1 code implementation • ECCV 2020 • Xiao Zhang, Rui Zhao, Yu Qiao, Hongsheng Li
To address this problem, this paper introduces a novel Radial Basis Function (RBF) distances to replace the commonly used inner products in the softmax loss function, such that it can adaptively assign losses to regularize the intra-class and inter-class distances by reshaping the relative differences, and thus creating more representative prototypes of classes to improve optimization.
no code implementations • 29 May 2024 • Fengshuo Bai, Rui Zhao, Hongming Zhang, Sijia Cui, Ying Wen, Yaodong Yang, Bo Xu, Lei Han
To boost the learning loop, we propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
no code implementations • 28 May 2024 • Weijiang Lai, Beihong Jin, Beibei Li, Yiyuan Zheng, Rui Zhao
Moreover, we conduct cross-view contrastive learning to keep the consistency between node embeddings from the two different views.
1 code implementation • 27 May 2024 • Jingqing Ruan, Ziyue Li, Hua Wei, Haoyuan Jiang, Jiaming Lu, Xuantang Xiong, Hangyu Mao, Rui Zhao
Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic signal control to alleviate congestion.
no code implementations • 22 May 2024 • Zhaojun Guo, Jinghui Lu, Xuejing Liu, Rui Zhao, Zhenxing Qian, Fei Tan
Despite the notable advancements achieved by leveraging pre-trained vision-language (VL) models through few-shot tuning for downstream tasks, our detailed empirical study highlights a significant dependence of few-shot learning outcomes on the careful selection of training examples - a facet that has been previously overlooked in research.
no code implementations • 15 May 2024 • Sun Yang, Qiong Su, Zhishuai Li, Ziyue Li, Hangyu Mao, Chenxi Liu, Rui Zhao
Consequently, there is a critical need to filter out unnecessary tables and columns, directing the language models attention to relevant tables and columns with schema-linking, to reduce errors during SQL generation.
no code implementations • 10 May 2024 • Rui Zhao, Zhiqiang Zuo, Ying Tan, Yijing Wang, Wentao Zhang
In this paper, the resilient control for switched systems in the presence of deception attack and denial-of-service (DoS) attack is addressed.
1 code implementation • 8 May 2024 • Rui Zhao, Bin Shi, Jianfei Ruan, Tianze Pan, Bo Dong
Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance.
1 code implementation • 1 May 2024 • Sirui Chen, Bo Peng, Meiqi Chen, Ruiqi Wang, Mengying Xu, Xingyu Zeng, Rui Zhao, Shengjie Zhao, Yu Qiao, Chaochao Lu
Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential for causal reasoning.
1 code implementation • 18 Apr 2024 • Haoyuan Jiang, Ziyue Li, Hua Wei, Xuantang Xiong, Jingqing Ruan, Jiaming Lu, Hangyu Mao, Rui Zhao
The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights.
1 code implementation • 16 Apr 2024 • Hengyuan Zhang, Yanru Wu, Dawei Li, Zacc Yang, Rui Zhao, Yong Jiang, Fei Tan
In an overall evaluation of both speciality and versatility, CoFiTune consistently outperforms baseline methods across diverse tasks and model scales.
no code implementations • 10 Apr 2024 • Chunxu Liu, Guozhen Zhang, Rui Zhao, LiMin Wang
Large motion poses a critical challenge in Video Frame Interpolation (VFI) task.
1 code implementation • 8 Apr 2024 • Zhengde Zhang, Yiyu Zhang, Haodong Yao, Jianwen Luo, Rui Zhao, Bo Huang, Jiameng Zhao, Yipu Liao, Ke Li, Lina Zhao, Jun Cao, Fazhi Qi, Changzheng Yuan
To address this challenge, a sophisticated large language model system named as Xiwu has been developed, allowing you switch between the most advanced foundation models and quickly teach the model domain knowledge.
1 code implementation • 15 Mar 2024 • Vidminas Vizgirda, Rui Zhao, Naman Goel
Unlike centralised Web and data architectures that keep user data tied to application and service providers, we show how one can use Solid -- a decentralised Web specification -- to decouple user data from generative AI applications.
1 code implementation • 13 Mar 2024 • Zhishuai Li, Xiang Wang, Jingjing Zhao, Sun Yang, Guoqing Du, Xiaoru Hu, Bin Zhang, Yuxiao Ye, Ziyue Li, Rui Zhao, Hangyu Mao
Then, in the first stage, question-SQL pairs are retrieved as few-shot demonstrations, prompting the LLM to generate a preliminary SQL (PreSQL).
Ranked #1 on Text-To-SQL on spider
2 code implementations • 12 Mar 2024 • Weijia Wu, Zhuang Li, YuChao Gu, Rui Zhao, Yefei He, David Junhao Zhang, Mike Zheng Shou, Yan Li, Tingting Gao, Di Zhang
We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation.
1 code implementation • 12 Mar 2024 • Rui Zhao, Jun Zhao
We believe this work demonstrates a practicality of a perennial DToU language and the potential of a paradigm shift to how users interact with data and applications in a decentralized Web, offering both improved privacy and usability.
no code implementations • 5 Mar 2024 • Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, Sun Yang, Chi Harold Liu, Rui Zhao, Ziyue Li, Hangyu Mao
Then we formulate five evaluation tasks to comprehensively assess the performance of diverse methods across various LLMs throughout the Text-to-SQL process. Our study highlights the performance disparities among LLMs and proposes optimal in-context learning solutions tailored to each task.
no code implementations • 27 Feb 2024 • Fufangchen Zhao, Guoqiang Jin, Jiaheng Huang, Rui Zhao, Fei Tan
The solution to this problem is often time-consuming and labor-intensive, and there is also an additional cost of secondary deployment, resulting in economic and time losses.
