no code implementations • ECCV 2020 • Jiabin Xing, Zhi Qi, Jiying Dong, Jiaxuan Cai, Hao liu
MABNet is based on a novel Multibranch Adjustable Bottleneck (MAB) module, which is less demanding on parameters and computation.
no code implementations • Findings (EMNLP) 2021 • MengNan Qi, Hao liu, Yuzhuo Fu, Ting Liu
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers.
no code implementations • EMNLP 2020 • Yunjie Ji, Hao liu, Bolei He, Xinyan Xiao, Hua Wu, Yanhua Yu
To this end, we propose a novel Diversified Multiple Instance Learning Network (D-MILN), which is able to achieve aspect-level sentiment classification with only document-level weak supervision.
no code implementations • 29 Sep 2023 • Hao liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, DaCheng Tao, Yixin Chen, Muhan Zhang
For in-context learning on graphs, OFA introduces a novel graph prompting paradigm that appends prompting substructures to the input graph, which enables it to address varied tasks without fine-tuning.
no code implementations • ICCV 2023 • Lu Dai, Liqian Ma, Shenhan Qian, Hao liu, Ziwei Liu, Hui Xiong
Finally, how to generate diverse and plausible results from a 2D clothing image.
no code implementations • 22 Sep 2023 • Xiaoheng Jiang, Shilong Tian, Zhiwen Zhu, Yang Lu, Hao liu, Li Chen, Shupan Li, Mingliang Xu
In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage.
no code implementations • 22 Sep 2023 • Xiaoheng Jiang, Kaiyi Guo, Yang Lu, Feng Yan, Hao liu, Jiale Cao, Mingliang Xu, DaCheng Tao
To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer.
1 code implementation • 19 Sep 2023 • Hao liu, Jiarui Feng, Lecheng Kong, DaCheng Tao, Yixin Chen, Muhan Zhang
In our study, we first identify two crucial advantages of contrastive learning compared to meta learning, including (1) the comprehensive utilization of graph nodes and (2) the power of graph augmentations.
1 code implementation • 19 Sep 2023 • Changyeon Kim, Younggyo Seo, Hao liu, Lisa Lee, Jinwoo Shin, Honglak Lee, Kimin Lee
Developing an agent capable of adapting to unseen environments remains a difficult challenge in imitation learning.
no code implementations • 5 Sep 2023 • Tomasz R. Bielecki, Igor Cialenco, Hao liu
We prove that these two classes of risk measures coincides.
no code implementations • ICCV 2023 • Haoyu Cao, Changcun Bao, Chaohu Liu, Huang Chen, Kun Yin, Hao liu, Yinsong Liu, Deqiang Jiang, Xing Sun
We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation.
no code implementations • 31 Aug 2023 • Weijia Zhang, Le Zhang, Jindong Han, Hao liu, Jingbo Zhou, Yu Mei, Hui Xiong
Accurate traffic forecasting at intersections governed by intelligent traffic signals is critical for the advancement of an effective intelligent traffic signal control system.
no code implementations • 19 Jul 2023 • Xiaohong Liu, Xiongkuo Min, Wei Sun, Yulun Zhang, Kai Zhang, Radu Timofte, Guangtao Zhai, Yixuan Gao, Yuqin Cao, Tengchuan Kou, Yunlong Dong, Ziheng Jia, Yilin Li, Wei Wu, Shuming Hu, Sibin Deng, Pengxiang Xiao, Ying Chen, Kai Li, Kai Zhao, Kun Yuan, Ming Sun, Heng Cong, Hao Wang, Lingzhi Fu, Yusheng Zhang, Rongyu Zhang, Hang Shi, Qihang Xu, Longan Xiao, Zhiliang Ma, Mirko Agarla, Luigi Celona, Claudio Rota, Raimondo Schettini, Zhiwei Huang, Yanan Li, Xiaotao Wang, Lei Lei, Hongye Liu, Wei Hong, Ironhead Chuang, Allen Lin, Drake Guan, Iris Chen, Kae Lou, Willy Huang, Yachun Tasi, Yvonne Kao, Haotian Fan, Fangyuan Kong, Shiqi Zhou, Hao liu, Yu Lai, Shanshan Chen, Wenqi Wang, HaoNing Wu, Chaofeng Chen, Chunzheng Zhu, Zekun Guo, Shiling Zhao, Haibing Yin, Hongkui Wang, Hanene Brachemi Meftah, Sid Ahmed Fezza, Wassim Hamidouche, Olivier Déforges, Tengfei Shi, Azadeh Mansouri, Hossein Motamednia, Amir Hossein Bakhtiari, Ahmad Mahmoudi Aznaveh
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
no code implementations • 18 Jul 2023 • Xue-Cheng Tai, Hao liu, Raymond Chan
We use the two-phase Potts model for image segmentation as an example for our explanations.
