enhances fine-grained control over individual animation layers within a video diffusion model, allowing users to independently manipulate foreground and background elements in distinct layers.
no code implementations • CVPR 2025 • Feng Wang, Jiahao Wang, Sucheng Ren, Guoyizhe Wei, Jieru Mei, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie
Qualitative observations suggest, compared to vanilla Vision Mamba, MambaReg's feature maps appear cleaner and more focused on semantically meaningful regions.
no code implementations • CVPR 2025 • Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei, Angtian Wang, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations.
no code implementations • 29 Dec 2024 • Zhengyang Lu, Weifan Wang, Tianhao Guo, Feng Wang
Reflections often degrade the visual quality of images captured through transparent surfaces, and reflection removal methods suffers from the shortage of paired real-world samples. This paper proposes a hybrid approach that combines cycle-consistency with denoising diffusion probabilistic models (DDPM) to effectively remove reflections from single images without requiring paired training data.
no code implementations • 14 Dec 2024 • Jianfeng Li, Jiawen Zhang, Feng Wang, Lianbo Ma
One-shot methods have significantly advanced the field of neural architecture search (NAS) by adopting weight-sharing strategy to reduce search costs.
1 code implementation • 6 Dec 2024 • Chaoda Zheng, Feng Wang, Naiyan Wang, Shuguang Cui, Zhen Li
Recognizing that foreground objects only occupy a small portion of the scene, we introduce object-centric occupancy as a supplement to object bboxes.
1 code implementation • 28 Nov 2024 • Shengjun Zhu, Siyu Liu, Yang Li, Qing Lei, Hongyan Hou, Hewei Jiang, Shujuan Guo, Feng Wang, Rongshang Chen, Xionglin Fan, Shengce Tao, Jiaxin Cai
We started by selecting serological indicators that significantly correlate with clinical outcomes and disease severity to serve as input data for the model.
1 code implementation • 15 Nov 2024 • Sucheng Ren, Yaodong Yu, Nataniel Ruiz, Feng Wang, Alan Yuille, Cihang Xie
In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales.
no code implementations • 11 Nov 2024 • Xianxin Song, Yuan Fang, Feng Wang, Zixiang Ren, Xianghao Yu, Ye Zhang, Fan Liu, Jie Xu, Derrick Wing Kwan Ng, Rui Zhang, Shuguang Cui
Next, we consider a single IRS to facilitate integrated sensing and communication (ISAC), in which the transmit signals at the BS are used for achieving both S&C functionalities, aided by the IRS through reflective beamforming.
1 code implementation • 25 Oct 2024 • Zhengyang Lu, Tianhao Guo, Feng Wang
In this work, we propose a semi-supervised approach using cycle-consistent adversarial networks to leverage the limited paired data and large unpaired corpus of poems and paintings.
1 code implementation • 10 Oct 2024 • Feng Wang, Timing Yang, Yaodong Yu, Sucheng Ren, Guoyizhe Wei, Angtian Wang, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie
In this work, we present a comprehensive analysis of causal image modeling and introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations.
no code implementations • 29 Sep 2024 • Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, Yongbo Wang, Feng Wang, Jingtong Wu, Xin Lu, Rui Yan
During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand.
no code implementations • 16 Sep 2024 • Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther, Bo wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, Han Xiao
We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens.
1 code implementation • 14 Aug 2024 • Liting Jiang, Yuming Xiang, Feng Wang, Hongjian You
In contrast, unsupervised learning methods can leverage the increasing availability of very-high-resolution (VHR) remote sensing images, offering considerable potential in the realm of stereo matching.
no code implementations • 14 Aug 2024 • Liting Jiang, Feng Wang, Wenyi Zhang, Peifeng Li, Hongjian You, Yuming Xiang
Stereo matching, a critical step of 3D reconstruction, has fully shifted towards deep learning due to its strong feature representation of remote sensing images.
no code implementations • 8 Aug 2024 • Wan Li, Xinyun Zhong, Wei Li, Song Zhang, Moheng Rong, Yan Xi, Peng Yuan, Zechen Wang, Xiaolei Jiang, Rongxi Yi, Hui Tang, Yang Chen, Chaohui Tong, Zhan Wu, Feng Wang
The experimental results confirm the effectiveness of the respiratory subtraction method and the proposed quantitative evaluation metric in assessing lung tumor treatment.
no code implementations • 1 Aug 2024 • Mingcong Lu, Jiangcai Zhu, Wang Hao, Zheng Li, Shusheng Zhang, Kailai Shao, Chao Chen, Nan Li, Feng Wang, Xin Lu
In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously.