1 code implementation • 23 Jan 2024 • Zhishuai Li, Yunhao Nie, Ziyue Li, Lei Bai, Yisheng Lv, Rui Zhao
As a pre-trained paradigm, we conduct the Kriging task from a new perspective of representation: we aim to first learn robust and general representations and then recover attributes from representations.
no code implementations • 18 Jan 2024 • Chenxi Liu, Sun Yang, Qianxiong Xu, Zhishuai Li, Cheng Long, Ziyue Li, Rui Zhao
In this paper, we propose a Spatial-Temporal Large Language Model (ST-LLM) for traffic prediction.
no code implementations • 15 Jan 2024 • Jay Zhangjie Wu, Guian Fang, HaoNing Wu, Xintao Wang, Yixiao Ge, Xiaodong Cun, David Junhao Zhang, Jia-Wei Liu, YuChao Gu, Rui Zhao, Weisi Lin, Wynne Hsu, Ying Shan, Mike Zheng Shou
Experiments on the TVGE dataset demonstrate the superiority of the proposed T2VScore on offering a better metric for text-to-video generation.
2 code implementations • 26 Dec 2023 • Hangyu Mao, Rui Zhao, Ziyue Li, Zhiwei Xu, Hao Chen, Yiqun Chen, Bin Zhang, Zhen Xiao, Junge Zhang, Jiangjin Yin
Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL.
1 code implementation • 25 Dec 2023 • Rui Zhao, Liang Zhang, Biao Fu, Cong Hu, Jinsong Su, Yidong Chen
The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.
1 code implementation • 22 Dec 2023 • Jiaming Lu, Jingqing Ruan, Haoyuan Jiang, Ziyue Li, Hangyu Mao, Rui Zhao
Furthermore, we implement a scenario-shared Co-Train module to facilitate the learning of generalizable dynamics information across different scenarios.
1 code implementation • 11 Dec 2023 • Zhishuai Li, Ziyue Li, Xiaoru Hu, Guoqing Du, Yunhao Nie, Feng Zhu, Lei Bai, Rui Zhao
Trajectory recovery based on the snapshots from the city-wide multi-camera network facilitates urban mobility sensing and driveway optimization.
no code implementations • 4 Dec 2023 • Lingmin Ran, Xiaodong Cun, Jia-Wei Liu, Rui Zhao, Song Zijie, Xintao Wang, Jussi Keppo, Mike Zheng Shou
To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model.
2 code implementations • 4 Dec 2023 • Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang
Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
Ranked #1 on Pedestrian Image Caption on CUHK-PEDES
no code implementations • 4 Dec 2023 • YuChao Gu, Yipin Zhou, Bichen Wu, Licheng Yu, Jia-Wei Liu, Rui Zhao, Jay Zhangjie Wu, David Junhao Zhang, Mike Zheng Shou, Kevin Tang
In contrast to previous methods that rely on dense correspondences, we introduce the VideoSwap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape.
no code implementations • 23 Nov 2023 • Bin Zhang, Hangyu Mao, Jingqing Ruan, Ying Wen, Yang Li, Shao Zhang, Zhiwei Xu, Dapeng Li, Ziyue Li, Rui Zhao, Lijuan Li, Guoliang Fan
The remarkable progress in Large Language Models (LLMs) opens up new avenues for addressing planning and decision-making problems in Multi-Agent Systems (MAS).
no code implementations • 19 Nov 2023 • Yilun Kong, Jingqing Ruan, Yihong Chen, Bin Zhang, Tianpeng Bao, Shiwei Shi, Guoqing Du, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao
Large Language Models (LLMs) have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools that require a blend of task planning and the utilization of external tools, such as APIs.
no code implementations • 16 Nov 2023 • Yuhan Sun, Mukai Li, Yixin Cao, Kun Wang, Wenxiao Wang, Xingyu Zeng, Rui Zhao
In response, we introduce ControlPE (Continuously Controllable Prompt Engineering).
no code implementations • 13 Nov 2023 • Xuejing Liu, Wei Tang, Xinzhe Ni, Jinghui Lu, Rui Zhao, Zechao Li, Fei Tan
This pipeline achieved superior performance compared to the majority of existing Multimodal Large Language Models (MLLM) on four text-rich VQA datasets.
no code implementations • 5 Nov 2023 • Qianxiong Xu, Cheng Long, Ziyue Li, Sijie Ruan, Rui Zhao, Zhishuai Li
To address this issue, we first present a novel Increment training strategy: instead of masking nodes (and reconstructing them), we add virtual nodes into the training graph so as to mitigate the graph gap issue naturally.
no code implementations • 5 Nov 2023 • Dedong Li, Ziyue Li, Zhishuai Li, Lei Bai, Qingyuan Gong, Lijun Sun, Wolfgang Ketter, Rui Zhao
Then, we propose a Multi-view Graph and Complexity Aware Transformer (MGCAT) model to encode these semantics in trajectory pre-training from two aspects: 1) adaptively aggregate the multi-view graph features considering trajectory pattern, and 2) higher attention to critical nodes in a complex trajectory.
no code implementations • 30 Oct 2023 • Vishal Ramesh, Rui Zhao, Naman Goel
Synthetic data is emerging as a promising way to harness the value of data, while reducing privacy risks.
no code implementations • 28 Oct 2023 • Guanghu Sui, Zhishuai Li, Ziyue Li, Sun Yang, Jingqing Ruan, Hangyu Mao, Rui Zhao
Our experiments with Large Language Models (LLMs) illustrate the significant performance improvement on the business dataset and prove the substantial potential of our method.
no code implementations • 16 Oct 2023 • Jia-Wei Liu, Yan-Pei Cao, Jay Zhangjie Wu, Weijia Mao, YuChao Gu, Rui Zhao, Jussi Keppo, Ying Shan, Mike Zheng Shou
To overcome this, we propose to introduce the dynamic Neural Radiance Fields (NeRF) as the innovative video representation, where the editing can be performed in the 3D spaces and propagated to the entire video via the deformation field.
no code implementations • 12 Oct 2023 • Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo
Active learning presents a promising avenue for training high-performance models with minimal labeled data, achieved by judiciously selecting the most informative instances to label and incorporating them into the task learner.