no code implementations • 18 Jul 2023 • Hao liu, Xue-Cheng Tai, Raymond Chan
In this paper, we give an algorithmic explanation for deep neural networks, especially in their connection with operator splitting and multigrid methods.
no code implementations • 6 Jul 2023 • Sheng-Lan Liu, Yu-Ning Ding, Si-Fan Zhang, Wen-Yue Chen, Ning Zhou, Hao liu, Gui-Hong Lao
MMFS, which possesses action recognition and action quality assessment, captures RGB, skeleton, and is collected the score of actions from 11671 clips with 256 categories including spatial and temporal labels.
1 code implementation • 26 Jun 2023 • Siqi Lai, Weijia Zhang, Hao liu
To this end, this paper proposes a preference-aware meta-optimization framework Meta-Pec for personalized vehicle energy consumption estimation.
1 code implementation • 25 Jun 2023 • Fan Liu, Weijia Zhang, Hao liu
Therefore, improving the adversarial robustness of these models is crucial for ITS.
1 code implementation • 20 Jun 2023 • Yansong Ning, Hao liu, Hao Wang, Zhenyu Zeng, Hui Xiong
We hope the proposed UUKG fosters research on urban knowledge graphs and broad smart city applications.
1 code implementation • 17 Jun 2023 • Fan Liu, Siqi Lai, Yansong Ning, Hao liu
To address these limitations, we propose Bkd-FedGNN, a benchmark for backdoor attacks on FedGNN.
1 code implementation • 5 Jun 2023 • Jiarui Feng, Lecheng Kong, Hao liu, DaCheng Tao, Fuhai Li, Muhan Zhang, Yixin Chen
We theoretically prove that even if we fix the space complexity to $O(n^2)$ in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem.
2 code implementations • 30 May 2023 • Hao liu, Pieter Abbeel
Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications.
no code implementations • 26 May 2023 • Hao liu, Pieter Abbeel
Our method consists of relabelling target return of each trajectory to the maximum total reward among in sequence of trajectories and training an autoregressive model to predict actions conditioning on past states, actions, rewards, target returns, and task completion tokens, the resulting model, Agentic Transformer (AT), can learn to improve upon itself both at training and test time.
1 code implementation • 25 May 2023 • Arnav Gudibande, Eric Wallace, Charlie Snell, Xinyang Geng, Hao liu, Pieter Abbeel, Sergey Levine, Dawn Song
This approach looks to cheaply imitate the proprietary model's capabilities using a weaker open-source model.
no code implementations • 25 May 2023 • Ying Fan, Olivia Watkins, Yuqing Du, Hao liu, MoonKyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, Kimin Lee
These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learned reward function.
no code implementations • 19 May 2023 • Hao liu, Huimin Ma, Tianyu Hu
In this paper, a Graph-attentive Frequency-enhanced Spatial-Temporal Wind Speed Forecasting model based on graph attention and frequency-enhanced mechanisms, i. e., GFST-WSF, is proposed to improve the accuracy of short-term wind speed forecasting.
no code implementations • 24 Apr 2023 • Xing Jia, Jiancheng An, Hao liu, Hongshu Liao, Lu Gan, Chau Yuen
Reconfigurable intelligent surface (RIS) is a revolutionary technology that can customize the wireless channel and improve the energy efficiency of next-generation cellular networks.
1 code implementation • 20 Apr 2023 • Yongming Yang, Shuwei Shao, Tao Yang, Peng Wang, Zhuo Yang, Chengdong Wu, Hao liu
To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures.
no code implementations • 4 Apr 2023 • Yongxin Zhu, Zhen Liu, Yukang Liang, Xin Li, Hao liu, Changcun Bao, Linli Xu
Different to conventional STVQA models which take the linguistic semantics and visual semantics in scene text as two separate features, in this paper, we propose a paradigm of "Locate Then Generate" (LTG), which explicitly unifies this two semantics with the spatial bounding box as a bridge connecting them.
no code implementations • 4 Apr 2023 • Liu Yang, Di Chai, Junxue Zhang, Yilun Jin, Leye Wang, Hao liu, Han Tian, Qian Xu, Kai Chen
From the hardware layer to the vertical federated system layer, researchers contribute to various aspects of VFL.