1 code implementation • 28 Jun 2024 • Yutao Zhu, Kun Zhou, Kelong Mao, Wentong Chen, Yiding Sun, Zhipeng Chen, Qian Cao, Yihan Wu, Yushuo Chen, Feng Wang, Lei Zhang, Junyi Li, Xiaolei Wang, Lei Wang, Beichen Zhang, Zican Dong, Xiaoxue Cheng, Yuhan Chen, Xinyu Tang, Yupeng Hou, Qiangqiang Ren, Xincheng Pang, Shufang Xie, Wayne Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ze-Feng Gao, Yueguo Chen, Weizheng Lu, Ji-Rong Wen
This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters.
no code implementations • 11 Jun 2024 • Feng Wang, Haihang Ruan, Zhihuang Xie, Ronggang Wang, Xiangyu Yue
Recently, Neural Video Compression (NVC) techniques have achieved remarkable performance, even surpassing the best traditional lossy video codec.
1 code implementation • 11 Jun 2024 • Sucheng Ren, Xianhang Li, Haoqin Tu, Feng Wang, Fangxun Shu, Lei Zhang, Jieru Mei, Linjie Yang, Peng Wang, Heng Wang, Alan Yuille, Cihang Xie
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks.
no code implementations • 11 Jun 2024 • Yunxuan Ma, Yide Bian, Hao Xu, Weitao Yang, Jingshu Zhao, Zhijian Duan, Feng Wang, Xiaotie Deng
Motivated by this, our paper investigates the computation of market equilibrium in scenarios with a large-scale buyer population, where buyers and goods are represented by their contexts.
no code implementations • 24 May 2024 • Jiaxing Li, Chi Xu, Feng Wang, Isaac M von Riedemann, Cong Zhang, Jiangchuan Liu
In this work, we for the first time conducted an analysis on real-world human-to-LLM interaction data, identifying key challenges in existing caching solutions for LLM-based chat services.
1 code implementation • 23 May 2024 • Feng Wang, Jiahao Wang, Sucheng Ren, Guoyizhe Wei, Jieru Mei, Wei Shao, Yuyin Zhou, Alan Yuille, Cihang Xie
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba.
1 code implementation • 15 May 2024 • Feng Wang, M. Cenk Gursoy, Senem Velipasalar
In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning.
no code implementations • 14 May 2024 • Bingdong Li, Zixiang Di, Yongfan Lu, Hong Qian, Feng Wang, Peng Yang, Ke Tang, Aimin Zhou
In this paper, we propose a novel Composite Diffusion Model based Pareto Set Learning algorithm, namely CDM-PSL, for expensive MOBO.
no code implementations • 19 Apr 2024 • Ruohan Guo, Feng Wang, Cungang Hu, Weixiang Shen
Next, a rapid estimation algorithm is proposed to identify the three electrode aging parameters (EAPs) which best reconstruct the 15 OCV feature points over the entire usable capacity range.
1 code implementation • 11 Mar 2024 • Zilong Chen, Yikai Wang, Feng Wang, Zhengyi Wang, Huaping Liu
To fully unleash the potential of video diffusion to perceive the 3D world, we further introduce geometrical consistency prior and extend the video diffusion model to a multi-view consistent 3D generator.
no code implementations • 1 Mar 2024 • Ruoqi Wang, Haitao Wang, Qiong Luo, Feng Wang, Hejun Wu
This hybrid approach allows VisRec to effectively leverage both labeled and unlabeled data.
2 code implementations • 26 Feb 2024 • Yiding Sun, Feng Wang, Yutao Zhu, Wayne Xin Zhao, Jiaxin Mao
The ability of the foundation models heavily relies on large-scale, diverse, and high-quality pretraining data.
no code implementations • 26 Feb 2024 • Isabelle Mohr, Markus Krimmel, Saba Sturua, Mohammad Kalim Akram, Andreas Koukounas, Michael Günther, Georgios Mastrapas, Vinit Ravishankar, Joan Fontanals Martínez, Feng Wang, Qi Liu, Ziniu Yu, Jie Fu, Saahil Ognawala, Susana Guzman, Bo wang, Maximilian Werk, Nan Wang, Han Xiao
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language.