1 code implementation • 12 Oct 2023 • Rui Zhao, YuChao Gu, Jay Zhangjie Wu, David Junhao Zhang, Jiawei Liu, Weijia Wu, Jussi Keppo, Mike Zheng Shou
Given a set of video clips of the same motion concept, the task of Motion Customization is to adapt existing text-to-video diffusion models to generate videos with this motion.
1 code implementation • 8 Oct 2023 • Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian Ge, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song
In order to encompass common detection expressions, we involve emerging vision-language model (VLM) and large language model (LLM) to generate instructions guided by text prompts and object bbxs, as the generalizations of foundation models are effective to produce human-like expressions (e. g., describing object property, category, and relationship).
1 code implementation • 27 Sep 2023 • David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, YuChao Gu, Difei Gao, Mike Zheng Shou
In this paper, we are the first to propose a hybrid model, dubbed as Show-1, which marries pixel-based and latent-based VDMs for text-to-video generation.
Ranked #2 on Text-to-Video Generation on EvalCrafter Text-to-Video (ECTV) Dataset (using extra training data)
no code implementations • 15 Sep 2023 • Jian Wu, Naoyuki Kanda, Takuya Yoshioka, Rui Zhao, Zhuo Chen, Jinyu Li
Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 14 Sep 2023 • Shaoshi Ling, Guoli Ye, Rui Zhao, Yifan Gong
Attention-based encoder-decoder (AED) speech recognition model has been widely successful in recent years.
no code implementations • 29 Aug 2023 • Lei Han, Qingxu Zhu, Jiapeng Sheng, Chong Zhang, Tingguang Li, Yizheng Zhang, He Zhang, Yuzhen Liu, Cheng Zhou, Rui Zhao, Jie Li, Yufeng Zhang, Rui Wang, Wanchao Chi, Xiong Li, Yonghui Zhu, Lingzhu Xiang, Xiao Teng, Zhengyou Zhang
In this work, we propose a framework for driving legged robots act like real animals with lifelike agility and strategy in complex environments.
1 code implementation • 15 Aug 2023 • Yan Tai, Weichen Fan, Zhao Zhang, Feng Zhu, Rui Zhao, Ziwei Liu
The ability to learn from context with novel concepts, and deliver appropriate responses are essential in human conversations.
1 code implementation • NeurIPS 2023 • Weijia Wu, Yuzhong Zhao, Hao Chen, YuChao Gu, Rui Zhao, Yefei He, Hong Zhou, Mike Zheng Shou, Chunhua Shen
To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic segmentation, instance segmentation, and depth estimation.
no code implementations • 11 Aug 2023 • Yapeng Meng, Songru Yang, Xu Hu, Rui Zhao, Lincheng Li, Zhenwei Shi, Zhengxia Zou
Our method can also be flexibly extended to real-time video face editing.
no code implementations • 7 Aug 2023 • Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao
With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications.
no code implementations • 1 Aug 2023 • Kaijian Liu, Shixiang Tang, Ziyue Li, Zhishuai Li, Lei Bai, Feng Zhu, Rui Zhao
The distribution representation of a clue is a vector consisting of the relation between this clue and all other clues from all modalities, thus being modality agnostic and good for person clustering.
2 code implementations • NeurIPS 2023 • Chi Xie, Zhao Zhang, Yixuan Wu, Feng Zhu, Rui Zhao, Shuang Liang
In this paper, we advance them to a more practical setting called Described Object Detection (DOD) by expanding category names to flexible language expressions for OVD and overcoming the limitation of REC only grounding the pre-existing object.
1 code implementation • 27 Jun 2023 • Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, Rui Zhao
Referential dialogue is a superset of various vision-language (VL) tasks.
Ranked #10 on Visual Question Answering on ViP-Bench
1 code implementation • journal 2023 • Jiangfeng Nan, Weiwen Deng, Member, IEEE, Ruzheng Zhang, Ying Wang, Rui Zhao, Juan Ding
To consider the interaction factor, the reward function for planning is utilized to evaluate the joint trajectories of the autonomous driving vehicle (ADV) and traffic vehicles.
no code implementations • 23 Jun 2023 • Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
1 code implementation • 15 Jun 2023 • Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, Hongsheng Li
By fine-tuning CLIP on HPD v2, we obtain Human Preference Score v2 (HPS v2), a scoring model that can more accurately predict human preferences on generated images.
1 code implementation • 13 Jun 2023 • Weizhen He, Yiheng Deng, Shixiang Tang, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan
This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.
1 code implementation • 12 Jun 2023 • Junpeng Lin, Ziyue Li, Zhishuai Li, Lei Bai, Rui Zhao, Chen Zhang
In this work, we propose a novel approach for traffic prediction that embeds time-varying dynamic Bayesian network to capture the fine spatiotemporal topology of traffic data.
Ranked #13 on Traffic Prediction on METR-LA
1 code implementation • 12 Jun 2023 • Luxuan Wang, Lei Bai, Ziyue Li, Rui Zhao, Fugee Tsung
We evaluated the effectiveness and flexibility of our representation learning framework on correlated time series forecasting and cold-start transferring the forecasting model to new instances with limited data.
Correlated Time Series Forecasting Representation Learning +1
1 code implementation • 5 Jun 2023 • Tian Lan, Ziyue Li, Zhishuai Li, Lei Bai, Man Li, Fugee Tsung, Wolfgang Ketter, Rui Zhao, Chen Zhang
This encourages the multi-task design: with each DAG as a task, the MM-DAG tries to learn the multiple DAGs jointly so that their consensus and consistency are maximized.
1 code implementation • CVPR 2023 • Yuchao Wang, Jingjing Fei, Haochen Wang, Wei Li, Tianpeng Bao, Liwei Wu, Rui Zhao, Yujun Shen
In this way, we manage to close the gap between the feature areas of different categories, resulting in a more balanced representation.