1 code implementation • 4 Apr 2023 • Ninghao Pu, Zhongxing Wu, Ao Wang, Hanshi Sun, Zijin Liu, Hao liu
With the development of deep learning, numerous ECG classification algorithms based on deep learning have emerged.
no code implementations • 2 Apr 2023 • Haitian Liu, Ye Guo, Hao liu
Improving renewable energy resource utilization efficiency is crucial to reducing carbon emissions, and multi-parametric programming has provided a systematic perspective in conducting analysis and optimization toward this goal in smart grid operations.
no code implementations • 25 Mar 2023 • Zhouzheng Li, Hao liu
Beta-VAE is a very classical model for disentangled representation learning, the use of an expanding bottleneck that allow information into the decoder gradually is key to representation disentanglement as well as high-quality reconstruction.
no code implementations • 24 Mar 2023 • Jinrui Xing, Hui Yuan, Raouf Hamzaoui, Hao liu, Junhui Hou
Specifically, we use a parallel-serial graph attention module with a multi-head graph attention mechanism to focus on important points or features and help them fuse together.
no code implementations • 17 Mar 2023 • Hao liu, Alex Havrilla, Rongjie Lai, Wenjing Liao
Our paper establishes statistical guarantees on the generalization error of chart autoencoders, and we demonstrate their denoising capabilities by considering $n$ noisy training samples, along with their noise-free counterparts, on a $d$-dimensional manifold.
no code implementations • 16 Mar 2023 • Hao liu, Xin Li, Mingming Gong, Bing Liu, Yunfei Wu, Deqiang Jiang, Yinsong Liu, Xing Sun
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community.
no code implementations • 5 Mar 2023 • Hao liu, Muhan Zhang, Zehao Dong, Lecheng Kong, Yixin Chen, Bradley Fritz, DaCheng Tao, Christopher King
We view time-associated disease prediction as classification tasks at multiple time points.
no code implementations • International Journal of Machine Learning and Cybernetics 2023 • Dazhi Jiang, Hao liu, Geng Tu & Runguo Wei
The Causal Emotion Entailment (CEE) task aims to extract all potential pairs of emotions and corresponding causes from the unannotated emotion document in the conversational context.
Ranked #2 on
Causal Emotion Entailment
on RECCON
1 code implementation • 23 Feb 2023 • Kimin Lee, Hao liu, MoonKyung Ryu, Olivia Watkins, Yuqing Du, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Shixiang Shane Gu
Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.
3 code implementations • 6 Feb 2023 • Hao liu, Carmelo Sferrazza, Pieter Abbeel
Applying our method to large language models, we observed that Chain of Hindsight significantly surpasses previous methods in aligning language models with human preferences.
1 code implementation • 2 Feb 2023 • Hao liu, Wilson Yan, Pieter Abbeel
Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks.
no code implementations • Cognitive Computation 2023 • Dazhi Jiang, Hao liu, Runguo Wei, Geng Tu
Moreover, the CSAT-FTCN can obtain the dependency relationships of target utterances on internal own key information and external contextual information to understand emotions in a more profound sense.
no code implementations • CVPR 2023 • Yajing Liu, Yuning Lu, Hao liu, Yaozu An, Zhuoran Xu, Zhuokun Yao, Baofeng Zhang, Zhiwei Xiong, Chenguang Gui
Considering this, we present Hierarchical Prompt (HiPro) learning, a simple and effective method for jointly adapting a pre-trained VLM to multiple downstream tasks.
no code implementations • 1 Dec 2022 • Jiahui Cheng, Minshuo Chen, Hao liu, Tuo Zhao, Wenjing Liao
Label Shift has been widely believed to be harmful to the generalization performance of machine learning models.
1 code implementation • 23 Nov 2022 • Fangchen Liu, Hao liu, Aditya Grover, Pieter Abbeel
We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models.
no code implementations • 15 Nov 2022 • Hao liu, Zhuoran Xu, Dan Wang, Baofeng Zhang, Guan Wang, Bo Dong, Xin Wen, Xinyu Xu
3D object detection is a critical task in autonomous driving.