1 code implementation • 17 Feb 2024 • Feng Wang, Renfang Wang, Hong Qiu
Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging.
1 code implementation • 1 Feb 2024 • Feng Wang, Bo Yang, Renfang Wang, Hong Qiu
To avoid generating and/or collecting labeled samples, we propose a novel method by integrating deep learning and dictionary learning to enhance the VMs with low resolution by using the traditional tomography-least square method (LSQR).
1 code implementation • 14 Jan 2024 • Zhengyang Lu, Feng Wang
Super-resolution techniques are crucial in improving image granularity, particularly in complex urban scenes, where preserving geometric structures is vital for data-informed cultural heritage applications.
2 code implementations • CVPR 2024 • Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lu, Hongsheng Li, Yu Qiao, Lewei Lu, Jie zhou, Jifeng Dai
The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
1 code implementation • 8 Jan 2024 • Feng Wang
With the development of artificial intelligence, large-scale models have become increasingly intelligent.
1 code implementation • 4 Jan 2024 • Xinyang Pu, Hecheng Jia, Linghao Zheng, Feng Wang, Feng Xu
Compared to conventional state-of-the-art semantic segmentation algorithms by extensive experiments, CWSAM showcases enhanced performance with fewer computing resources, highlighting the potential of leveraging foundational models like SAM for specific downstream tasks in the SAR domain.
1 code implementation • CVPR 2024 • Ruoqi Wang, Zhuoyang Chen, JiaYi Zhu, Qiong Luo, Feng Wang
Unfortunately existing reconstruction methods often miss some components of visibility in frequency domain so blurred object edges and persistent artifacts remain in the images.
no code implementations • 29 Dec 2023 • Youzhe Song, Feng Wang
We propose a novel quality-guided joint training approach for mixed-quality face recognition, which could simultaneously learn the images of different qualities with a single encoder.
no code implementations • 17 Dec 2023 • Wenhao Guan, Yishuang Li, Tao Li, Hukai Huang, Feng Wang, Jiayan Lin, Lingyan Huang, Lin Li, Qingyang Hong
The challenges of modeling such a multi-modal style controllable TTS mainly lie in two aspects:1)aligning the multi-modal information into a unified style space to enable the input of arbitrary modality as the style prompt in a single system, and 2)efficiently transferring the unified style representation into the given text content, thereby empowering the ability to generate prompt style-related voice.
no code implementations • 8 Dec 2023 • Yuquan Zhang, Zhong Cao, Feng Wang, Lam, Man I, Hui Deng, Ying Mei, Lei Tan
Real-time identification of galaxy and nebula/star cluster (abbreviated as NSC) images is of great value during CSST survey.
1 code implementation • 4 Dec 2023 • Feng Wang, Jieru Mei, Alan Yuille
Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation.
1 code implementation • CVPR 2024 • YiWen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin
3D editing plays a crucial role in many areas such as gaming and virtual reality.
no code implementations • 19 Nov 2023 • Feng Wang, M. Cenk Gursoy, Senem Velipasalar
We evaluate the performance of the proposed policy ensemble algorithm by applying on the network slicing agents and the jammer agent in simulations to show its effectiveness.
1 code implementation • 30 Oct 2023 • Feng Wang, Senem Velipasalar, M. Cenk Gursoy
MKOR only requires the server to send secretly modified parameters to clients and can efficiently and inconspicuously reconstruct the input images from clients' gradient updates.
no code implementations • 4 Oct 2023 • Guoyizhe Wei, Feng Wang, Anshul Shah, Rama Chellappa
Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models.
1 code implementation • CVPR 2024 • Zilong Chen, Feng Wang, Yikai Wang, Huaping Liu
Specifically, our method adopts a progressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage.
no code implementations • 22 Sep 2023 • Jiangqi Liu, Feng Wang
Most existing methods for unsupervised industrial anomaly detection train a separate model for each object category.