2 code implementations • NeurIPS 2023 • YuChao Gu, Xintao Wang, Jay Zhangjie Wu, Yujun Shi, Yunpeng Chen, Zihan Fan, Wuyou Xiao, Rui Zhao, Shuning Chang, Weijia Wu, Yixiao Ge, Ying Shan, Mike Zheng Shou
Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community.
1 code implementation • 29 May 2023 • Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, Fei Tan
Recent advancements in multimodal foundation models (e. g., CLIP) have excelled in zero-shot generalization.
no code implementations • 29 May 2023 • Jianqiu Chen, Mingshan Sun, Tianpeng Bao, Rui Zhao, Liwei Wu, Zhenyu He
In this paper, we present a CAD model-based zero-shot pose estimation pipeline called ZeroPose.
1 code implementation • ICCV 2023 • Yixuan Wu, Zhao Zhang, Xie Chi, Feng Zhu, Rui Zhao
To overcome this limitation, we propose a more realistic and general setting, named Group-wise Referring Expression Segmentation (GRES), which expands RES to a collection of related images, allowing the described objects to be present in a subset of input images.
no code implementations • 13 May 2023 • Bin Zhang, Hangyu Mao, Lijuan Li, Zhiwei Xu, Dapeng Li, Rui Zhao, Guoliang Fan
Our research contributes to the development of an effective and adaptable asynchronous action coordination method that can be widely applied to various task types and environmental configurations in MAS.
1 code implementation • ICCV 2023 • Xiaoshi Wu, Keqiang Sun, Feng Zhu, Rui Zhao, Hongsheng Li
To address this issue, we collect a dataset of human choices on generated images from the Stable Foundation Discord channel.
no code implementations • 24 Mar 2023 • Yulin Luo, Rui Zhao, Xiaobao Wei, Jinwei Chen, Yijie Lu, Shenghao Xie, Tianyu Wang, Ruiqin Xiong, Ming Lu, Shanghang Zhang
To this end, we propose a method called Weather-aware Multi-scale MoE (WM-MoE) based on Transformer for blind weather removal.
no code implementations • 23 Mar 2023 • Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao
To construct a representative synthetic training dataset, we maximize the diversity of the selected images via a sample-based and cluster-based method.
1 code implementation • CVPR 2023 • Xiaoshi Wu, Feng Zhu, Rui Zhao, Hongsheng Li
To overcome these obstacles, we propose CORA, a DETR-style framework that adapts CLIP for Open-vocabulary detection by Region prompting and Anchor pre-matching.
Ranked #6 on Open Vocabulary Object Detection on MSCOCO (using extra training data)
1 code implementation • 21 Mar 2023 • Yajing Zheng, Jiyuan Zhang, Rui Zhao, Jianhao Ding, Shiyan Chen, Ruiqin Xiong, Zhaofei Yu, Tiejun Huang
SpikeCV focuses on encapsulation for spike data, standardization for dataset interfaces, modularization for vision tasks, and real-time applications for challenging scenes.
no code implementations • 15 Mar 2023 • Guoqiang Jin, Fan Yang, Mingshan Sun, Ruyi Zhao, Yakun Liu, Wei Li, Tianpeng Bao, Liwei Wu, Xingyu Zeng, Rui Zhao
To this end, we propose SeqCo-DETR, a novel Sequence Consistency-based self-supervised method for object DEtection with TRansformers.
1 code implementation • CVPR 2023 • Shixiang Tang, Cheng Chen, Qingsong Xie, Meilin Chen, Yizhou Wang, Yuanzheng Ci, Lei Bai, Feng Zhu, Haiyang Yang, Li Yi, Rui Zhao, Wanli Ouyang
Specifically, we propose a \textbf{HumanBench} based on existing datasets to comprehensively evaluate on the common ground the generalization abilities of different pretraining methods on 19 datasets from 6 diverse downstream tasks, including person ReID, pose estimation, human parsing, pedestrian attribute recognition, pedestrian detection, and crowd counting.
Ranked #1 on Pedestrian Attribute Recognition on PA-100K (using extra training data)
1 code implementation • CVPR 2023 • Yuanzheng Ci, Yizhou Wang, Meilin Chen, Shixiang Tang, Lei Bai, Feng Zhu, Rui Zhao, Fengwei Yu, Donglian Qi, Wanli Ouyang
When adapted to a specific task, UniHCP achieves new SOTAs on a wide range of human-centric tasks, e. g., 69. 8 mIoU on CIHP for human parsing, 86. 18 mA on PA-100K for attribute prediction, 90. 3 mAP on Market1501 for ReID, and 85. 8 JI on CrowdHuman for pedestrian detection, performing better than specialized models tailored for each task.
Ranked #1 on Pose Estimation on MS-COCO
no code implementations • CVPR 2023 • Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li, Zhengxia Zou, Zhenwei Shi, Changjie Fan
In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework.
no code implementations • 28 Feb 2023 • Shaobo Lin, Kun Wang, Xingyu Zeng, Rui Zhao
Specifically, we first discover the base images which contain the FP of novel categories and select a certain amount of samples from them for the base and novel categories balance.
no code implementations • 28 Feb 2023 • Zhaowen Li, Yousong Zhu, Zhiyang Chen, Wei Li, Chaoyang Zhao, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
However, its high random mask ratio would result in two serious problems: 1) the data are not efficiently exploited, which brings inefficient pre-training (\eg, 1600 epochs for MAE $vs.$ 300 epochs for the supervised), and 2) the high uncertainty and inconsistency of the pre-trained model, \ie, the prediction of the same patch may be inconsistent under different mask rounds.
no code implementations • 22 Feb 2023 • Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Haiyang Yang, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang
Despite being feasible, recent works largely overlooked discovering the most discriminative regions for contrastive learning to object representations in scene images.
no code implementations • 26 Jan 2023 • Shaobo Lin, Xingyu Zeng, Rui Zhao
The generalization power of the pre-trained model is the key for few-shot deep learning.
no code implementations • ICCV 2023 • Aojun Zhou, Yang Li, Zipeng Qin, Jianbo Liu, Junting Pan, Renrui Zhang, Rui Zhao, Peng Gao, Hongsheng Li
In this paper, we aim to reduce model complexity from large vision transformers pretrained by MAE with assistant of sparse training.