1 code implementation • 24 Oct 2022 • Hao liu, Lisa Lee, Kimin Lee, Pieter Abbeel
Our \ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a transformer-based policy that predicts actions based on encoded representations.
no code implementations • 24 Oct 2022 • Hao liu, Xinyang Geng, Lisa Lee, Igor Mordatch, Sergey Levine, Sharan Narang, Pieter Abbeel
Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing impressive zero-shot and few-shot capabilities across a wide range of tasks.
no code implementations • 19 Oct 2022 • Hao liu, Tom Zahavy, Volodymyr Mnih, Satinder Singh
In this work, we aim to bring the best of both worlds and propose an algorithm that exhibits an exploratory behavior whilst it utilizes large diverse datasets.
2 code implementations • 5 Oct 2022 • Fan Liu, Hao liu, Wenzhao Jiang
Remarkably, we also show that adversarial training with our proposed attacks can significantly improve the robustness of spatiotemporal traffic forecasting models.
no code implementations • 22 Aug 2022 • Chang Nie, Yiqing Hu, Yanqiu Qu, Hao liu, Deqiang Jiang, Bo Ren
To realize this goal, we design the learning paradigm from three perspectives: 1) generating attribute views, 2) extracting subtle but crucial details, and 3) exploiting valued view pairs for learning, to fully unlock the pre-training potential.
no code implementations • 23 Jul 2022 • Song Li, Song Ke, Chenxing Yang, Jun Chen, Yi Xiong, Lirong Zheng, Hao liu, Liang Hong
Gonadotrophin-releasing hormone receptor (GnRH1R) is a promising therapeutic target for the treatment of uterine diseases.
1 code implementation • 19 Jul 2022 • Xulong Shi, Zhi Qi, Jiaxuan Cai, Keqi Fu, Yaru Zhao, Zan Li, Xuanyu Liu, Hao liu
Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit.
no code implementations • 12 Jul 2022 • Hao liu, Bin Chen, Bo wang, Chunpeng Wu, Feng Dai, Peng Wu
To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2.
no code implementations • NAACL 2022 • Haoyu Cao, Jiefeng Ma, Antai Guo, Yiqing Hu, Hao liu, Deqiang Jiang, Yinsong Liu, Bo Ren
Document Information Extraction (DIE) has attracted increasing attention due to its various advanced applications in the real world.
no code implementations • 28 Jun 2022 • Younggyo Seo, Danijar Hafner, Hao liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel
Yet the current approaches typically train a single model end-to-end for learning both visual representations and dynamics, making it difficult to accurately model the interaction between robots and small objects.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
no code implementations • 25 Jun 2022 • Sugirtha T, Sridevi M, Khailash Santhakumar, Hao liu, B Ravi Kiran, Thomas Gauthier, Senthil Yogamani
We evaluate the pretext task using the RTM3D detection model as baseline, with and without the application of data augmentation.
no code implementations • 9 Jun 2022 • Hao liu, Minshuo Chen, Siawpeng Er, Wenjing Liao, Tong Zhang, Tuo Zhao
Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness.
no code implementations • 31 May 2022 • Can Chen, Chen Ma, Xi Chen, Sirui Song, Hao liu, Xue Liu
Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure.
1 code implementation • 27 May 2022 • Xinyang Geng, Hao liu, Lisa Lee, Dale Schuurmans, Sergey Levine, Pieter Abbeel
We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks.
no code implementations • 23 May 2022 • Lijie Wang, Yaozong Shen, Shuyuan Peng, Shuai Zhang, Xinyan Xiao, Hao liu, Hongxuan Tang, Ying Chen, Hua Wu, Haifeng Wang
Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability.
no code implementations • 12 May 2022 • Wei Fan, Kunpeng Liu, Hao liu, HengShu Zhu, Hui Xiong, Yanjie Fu
Feature selection and instance selection are two important techniques of data processing.