2 code implementations • 19 Sep 2023 • Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, Fan Yang, Fei Deng, Feng Wang, Feng Liu, Guangwei Ai, Guosheng Dong, Haizhou Zhao, Hang Xu, Haoze Sun, Hongda Zhang, Hui Liu, Jiaming Ji, Jian Xie, Juntao Dai, Kun Fang, Lei Su, Liang Song, Lifeng Liu, Liyun Ru, Luyao Ma, Mang Wang, Mickel Liu, MingAn Lin, Nuolan Nie, Peidong Guo, Ruiyang Sun, Tao Zhang, Tianpeng Li, Tianyu Li, Wei Cheng, WeiPeng Chen, Xiangrong Zeng, Xiaochuan Wang, Xiaoxi Chen, Xin Men, Xin Yu, Xuehai Pan, Yanjun Shen, Yiding Wang, Yiyu Li, Youxin Jiang, Yuchen Gao, Yupeng Zhang, Zenan Zhou, Zhiying Wu
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
no code implementations • 28 Aug 2023 • Ruoqi Wang, Zhuoyang Chen, JiaYi Zhu, Qiong Luo, Feng Wang
This representation matches the way in which radio telescopes observe a celestial area as the Earth rotates.
no code implementations • 10 Aug 2023 • Feng Wang, Giovanni Geraci, Lingxiang Li, Peng Wang, Tony Q. S. Quek
In this paper, we introduce a novel approach to optimize wireless edge content placement using NTN, positioning NTN as a complement to TN for achieving optimal content broadcasting.
2 code implementations • 7 Aug 2023 • Lue Fan, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
Consequently, we develop a suite of components to complement the virtual voxel concept, including a virtual voxel encoder, a virtual voxel mixer, and a virtual voxel assignment strategy.
1 code implementation • NeurIPS 2023 • Yang Liu, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
Radar is ubiquitous in autonomous driving systems due to its low cost and good adaptability to bad weather.
no code implementations • 11 Jul 2023 • Zhengxin Lei, Feng Xu, Jiangtao Wei, Feng Cai, Feng Wang, Ya-Qiu Jin
SAR images are highly sensitive to observation configurations, and they exhibit significant variations across different viewing angles, making it challenging to represent and learn their anisotropic features.
no code implementations • 19 Jun 2023 • Xirui Li, Feng Wang, Naiyan Wang, Chao Ma
To ''forward'' frames, we use vehicle motion models to estimate the future pose of the bounding boxes.
1 code implementation • 16 May 2023 • Ruoqi Wang, Zhuoyang Chen, Qiong Luo, Feng Wang
In radio astronomy, signals from radio telescopes are transformed into images of observed celestial objects, or sources.
2 code implementations • ICCV 2023 • Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang
Drawing inspiration from this, we propose a high-performance offline detector in a track-centric perspective instead of the conventional object-centric perspective.
no code implementations • 23 Apr 2023 • Youzhe Song, Feng Wang
To alleviate the above problem, we propose a novel approach namely Contrastive Regularization for Face recognition (CoReFace) to apply image-level regularization in feature representation learning.
no code implementations • 3 Apr 2023 • Jiaqi Ye, XiaoDong Li, Pangjing Wu, Feng Wang
Then, we design two different AP methods: frequency-based global method and state clustering-based local method, based on the prior optimal policy.
no code implementations • 6 Mar 2023 • Feng Wang, Haihang Ruan, Fei Xiong, Jiayu Yang, Litian Li, Ronggang Wang
Using more reference frames can significantly improve the compression efficiency in neural video compression.
no code implementations • 4 Feb 2023 • Bohan Li, Xiao Xu, Xinghao Wang, Yutai Hou, Yunlong Feng, Feng Wang, Xuanliang Zhang, Qingfu Zhu, Wanxiang Che
In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus incorrectly changing the essential semantics of the original image.
2 code implementations • 5 Jan 2023 • Lue Fan, Yuxue Yang, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD.
1 code implementation • ICCV 2023 • Feng Wang, Sinan Tan, Xinghang Li, Zeyue Tian, Yafei Song, Huaping Liu
In this paper, we present a novel method named MixVoxels to better represent the dynamic scenes with fast training speed and competitive rendering qualities.