1 code implementation • 30 Dec 2022 • Hangyu Mao, Rui Zhao, Hao Chen, Jianye Hao, Yiqun Chen, Dong Li, Junge Zhang, Zhen Xiao
Recent methods combine the Transformer with these modules for better performance.
no code implementations • 5 Dec 2022 • Rui Zhao, Jian Xue, Partha Parthasarathy, Veljko Miljanic, Jinyu Li
Neural transducer is now the most popular end-to-end model for speech recognition, due to its naturally streaming ability.
1 code implementation • 3 Dec 2022 • Yu Qi, Fan Yang, Yousong Zhu, Yufei Liu, Liwei Wu, Rui Zhao, Wei Li
By introducing stochastic prediction and the parallel encoder-decoder, SAIM significantly improve the performance of autoregressive image modeling.
1 code implementation • 27 Nov 2022 • Jinghui Lu, Rui Zhao, Brian Mac Namee, Fei Tan
In this work, we present a ``versatile'' model -- the Prompting-based Unified NER system (PUnifiedNER) -- that works with data from different domains and can recognise up to 37 entity types simultaneously, and theoretically it could be as many as possible.
no code implementations • 25 Nov 2022 • Tianpeng Bao, Jiadong Chen, Wei Li, Xiang Wang, Jingjing Fei, Liwei Wu, Rui Zhao, Ye Zheng
However, existing datasets for unsupervised anomaly detection are biased towards manufacturing inspection, not considering maintenance inspection which is usually conducted under outdoor uncontrolled environment such as varying camera viewpoints, messy background and degradation of object surface after long-term working.
no code implementations • 17 Nov 2022 • Xun Gong, Yu Wu, Jinyu Li, Shujie Liu, Rui Zhao, Xie Chen, Yanmin Qian
This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 20 Oct 2022 • Jianqiu Chen, Mingshan Sun, Ye Zheng, Tianpeng Bao, Zhenyu He, Donghai Li, Guoqiang Jin, Rui Zhao, Liwei Wu, Xiaoke Jiang
Numerous 6D pose estimation methods have been proposed that employ end-to-end regression to directly estimate the target pose parameters.
no code implementations • 12 Oct 2022 • Shaobo Lin, Xingyu Zeng, Rui Zhao
Conventional training of deep neural networks usually requires a substantial amount of data with expensive human annotations.
1 code implementation • 8 Oct 2022 • Dongsheng Zhu, Zhenyu Mao, Jinghui Lu, Rui Zhao, Fei Tan
Contrastive learning has recently achieved compelling performance in unsupervised sentence representation.
1 code implementation • 30 Sep 2022 • Jinghui Lu, Dongsheng Zhu, Weidong Han, Rui Zhao, Brian Mac Namee, Fei Tan
Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori.
2 code implementations • 28 Sep 2022 • Zhiyang Chen, Yousong Zhu, Zhaowen Li, Fan Yang, Wei Li, Haixin Wang, Chaoyang Zhao, Liwei Wu, Rui Zhao, Jinqiao Wang, Ming Tang
Obj2Seq is able to flexibly determine input categories to satisfy customized requirements, and be easily extended to different visual tasks.
1 code implementation • 15 Sep 2022 • Ye Du, Yujun Shen, Haochen Wang, Jingjing Fei, Wei Li, Liwei Wu, Rui Zhao, Zehua Fu, Qingjie Liu
Self-training has shown great potential in semi-supervised learning.
1 code implementation • 14 Sep 2022 • Zhenyu Mao, Ziyue Li, Dedong Li, Lei Bai, Rui Zhao
Unlike the existing cross-scale contrastive learning methods on graphs that only contrast a graph and its belonging nodes, the contrast between road segment and trajectory is elaborately tailored via novel positive sampling and adaptive weighting strategies.
no code implementations • 15 Aug 2022 • Mingshan Sun, Ye Zheng, Tianpeng Bao, Jianqiu Chen, Guoqiang Jin, Liwei Wu, Rui Zhao, Xiaoke Jiang
Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images.
no code implementations • 1 Aug 2022 • Xulin Li, Yan Lu, Bin Liu, Yating Liu, Guojun Yin, Qi Chu, Jinyang Huang, Feng Zhu, Rui Zhao, Nenghai Yu
But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap, which is a property of VI-ReID task.
no code implementations • 22 Jun 2022 • Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao
In this work, we propose Auto-Encoding Adversarial Imitation Learning (AEAIL), a robust and scalable AIL framework.
no code implementations • 10 May 2022 • Haiyang Yang, Meilin Chen, Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Wanli Ouyang
While recent self-supervised learning methods have achieved good performances with evaluation set on the same domain as the training set, they will have an undesirable performance decrease when tested on a different domain.
no code implementations • 28 Apr 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
Scalability is an important consideration for deep graph neural networks.
no code implementations • CVPR 2022 • Xiaoke Jiang, Donghai Li, Hao Chen, Ye Zheng, Rui Zhao, Liwei Wu
They use a 2D CNN for RGB images and a per-pixel point cloud network for depth data, as well as a fusion network for feature fusion.
no code implementations • CVPR 2022 • Zhaowen Li, Yousong Zhu, Fan Yang, Wei Li, Chaoyang Zhao, Yingying Chen, Zhiyang Chen, Jiahao Xie, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
1 code implementation • CVPR 2022 • Yuchao Wang, Haochen Wang, Yujun Shen, Jingjing Fei, Wei Li, Guoqiang Jin, Liwei Wu, Rui Zhao, Xinyi Le
A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.
no code implementations • CVPR 2022 • Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiaokang Yang
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
2 code implementations • 22 Dec 2021 • Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng, Yang Gao, Yi Wu, Zhongqian Sun, Yang Wei
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data.