1 code implementation • 7 May 2022 • Ao Wang, Wenxing Xu, Hanshi Sun, Ninghao Pu, Zijin Liu, Hao liu
In this paper, a binarized convolutional neural network suitable for ECG monitoring is proposed, which is hardware-friendly and more suitable for use in resource-constrained wearable devices.
no code implementations • 20 Apr 2022 • Kelly Payette, Hongwei Li, Priscille de Dumast, Roxane Licandro, Hui Ji, Md Mahfuzur Rahman Siddiquee, Daguang Xu, Andriy Myronenko, Hao liu, Yuchen Pei, Lisheng Wang, Ying Peng, Juanying Xie, Huiquan Zhang, Guiming Dong, Hao Fu, Guotai Wang, ZunHyan Rieu, Donghyeon Kim, Hyun Gi Kim, Davood Karimi, Ali Gholipour, Helena R. Torres, Bruno Oliveira, João L. Vilaça, Yang Lin, Netanell Avisdris, Ori Ben-Zvi, Dafna Ben Bashat, Lucas Fidon, Michael Aertsen, Tom Vercauteren, Daniel Sobotka, Georg Langs, Mireia Alenyà, Maria Inmaculada Villanueva, Oscar Camara, Bella Specktor Fadida, Leo Joskowicz, Liao Weibin, Lv Yi, Li Xuesong, Moona Mazher, Abdul Qayyum, Domenec Puig, Hamza Kebiri, Zelin Zhang, Xinyi Xu, Dan Wu, Kuanlun Liao, Yixuan Wu, Jintai Chen, Yunzhi Xu, Li Zhao, Lana Vasung, Bjoern Menze, Meritxell Bach Cuadra, Andras Jakab
Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context.
no code implementations • 18 Apr 2022 • Hao liu, Xinghua Jiang, Xin Li, Antai Guo, Deqiang Jiang, Bo Ren
The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent ability of learning visual representation from unlabeled data.
1 code implementation • CVPR 2022 • Hao Wang, Junchao Liao, Tianheng Cheng, Zewen Gao, Hao liu, Bo Ren, Xiang Bai, Wenyu Liu
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification.
no code implementations • 27 Mar 2022 • Yasser Abduallah, Vania K. Jordanova, Hao liu, Qin Li, Jason T. L. Wang, Haimin Wang
Solar energetic particles (SEPs) are an essential source of space radiation, which are hazards for humans in space, spacecraft, and technology in general.
no code implementations • 23 Mar 2022 • Hao liu, Ye Guo, Haitian Liu, Hongbin Sun
We consider the problem of how multiple areas should jointly cover congestion rents of internal and tie-lines in an interconnected power system.
no code implementations • 18 Mar 2022 • Hao liu, Xue-Cheng Tai, Ron Kimmel, Roland Glowinski
Recently, the authors proposed a color elastica model, which minimizes both the surface area and elastica of the image manifold.
1 code implementation • Findings (ACL) 2022 • Wei Li, Can Gao, guocheng niu, Xinyan Xiao, Hao liu, Jiachen Liu, Hua Wu, Haifeng Wang
In particular, we propose to conduct grounded learning on both images and texts via a sharing grounded space, which helps bridge unaligned images and texts, and align the visual and textual semantic spaces on different types of corpora.
no code implementations • 2 Mar 2022 • Hao liu, Hui Yuan, Junhui Hou, Raouf Hamzaoui, Wei Gao
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
1 code implementation • 27 Feb 2022 • Hanshi Sun, Ao Wang, Ninghao Pu, Zhiqing Li, Junguang Huang, Hao liu, Zhi Qi
In order to adapt to our compression method, we need a smaller and simpler network.
no code implementations • 3 Feb 2022 • Tao Liu, Shu Guo, Hao liu, Rui Kang, Mingyang Bai, Jiyang Jiang, Wei Wen, Xing Pan, Jun Tai, JianXin Li, Jian Cheng, Jing Jing, Zhenzhou Wu, Haijun Niu, Haogang Zhu, Zixiao Li, Yongjun Wang, Henry Brodaty, Perminder Sachdev, Daqing Li
Degeneration and adaptation are two competing sides of the same coin called resilience in the progressive processes of brain aging or diseases.
1 code implementation • 1 Feb 2022 • Michael Laskin, Hao liu, Xue Bin Peng, Denis Yarats, Aravind Rajeswaran, Pieter Abbeel
We introduce Contrastive Intrinsic Control (CIC), an algorithm for unsupervised skill discovery that maximizes the mutual information between state-transitions and latent skill vectors.
1 code implementation • 31 Jan 2022 • Denis Yarats, David Brandfonbrener, Hao liu, Michael Laskin, Pieter Abbeel, Alessandro Lazaric, Lerrel Pinto
In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL.
no code implementations • ICLR 2022 • Hao liu, Huaping Liu
Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks.
no code implementations • CVPR 2022 • Ruyang Liu, Hao liu, Ge Li, Haodi Hou, TingHao Yu, Tao Yang
As a common problem in the visual world, contextual bias means the recognition may depend on the co-occurrence context rather than the objects themselves, which is even more severe in multi-label tasks due to multiple targets and the absence of location.