1 code implementation • 14 Nov 2022 • Dexin Liao, Tao Jiang, Feng Wang, Lin Li, Qingyang Hong
Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
1 code implementation • 14 Oct 2022 • Daiheng Gao, Yuliang Xiu, Kailin Li, Lixin Yang, Feng Wang, Peng Zhang, Bang Zhang, Cewu Lu, Ping Tan
Unity GUI is also provided to generate synthetic hand data with user-defined settings, e. g., pose, camera, background, lighting, textures, and accessories.
no code implementations • 9 Oct 2022 • Feng Wang, Manling Li, Xudong Lin, Hairong Lv, Alexander G. Schwing, Heng Ji
Recent advances in pre-training vision-language models like CLIP have shown great potential in learning transferable visual representations.
1 code implementation • 12 Sep 2022 • Feng Wang, M. Cenk Gursoy, Senem Velipasalar
In order to improve the communication efficiency, we in this paper propose the feature-based federated transfer learning as an innovative approach to reduce the uplink payload by more than five orders of magnitude compared to that of existing approaches.
1 code implementation • 12 Sep 2022 • Zheqi Lv, Wenqiao Zhang, Shengyu Zhang, Kun Kuang, Feng Wang, Yongwei Wang, Zhengyu Chen, Tao Shen, Hongxia Yang, Beng Chin Ooi, Fei Wu
DUET is deployed on a powerful cloud server that only requires the low cost of forwarding propagation and low time delay of data transmission between the device and the cloud.
no code implementations • 19 Aug 2022 • Zheqi Lv, Feng Wang, Shengyu Zhang, Kun Kuang, Hongxia Yang, Fei Wu
In this paper, we propose a novel approach that significantly improves the recommendation performance of the tail users while achieving at least comparable performance for the head users over the base model.
4 code implementations • 20 Jul 2022 • Lue Fan, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
To enable efficient long-range LiDAR-based object detection, we build a fully sparse 3D object detector (FSD).
no code implementations • 11 Jul 2022 • Jie Qin, Shuaihang Yuan, Jiaxin Chen, Boulbaba Ben Amor, Yi Fang, Nhat Hoang-Xuan, Chi-Bien Chu, Khoi-Nguyen Nguyen-Ngoc, Thien-Tri Cao, Nhat-Khang Ngo, Tuan-Luc Huynh, Hai-Dang Nguyen, Minh-Triet Tran, Haoyang Luo, Jianning Wang, Zheng Zhang, Zihao Xin, Yang Wang, Feng Wang, Ying Tang, Haiqin Chen, Yan Wang, Qunying Zhou, Ji Zhang, Hongyuan Wang
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
no code implementations • 7 Jul 2022 • Jiangchao Yao, Feng Wang, Xichen Ding, Shaohu Chen, Bo Han, Jingren Zhou, Hongxia Yang
To overcome this issue, we propose a meta controller to dynamically manage the collaboration between the on-device recommender and the cloud-based recommender, and introduce a novel efficient sample construction from the causal perspective to solve the dataset absence issue of meta controller.
2 code implementations • 7 Jun 2022 • Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, Feng Wang, Jiashui Wang
According to the characteristic of SRSs, we present 22 diverse transformations and thoroughly evaluate them using 7 recent promising adversarial attacks (4 white-box and 3 black-box) on speaker recognition.
no code implementations • ACL 2022 • Mingzhe Li, Xiexiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan
Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references.
1 code implementation • 22 Mar 2022 • Feng Wang, Huiyu Wang, Chen Wei, Alan Yuille, Wei Shen
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation.
no code implementations • 16 Mar 2022 • Cheng Ge, Yi Lu, Jia Qu, Liangxu Xie, Feng Wang, Hong Zhang, Ren Kong, Shan Chang
De novo peptide sequencing from mass spectrometry data is an important method for protein identification.
no code implementations • 19 Dec 2021 • Lianmeng Jiao, Feng Wang, Zhun-Ga Liu, Quan Pan
As a representative evidential clustering algorithm, evidential c-means (ECM) provides a deeper insight into the data by allowing an object to belong not only to a single class, but also to any subset of a collection of classes, which generalizes the hard, fuzzy, possibilistic, and rough partitions.
no code implementations • 15 Dec 2021 • Xi Yang, Jie Zhang, Kejiang Chen, Weiming Zhang, Zehua Ma, Feng Wang, Nenghai Yu
Tracing text provenance can help claim the ownership of text content or identify the malicious users who distribute misleading content like machine-generated fake news.
2 code implementations • CVPR 2022 • Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases.