1 code implementation • CVPR 2022 • Zhikang Wang, Feng Zhu, Shixiang Tang, Rui Zhao, Lihuo He, Jiangning Song
With the guidance of the occlusion scores from OEM, the feature diffusion process is mainly conducted on visible body parts, which guarantees the quality of the synthesized NTP characteristics.
Ranked #1 on Person Re-Identification on Occluded REID (Rank-1 metric)
no code implementations • CVPR 2022 • Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang
The pretrain-finetune paradigm is a classical pipeline in visual learning.
5 code implementations • 15 Nov 2021 • Jiawei Yu, Ye Zheng, Xiang Wang, Wei Li, Yushuang Wu, Rui Zhao, Liwei Wu
However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies.
Ranked #20 on Anomaly Detection on MVTec AD
Unsupervised Anomaly Detection Weakly Supervised Defect Detection
no code implementations • 2 Nov 2021 • Peng Zhi, Haoran Zhou, Hang Huang, Rui Zhao, Rui Zhou, Qingguo Zhou
In the field of state-of-the-art object detection, the task of object localization is typically accomplished through a dedicated subnet that emphasizes bounding box regression.
no code implementations • 9 Oct 2021 • Ye Zheng, Xiang Wang, Rui Deng, Tianpeng Bao, Rui Zhao, Liwei Wu
To facilitate the learning with only normal images, we propose a new pretext task called non-contrastive learning for the fine alignment stage.
Ranked #49 on Anomaly Detection on MVTec AD
1 code implementation • CVPR 2022 • Liwen Hu, Rui Zhao, Ziluo Ding, Lei Ma, Boxin Shi, Ruiqin Xiong, Tiejun Huang
Further, for training SCFlow, we synthesize two sets of optical flow data for the spiking camera, SPIkingly Flying Things and Photo-realistic High-speed Motion, denoted as SPIFT and PHM respectively, corresponding to random high-speed and well-designed scenes.
no code implementations • 3 Oct 2021 • Rui Zhao, Malcolm Atkinson, Petros Papapanagiotou, Federica Magnoni, Jacques Fleuriot
It depends on federations sharing data that often have governance rules or external regulations restricting their use.
no code implementations • 29 Sep 2021 • Shaobo Lin, Xingyu Zeng, Rui Zhao
Conventional training of deep neural networks usually requires a substantial amount of data with expensive human annotations.
no code implementations • 29 Sep 2021 • Yizhou Wang, Shixiang Tang, Feng Zhu, Lei Bai, Rui Zhao, Donglian Qi, Wanli Ouyang
The pretrain-finetune paradigm is a classical pipeline in visual learning.
no code implementations • ICLR 2022 • Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiaokang Yang
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
no code implementations • 29 Sep 2021 • Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function.
no code implementations • 21 Sep 2021 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Keyu Wu, Min Wu, Rui Zhao, Zhenghua Chen
Multi-Source Domain Adaptation (MSDA) is a more practical domain adaptation scenario in real-world scenarios.
1 code implementation • 10 Sep 2021 • Ziluo Ding, Rui Zhao, Jiyuan Zhang, Tianxiao Gao, Ruiqin Xiong, Zhaofei Yu, Tiejun Huang
Recently, many deep learning methods have shown great success in providing promising solutions to many event-based problems, such as optical flow estimation.
no code implementations • 2 Sep 2021 • Rui Zhao
We propose Dr. Aid, a logic-based AI framework for automated compliance checking of data governance rules over data-flow graphs.
no code implementations • NeurIPS 2021 • Zhaowen Li, Zhiyang Chen, Fan Yang, Wei Li, Yousong Zhu, Chaoyang Zhao, Rui Deng, Liwei Wu, Rui Zhao, Ming Tang, Jinqiao Wang
More importantly, the masked tokens together with the remaining tokens are further recovered by a global image decoder, which preserves the spatial information of the image and is more friendly to the downstream dense prediction tasks.
no code implementations • 28 May 2021 • Zhenghao Chen, Shuhang Gu, Feng Zhu, Jing Xu, Rui Zhao
For the spatial correlation, we aggregate attributes with spatial similarity into a part-based group and then introduce a Group Attention Learning to generate the group attention and the part-based group feature.
no code implementations • 26 May 2021 • Shijie Yu, Feng Zhu, Dapeng Chen, Rui Zhao, Haobin Chen, Shixiang Tang, Jinguo Zhu, Yu Qiao
In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts.
no code implementations • 16 May 2021 • Shijie Yu, Dapeng Chen, Rui Zhao, Haobin Chen, Yu Qiao
Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance.
no code implementations • 27 Apr 2021 • Yixiao Ge, Xiao Zhang, Ching Lam Choi, Ka Chun Cheung, Peipei Zhao, Feng Zhu, Xiaogang Wang, Rui Zhao, Hongsheng Li
In this way, our BAKE framework achieves online knowledge ensembling across multiple samples with only a single network.
no code implementations • 27 Apr 2021 • Rui Zhao, Jian Xue, Jinyu Li, Wenning Wei, Lei He, Yifan Gong
The first challenge is solved with a splicing data method which concatenates the speech segments extracted from the source domain data.
no code implementations • 29 Mar 2021 • Rui Zhao, Kecheng Zheng, Zheng-Jun Zha, Hongtao Xie, Jiebo Luo
The cross-modal memory module is employed to record the instance embeddings of all the datasets for global negative mining.
2 code implementations • ICLR 2021 • Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu
Reinforcement learning has been shown to be highly successful at many challenging tasks.