Ranked #9 on
Multi-Label Classification
on MS-COCO
no code implementations • 1 Jan 2022 • Hao liu, Haizhao Yang, Minshuo Chen, Tuo Zhao, Wenjing Liao
Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and simulations, etc.
1 code implementation • 23 Dec 2021 • Denghui Zhang, Zixuan Yuan, Hao liu, Xiaodong Lin, Hui Xiong
Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths.
no code implementations • 1 Dec 2021 • Denghui Zhang, Zixuan Yuan, Yanchi Liu, Hao liu, Fuzhen Zhuang, Hui Xiong, Haifeng Chen
Also, the word co-occurrences guided semantic learning of pre-training models can be largely augmented by entity-level association knowledge.
1 code implementation • NeurIPS 2021 • Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue (Steve) Liu, Hao liu, Dejing Dou
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
no code implementations • CVPR 2022 • Hao liu, Xin Li, Bing Liu, Deqiang Jiang, Yinsong Liu, Bo Ren
We also show that the proposed NCGM can modulate collaborative pattern of different modalities conditioned on the context of intra-modality cues, which is vital for diversified table cases.
Ranked #5 on
Table Recognition
on PubTabNet
1 code implementation • 25 Nov 2021 • Qian Yin, Qingyong Hu, Hao liu, Feng Zhang, Yingqian Wang, Zaiping Lin, Wei An, Yulan Guo
Satellite video cameras can provide continuous observation for a large-scale area, which is important for many remote sensing applications.
1 code implementation • CVPR 2022 • Hao liu, Xinghua Jiang, Xin Li, Zhimin Bao, Deqiang Jiang, Bo Ren
For the sake of trade-off between efficiency and performance, a group of works merely perform SA operation within local patches, whereas the global contextual information is abandoned, which would be indispensable for visual recognition tasks.
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 • 29 Oct 2021 • Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue Liu, Hao liu, Dejing Dou
To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.
1 code implementation • 28 Oct 2021 • Michael Laskin, Denis Yarats, Hao liu, Kimin Lee, Albert Zhan, Kevin Lu, Catherine Cang, Lerrel Pinto, Pieter Abbeel
Deep Reinforcement Learning (RL) has emerged as a powerful paradigm to solve a range of complex yet specific control tasks.
no code implementations • 27 Oct 2021 • Xiaowei Yuan, Jingyuan Hu, Xiaodan Zhang, Honglei Lv, Hao liu
In this paper, we propose an emoji-based co-attention network that learns the mutual emotional semantics between text and emojis on microblogs.
no code implementations • 19 Oct 2021 • Yimin Wei, Hao liu, TingTing Xie, Qiuhong Ke, Yulan Guo
We test the effectiveness our PST2 with two different tasks on point cloud sequences, i. e., 4D semantic segmentation and 3D action recognition.
no code implementations • 29 Sep 2021 • Zhuoran Xu, Hao liu, Bo Dong
In this paper we propose a novel idea, "There are free lunches" (TAFL) Theorem, which states that some algorithms can achieve the best performance in all possible tasks, in the condition that tasks are given in a specific order.
no code implementations • 29 Sep 2021 • Eric Zhao, De-An Huang, Hao liu, Zhiding Yu, Anqi Liu, Olga Russakovsky, Anima Anandkumar
In real-world applications, however, there are multiple protected attributes yielding a large number of intersectional protected groups.
no code implementations • 17 Sep 2021 • Hongxuan Tang, Hao liu, Xinyan Xiao, Hua Wu
Based on this, we propose a multimodal sentiment analysis dataset, named baiDu Video Sentiment dataset (DuVideoSenti), and introduce a new sentiment system which is designed to describe the sentimental style of a video on recommendation scenery.
no code implementations • 7 Sep 2021 • Hao liu, Minshuo Chen, Tuo Zhao, Wenjing Liao
Most of existing statistical theories on deep neural networks have sample complexities cursed by the data dimension and therefore cannot well explain the empirical success of deep learning on high-dimensional data.
no code implementations • 31 Aug 2021 • Hao liu, Pieter Abbeel
We introduce a new unsupervised pretraining objective for reinforcement learning.