Ranked #3 on
3D Object Detection
on waymo cyclist
no code implementations • 11 Nov 2021 • Jiaxi Zhang, Liwei Ni, Shenggen Zheng, Hao liu, Xiangfu Zou, Feng Wang, Guojie Luo
In this paper, we introduce Boolean sensitivity into Boolean matching and design several sensitivity-related signatures to enhance fast Boolean matching.
1 code implementation • 11 Nov 2021 • Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang, Ziqi Tan, Kun Kuang, Chao Wu, Fei Wu, Jingren Zhou, Hongxia Yang
However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed.
no code implementations • 18 Oct 2021 • Feng Wang, Trond R. Henninen, Debora Keller, Rolf Erni
We propose an effective deep learning model for signal reconstruction, which requires no signal prior, no noise model calibration, and no clean samples.
2 code implementations • 14 Oct 2021 • Feng Wang, Tao Kong, Rufeng Zhang, Huaping Liu, Hang Li
To solve this problem, we propose to maximize the mutual information between the input and the class predictions.
Ranked #1 on
Image Classification
on Oxford-IIIT Pet Dataset
Fine-Grained Image Classification
Representation Learning
+5
no code implementations • NeurIPS 2021 • Feng Wang, Guoyizhe Wei, Qiao Liu, Jinxiang Ou, Xian Wei, Hairong Lv
In the experiments, it yields up to 5. 02% higher accuracy over single EfficientNet-B0 on the imbalanced datasets.
no code implementations • 25 Sep 2021 • Zeyuan Chen, Jiangchao Yao, Feng Wang, Kunyang Jia, Bo Han, Wei zhang, Hongxia Yang
With the hardware development of mobile devices, it is possible to build the recommendation models on the mobile side to utilize the fine-grained features and the real-time feedbacks.
42 code implementations • 18 Jul 2021 • Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, Jian Sun
In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.
Ranked #1 on
Real-Time Object Detection
on Argoverse-HD (Detection-Only, Val)
(using extra training data)
no code implementations • 12 May 2021 • Feng Wang, M. Cenk Gursoy, Senem Velipasalar
Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications.
no code implementations • 14 Apr 2021 • Jiangchao Yao, Feng Wang, Kunyang Jia, Bo Han, Jingren Zhou, Hongxia Yang
With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features.
1 code implementation • CVPR 2021 • Zhichao Li, Feng Wang, Naiyan Wang
LiDAR-based 3D detection in point cloud is essential in the perception system of autonomous driving.
1 code implementation • 18 Mar 2021 • Lue Fan, Xuan Xiong, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
The most notable difference with previous works is that our method is purely based on the range view representation.
1 code implementation • ICCV 2021 • Lue Fan, Xuan Xiong, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
We first analyze the existing range-view-based methods and find two issues overlooked by previous works: 1) the scale variation between nearby and far away objects; 2) the inconsistency between the 2D range image coordinates used in feature extraction and the 3D Cartesian coordinates used in output.
no code implementations • CVPR 2021 • Feng Wang, Huaping Liu
We will show that the contrastive loss is a hardness-aware loss function, and the temperature {\tau} controls the strength of penalties on hard negative samples.
no code implementations • 11 Dec 2020 • Jie Gu, Feng Wang, Qinghui Sun, Zhiquan Ye, Xiaoxiao Xu, Jingmin Chen, Jun Zhang
In this work, we focus on developing universal user representation model.
no code implementations • NeurIPS 2020 • Feng Wang, Huaping Liu, Di Guo, Sun Fuchun
In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category.
1 code implementation • 7 Oct 2020 • Feng Wang, Huaping Liu, Di Guo, Fuchun Sun
In this paper, we propose Invariance Propagation to focus on learning representations invariant to category-level variations, which are provided by different instances from the same category.
no code implementations • 14 Aug 2020 • Feng Wang, Dongjie Shi, Teng Liu, Xiaolin Tang
Decision-making module enables autonomous vehicles to reach appropriate maneuvers in the complex urban environments, especially the intersection situations.