1 code implementation • ICCV 2021 • Chen Zhao, Yixiao Ge, Feng Zhu, Rui Zhao, Hongsheng Li, Mathieu Salzmann
Correspondence selection aims to correctly select the consistent matches (inliers) from an initial set of putative correspondences.
no code implementations • 3 Nov 2020 • Zhong Meng, Sarangarajan Parthasarathy, Eric Sun, Yashesh Gaur, Naoyuki Kanda, Liang Lu, Xie Chen, Rui Zhao, Jinyu Li, Yifan Gong
The external language models (LM) integration remains a challenging task for end-to-end (E2E) automatic speech recognition (ASR) which has no clear division between acoustic and language models.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 2 Nov 2020 • Rui Zhao
Based on current security threats faced by deep learning, this paper introduces the problem of adversarial examples in deep learning, sorts out the existing attack and defense methods of the black box and white box, and classifies them.
no code implementations • 9 Sep 2020 • Rui Zhao, Daniel P. K. Lun, Kin-Man Lam
Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks.
no code implementations • 12 Aug 2020 • Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li
Transfer learning (TL) is widely used in conventional hybrid automatic speech recognition (ASR) system, to transfer the knowledge from source to target language.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 11 Aug 2020 • Yongchao Liu, Yue Jin, Yong Chen, Teng Teng, Hang Ou, Rui Zhao, Yao Zhang
Accelerating deep model training and inference is crucial in practice.
no code implementations • 1 Aug 2020 • Rui Zhao, Xinjie Wang, Junjuan Xia, Liseng Fan
In particular, the system cost of latency and energy consumption can be reduced significantly by the proposed deep reinforcement learning based algorithm.
no code implementations • 30 Jul 2020 • Jinyu Li, Rui Zhao, Zhong Meng, Yanqing Liu, Wenning Wei, Sarangarajan Parthasarathy, Vadim Mazalov, Zhenghao Wang, Lei He, Sheng Zhao, Yifan Gong
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 9 Jul 2020 • Rui Zhao, Tianshan Liu, Jun Xiao, Daniel P. K. Lun, Kin-Man Lam
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks.
Facial Expression Recognition Facial Expression Recognition (FER) +2
1 code implementation • 2 Jul 2020 • Zhiliang Wu, Yinchong Yang, Yunpu Ma, Yushan Liu, Rui Zhao, Michael Moor, Volker Tresp
Randomized controlled trials typically analyze the effectiveness of treatments with the goal of making treatment recommendations for patient subgroups.
no code implementations • 28 Jun 2020 • Rui Zhao, Kin-Man Lam, Daniel P. K. Lun
Since most of the content or energy of natural images resides in the low-frequency spectrum, their transformed coefficients in the frequency domain are highly imbalanced.
1 code implementation • 8 Jun 2020 • Bo Zhao, Shixiang Tang, Dapeng Chen, Hakan Bilen, Rui Zhao
With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important.
3 code implementations • ECCV 2020 • Yixiao Ge, Haibo Wang, Feng Zhu, Rui Zhao, Hongsheng Li
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset.
3 code implementations • NeurIPS 2020 • Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li
To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory.
Ranked #3 on Unsupervised Domain Adaptation on Market to MSMT
1 code implementation • CVPR 2020 • Rui Zhao, Hui Su, Qiang Ji
By explicitly capturing the distribution of the data and parameters, our model has a more compact parameterization compared to GAN-based generative models.
1 code implementation • 28 May 2020 • Jinyu Li, Yu Wu, Yashesh Gaur, Chengyi Wang, Rui Zhao, Shujie Liu
Among all three E2E models, transformer-AED achieved the best accuracy in both streaming and non-streaming mode.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • CVPR 2020 • Shijie Yu, Shihua Li, Dapeng Chen, Rui Zhao, Junjie Yan, Yu Qiao
To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes.
no code implementations • 1 May 2020 • Hu Hu, Rui Zhao, Jinyu Li, Liang Lu, Yifan Gong
Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 10 Apr 2020 • Rui Zhao, Kecheng Zheng, Zheng-Jun Zha
Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity.
3 code implementations • CVPR 2020 • Lei Yang, Dapeng Chen, Xiaohang Zhan, Rui Zhao, Chen Change Loy, Dahua Lin
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
no code implementations • 17 Mar 2020 • Jinyu Li, Rui Zhao, Eric Sun, Jeremy H. M. Wong, Amit Das, Zhong Meng, Yifan Gong
While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that such conventional hybrid models can still be significantly improved.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
3 code implementations • 14 Mar 2020 • Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Xiaogang Wang, Hongsheng Li
To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.
Ranked #4 on Unsupervised Domain Adaptation on Market to MSMT
no code implementations • 5 Feb 2020 • Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp, Wei Xu
In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal.
no code implementations • 19 Nov 2019 • Rui Zhao, Malcolm Atkinson
With the needs of science and business, data sharing and re-use has become an intensive activity for various areas.
no code implementations • ICCV 2019 • Rui Zhao, Kang Wang, Hui Su, Qiang Ji
Finally, the whole model is extended under the Bayesian framework to a probabilistic model in order to better capture the stochasticity and variation in the data.
Ranked #91 on Skeleton Based Action Recognition on NTU RGB+D
1 code implementation • 26 Sep 2019 • Jinyu Li, Rui Zhao, Hu Hu, Yifan Gong
In this paper, we improve the RNN-T training in two aspects.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 25 Sep 2019 • Rui Zhao, Volker Tresp, Wei Xu
Our results show that the mutual information between the context states and the states of interest can be an effective ingredient for overcoming challenges in robotic manipulation tasks with sparse rewards.
no code implementations • ICCV 2019 • Suichan Li, Dapeng Chen, Bin Liu, Nenghai Yu, Rui Zhao
Learning discriminative image feature embeddings is of great importance to visual recognition.
1 code implementation • CVPR 2019 • Rui Zhao, Wanru Xu, Hui Su, Qiang Ji
Human action recognition remains as a challenging task partially due to the presence of large variations in the execution of action.
Ranked #3 on Skeleton Based Action Recognition on MSR Action3D
3 code implementations • 21 May 2019 • Rui Zhao, Xudong Sun, Volker Tresp
This objective encourages the agent to maximize the expected return, as well as to achieve more diverse goals.
no code implementations • CVPR 2019 • Xiao Zhang, Rui Zhao, Junjie Yan, Mengya Gao, Yu Qiao, Xiaogang Wang, Hongsheng Li
Cosine-based softmax losses significantly improve the performance of deep face recognition networks.
5 code implementations • CVPR 2019 • Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li
Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy.
Ranked #6 on Face Verification on MegaFace
no code implementations • 4 Apr 2019 • Rui Zhao, David Bieber, Kevin Swersky, Daniel Tarlow
In this work, we instead treat source code as a dynamic object and tackle the problem of modeling the edits that software developers make to source code files.
no code implementations • 20 Feb 2019 • Rui Zhao, Volker Tresp
In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning.
no code implementations • 31 Dec 2018 • Amit Das, Jinyu Li, Guoli Ye, Rui Zhao, Yifan Gong
In particular, we introduce Attention CTC, Self-Attention CTC, Hybrid CTC, and Mixed-unit CTC.
2 code implementations • 2 Oct 2018 • Rui Zhao, Volker Tresp
This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning.
2 code implementations • 2 Oct 2018 • Rui Zhao, Volker Tresp
We evaluate our Energy-Based Prioritization (EBP) approach on four challenging robotic manipulation tasks in simulation.
1 code implementation • 2 Jul 2018 • Rui Zhao, Volker Tresp
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic.
no code implementations • CVPR 2018 • Kang Wang, Rui Zhao, Qiang Ji
Through a top-down inference, the HGM can synthesize eye images consistent with the given eye gaze.
no code implementations • CVPR 2018 • Yong Zhang, Rui Zhao, Wei-Ming Dong, Bao-Gang Hu, Qiang Ji
The majority of methods directly apply supervised learning techniques to AU intensity estimation while few methods exploit unlabeled samples to improve the performance.
no code implementations • CVPR 2018 • Jing Xu, Rui Zhao, Feng Zhu, Huaming Wang, Wanli Ouyang
AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC).
15 code implementations • ICLR 2018 • Adams Wei Yu, David Dohan, Minh-Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le
On the SQuAD dataset, our model is 3x to 13x faster in training and 4x to 9x faster in inference, while achieving equivalent accuracy to recurrent models.
Ranked #27 on Question Answering on SQuAD1.1 dev
no code implementations • 14 Apr 2018 • Jinyu Li, Rui Zhao, Zhuo Chen, Changliang Liu, Xiong Xiao, Guoli Ye, Yifan Gong
In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system.
no code implementations • 15 Mar 2018 • Jinyu Li, Guoli Ye, Amit Das, Rui Zhao, Yifan Gong
However, the word-based CTC model suffers from the out-of-vocabulary (OOV) issue as it can only model limited number of words in the output layer and maps all the remaining words into an OOV output node.
no code implementations • 15 Mar 2018 • Amit Das, Jinyu Li, Rui Zhao, Yifan Gong
In this study, we propose advancing all-neural speech recognition by directly incorporating attention modeling within the Connectionist Temporal Classification (CTC) framework.
4 code implementations • 10 Jan 2018 • Daniel A. Abolafia, Mohammad Norouzi, Jonathan Shen, Rui Zhao, Quoc V. Le
Models and examples built with TensorFlow
no code implementations • 28 Nov 2017 • Jinyu Li, Guoli Ye, Rui Zhao, Jasha Droppo, Yifan Gong
However, this type of word-based CTC model suffers from the out-of-vocabulary (OOV) issue as it can only model limited number of words in the output layer and maps all the remaining words into an OOV output node.
1 code implementation • 6 Nov 2017 • Suyoun Kim, Michael L. Seltzer, Jinyu Li, Rui Zhao
Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training.
no code implementations • 17 Aug 2017 • Jinyu Li, Michael L. Seltzer, Xi Wang, Rui Zhao, Yifan Gong
High accuracy speech recognition requires a large amount of transcribed data for supervised training.
no code implementations • 17 Apr 2017 • Rui Zhao, Raymond H. Chan
Then a low-rank model is used to construct the reference frame in high-resolution by incorporating the information of the low-resolution frames.
no code implementations • 22 Mar 2017 • Rui Zhao, Haider Ali, Patrick van der Smagt
The recognition of actions from video sequences has many applications in health monitoring, assisted living, surveillance, and smart homes.
no code implementations • 8 Feb 2017 • Pei Wang, Guochao Bu, Ronghao Li, Rui Zhao
The new scanner was named as BEE, which can scan the forest trees in three dimension.
1 code implementation • 16 Dec 2016 • Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, Robert X. Gao
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation.
no code implementations • CVPR 2016 • Rui Zhao, Quan Gan, Shangfei Wang, Qiang Ji
In fully supervised case, all the frames are provided with intensity annotations.
no code implementations • CVPR 2015 • Rui Zhao, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance.
no code implementations • 15 Dec 2014 • Hongsheng Li, Rui Zhao, Xiaogang Wang
The proposed algorithms eliminate all the redundant computation in convolution and pooling on images by introducing novel d-regularly sparse kernels.
no code implementations • 5 Dec 2014 • Rui Zhao, Wanli Ouyang, Xiaogang Wang
(3) saliency matching is proposed based on patch matching.
1 code implementation • 8 Sep 2014 • Anthony Iarrobino, Leila Khatami, Bart Van Steirteghem, Rui Zhao
In 2012 P. Oblak formulated a conjecture concerning the cardinality of the set of partitions $P$ such that ${\mathcal Q}(P)$ is a given stable partition $ Q$ with two parts, and proved some special cases.
Rings and Algebras Commutative Algebra Representation Theory 15A27 (Primary), 05E40 (Secondary), 13E10, 15A21
no code implementations • CVPR 2014 • Rui Zhao, Wanli Ouyang, Xiaogang Wang
In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification.
no code implementations • CVPR 2014 • Wei Li, Rui Zhao, Tong Xiao, Xiaogang Wang
In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter.
no code implementations • CVPR 2013 • Rui Zhao, Wanli Ouyang, Xiaogang Wang
In this paper, we propose a novel perspective for person re-identification based on unsupervised salience learning.