no code implementations • 7 Aug 2020 • Dejan Kostyszyn, Tobias Fechter, Nico Bartl, Anca L. Grosu, Christian Gratzke, August Sigle, Michael Mix, Juri Ruf, Thomas F. Fassbender, Selina Kiefer, Alisa S. Bettermann, Nils H. Nicolay, Simon Spohn, Maria U. Kramer, Peter Bronsert, Hongqian Guo, Xuefeng Qiu, Feng Wang, Christoph Henkenberens, Rudolf A. Werner, Dimos Baltas, Philipp T. Meyer, Thorsten Derlin, Mengxia Chen, Constantinos Zamboglou
Accurate delineation of the intraprostatic gross tumour volume (GTV) is a prerequisite for treatment approaches in patients with primary prostate cancer (PCa).
no code implementations • 12 Jul 2020 • Feng Wang, Chen Zhong, M. Cenk Gursoy, Senem Velipasalar
As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention.
no code implementations • ACL 2020 • Zhiquan Ye, Yuxia Geng, Jiaoyan Chen, Jingmin Chen, Xiaoxiao Xu, SuHang Zheng, Feng Wang, Jun Zhang, Huajun Chen
In this situation, transferring from seen classes to unseen classes is extremely hard.
no code implementations • 19 Jun 2020 • Xiaojing Chen, Zhouyu Lu, Wei Ni, Xin Wang, Feng Wang, Shunqing Zhang, Shugong Xu
Driven by explosive computation demands of Internet of Things (IoT), mobile edge computing (MEC) provides a promising technique to enhance the computation capability for mobile users.
1 code implementation • ACL 2020 • Xingyi Cheng, Weidi Xu, Kunlong Chen, Shaohua Jiang, Feng Wang, Taifeng Wang, Wei Chu, Yuan Qi
This paper proposes to incorporate phonological and visual similarity knowledge into language models for CSC via a specialized graph convolutional network (SpellGCN).
no code implementations • 19 Apr 2020 • Yong Wang, Qi Liu, Hongyu Zu, Xiao Liu, Ruichao Xie, Feng Wang
Pixel-wise operations between polarimetric images are important for processing polarization information.
no code implementations • 29 Feb 2020 • Ren Kong, Guangbo Yang, Rui Xue, Ming Liu, Feng Wang, Jianping Hu, Xiaoqiang Guo, Shan Chang
Motivation: The coronavirus disease 2019 (COVID-19) caused by a new type of coronavirus has been emerging from China and led to thousands of death globally since December 2019.
no code implementations • 28 Nov 2019 • Wen Wang, Lijun Du, Yinxing Gao, Yanzhou Su, Feng Wang, Jian Cheng
Concretely, for remote sensing image scene classification, we would like to map images from the same scene to feature vectors that are close, and map images from different scenes to feature vectors that are widely separated.
no code implementations • WS 2019 • Xinze Guo, Chang Liu, Xiaolong Li, Yiran Wang, Guoliang Li, Feng Wang, Zhitao Xu, Liuyi Yang, Li Ma, Changliang Li
This paper describes the Kingsoft AI Lab{'}s submission to the WMT2019 news translation shared task.
1 code implementation • 29 Jul 2019 • Xianyang Li, Feng Wang, Qinghao Hu, Cong Leng
With the development of convolutional neural network, significant progress has been made in computer vision tasks.
no code implementations • 18 Feb 2019 • Linhao Dong, Feng Wang, Bo Xu
Experiments on two Mandarin ASR datasets show the replacement of RNNs by the self-attention networks yields a 8. 4%-10. 2% relative character error rate (CER) reduction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
2 code implementations • 29 Oct 2018 • Feng Wang, Alberto Eljarrat, Johannes Müller, Trond Henninen, Erni Rolf, Christoph Koch
We propose a novel neural network architecture highlighting fast convergence as a generic solution addressing image(s)-to-image(s) inverse problems of different domains.
Computational Physics Materials Science
1 code implementation • 6 Sep 2018 • Han Xiao, Feng Wang, Jian-Feng Yan, Jingyao Zheng
The task of question answering or question generation aims to infer an answer or a question when given the counterpart based on context.
1 code implementation • EMNLP 2018 • Yiqun Yao, Jiaming Xu, Feng Wang, Bo Xu
Our code is available at https://github. com/FlamingHorizon/CMM-VR.
no code implementations • COLING 2018 • Feng Wang, Wei Chen, Zhen Yang, Qianqian Dong, Shuang Xu, Bo Xu
While the disfluency detection has achieved notable success in the past years, it still severely suffers from the data scarcity.
1 code implementation • ACL 2018 • Zhen Yang, Wei Chen, Feng Wang, Bo Xu
Unsupervised neural machine translation (NMT) is a recently proposed approach for machine translation which aims to train the model without using any labeled data.
Ranked #6 on
Machine Translation
on WMT2016 German-English
no code implementations • 13 Apr 2018 • Haonan Qiu, Yingbin Zheng, Hao Ye, Yao Lu, Feng Wang, Liang He
The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action.
no code implementations • 31 Mar 2018 • Song Feng, Linhua Deng, Guofeng Shu, Feng Wang, Hui Deng, Kaifan Ji
This paper presents a fast algorithm for obtaining high-accuracy subpixel translation of low PSNR images.
10 code implementations • 17 Jan 2018 • Feng Wang, Weiyang Liu, Haijun Liu, Jian Cheng
In this work, we introduce a novel additive angular margin for the Softmax loss, which is intuitively appealing and more interpretable than the existing works.
Ranked #2 on
Face Identification
on Trillion Pairs Dataset
no code implementations • EMNLP 2017 • Xiaowei Zhang, Wei Chen, Feng Wang, Shuang Xu, Bo Xu
Neural Machine Translation (NMT) lays intensive burden on computation and memory cost.
2 code implementations • ACL 2017 • Suncong Zheng, Feng Wang, Hongyun Bao, Yuexing Hao, Peng Zhou, Bo Xu
Joint extraction of entities and relations is an important task in information extraction.
Ranked #3 on
Relation Extraction
on NYT-single
3 code implementations • 21 Apr 2017 • Feng Wang, Xiang Xiang, Jian Cheng, Alan L. Yuille
We show that both strategies, and small variants, consistently improve performance by between 0. 2% to 0. 4% on the LFW dataset based on two models.
no code implementations • 17 Mar 2017 • Chengan Du, Yunpeng Zhao, Feng Wang
We prove the consistency of graph-based learning in the case that the estimated scores are enforced to be equal to the observed responses for the labeled data.
3 code implementations • NAACL 2018 • Zhen Yang, Wei Chen, Feng Wang, Bo Xu
During training, both the dynamic discriminator and the static BLEU objective are employed to evaluate the generated sentences and feedback the evaluations to guide the learning of the generator.
2 code implementations • 24 Feb 2017 • Chen Wu, Rodrigo Tobar, Kevin Vinsen, Andreas Wicenec, Dave Pallot, Baoqiang Lao, Ruonan Wang, Tao An, Mark Boulton, Ian Cooper, Richard Dodson, Markus Dolensky, Ying Mei, Feng Wang
The Data Activated Liu Graph Engine - DALiuGE - is an execution framework for processing large astronomical datasets at a scale required by the Square Kilometre Array Phase 1 (SKA1).
Distributed, Parallel, and Cluster Computing Instrumentation and Detectors
2 code implementations • 22 Feb 2017 • Feng Wang, Xiang Xiang, Chang Liu, Trac. D. Tran, Austin Reiter, Gregory D. Hager, Harry Quon, Jian Cheng, Alan L. Yuille
In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification.
no code implementations • 18 Feb 2017 • Chang Liu, Fuchun Sun, Changhu Wang, Feng Wang, Alan Yuille
In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model.
no code implementations • COLING 2016 • Zhen Yang, Wei Chen, Feng Wang, Bo Xu
This article proposes a novel character-aware neural machine translation (NMT) model that views the input sequences as sequences of characters rather than words.
1 code implementation • 6 May 2016 • Feng Wang, Huichao Gong, Gaochao liu, Meijing Li, Chuangye Yan, Tian Xia, Xueming Li, Jianyang Zeng
Particle picking is a time-consuming step in single-particle analysis and often requires significant interventions from users, which has become a bottleneck for future automated electron cryo-microscopy (cryo-EM).
no code implementations • 25 Jan 2016 • Feng Wang, David M. J. Tax
In this survey, we introduce some attention based RNN models which can focus on different parts of the input for each output item, in order to explore and take advantage of the implicit relations between the input and the output items.
no code implementations • 14 May 2013 • Xiao-Bo Jin, Qiang Lu, Feng Wang, Quan-gong Huo
The study focused on the machine learning analysis approaches to identify the adulteration of 9 kinds of edible oil qualitatively and answered the following three questions: Is the oil sample adulterant?