no code implementations • 30 Aug 2021 • Lijie Wang, Hao liu, Shuyuan Peng, Hongxuan Tang, Xinyan Xiao, Ying Chen, Hua Wu, Haifeng Wang
Therefore, in order to systematically evaluate the factors for building trustworthy systems, we propose a novel and well-annotated sentiment analysis dataset to evaluate robustness and interpretability.
no code implementations • 9 Aug 2021 • Zhuoran Xu, Hao liu
Artificial Intelligence has been developed for decades with the achievement of great progress.
no code implementations • 4 Aug 2021 • Hao liu, Xue-Cheng Tai, Roland Glowinski
In our method, we decouple the full nonlinearity of Gaussian curvature from differential operators by introducing two matrix- and vector-valued functions.
no code implementations • 12 Jul 2021 • Weijia Zhang, Hao liu, Lijun Zha, HengShu Zhu, Ji Liu, Dejing Dou, Hui Xiong
Real estate appraisal refers to the process of developing an unbiased opinion for real property's market value, which plays a vital role in decision-making for various players in the marketplace (e. g., real estate agents, appraisers, lenders, and buyers).
no code implementations • 8 Jun 2021 • Ziyu Guan, Hongchang Wu, Qingyu Cao, Hao liu, Wei Zhao, Sheng Li, Cai Xu, Guang Qiu, Jian Xu, Bo Zheng
Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose.
1 code implementation • 3 Jun 2021 • Hao liu, Qian Gao, Jiang Li, Xiaochao Liao, Hao Xiong, Guangxing Chen, Wenlin Wang, Guobao Yang, Zhiwei Zha, daxiang dong, Dejing Dou, Haoyi Xiong
In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
no code implementations • 30 Apr 2021 • Junru Chen, Shiqing Geng, Yongluan Yan, Danyang Huang, Hao liu, Yadong Li
Vehicle Re-identification aims to identify a specific vehicle across time and camera view.
no code implementations • 30 Mar 2021 • Bo Dong, Hao liu, Yu Bai, Jinbiao Lin, Zhuoran Xu, Xinyu Xu, Qi Kong
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety.
1 code implementation • NeurIPS 2021 • Hao liu, Pieter Abbeel
We introduce a new unsupervised pre-training method for reinforcement learning called APT, which stands for Active Pre-Training.
1 code implementation • CVPR 2021 • Zongyong Deng, Hao liu, Yaoxing Wang, Chenyang Wang, Zekuan Yu, Xuehong Sun
In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification.
1 code implementation • 15 Feb 2021 • Weijia Zhang, Hao liu, Fan Wang, Tong Xu, Haoran Xin, Dejing Dou, Hui Xiong
Electric Vehicle (EV) has become a preferable choice in the modern transportation system due to its environmental and energy sustainability.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
1 code implementation • 29 Jan 2021 • Haoran Xin, Xinjiang Lu, Tong Xu, Hao liu, Jingjing Gu, Dejing Dou, Hui Xiong
Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM).
no code implementations • 28 Jan 2021 • Carter Blum, Hao liu, Hui Xiong
Electric vehicles have been rapidly increasing in usage, but stations to charge them have not always kept up with demand, so efficient routing of vehicles to stations is critical to operating at maximum efficiency.
no code implementations • 17 Jan 2021 • Anqi Liu, Hao liu, Tongxin Li, Saeed Karimi-Bidhendi, Yisong Yue, Anima Anandkumar
Thus, we provide a principled approach to tackling the joint problem of causal discovery and latent variable inference.
no code implementations • 16 Jan 2021 • Ruocheng Guo, Pengchuan Zhang, Hao liu, Emre Kiciman
Nevertheless, we find that the performance of IRM can be dramatically degraded under \emph{strong $\Lambda$ spuriousness} -- when the spurious correlation between the spurious features and the class label is strong due to the strong causal influence of their common cause, the domain label, on both of them (see Fig.
no code implementations • 8 Jan 2021 • Hui Luo, Jingbo Zhou, Zhifeng Bao, Shuangli Li, J. Shane Culpepper, Haochao Ying, Hao liu, Hui Xiong
We design a novel multi-task learning model called MPR (short for Multi-level POI Recommendation), where each task aims to return the top-k POIs at a certain spatial granularity level.
no code implementations • 1 Jan 2021 • Hao liu, Pieter Abbeel
On DMControl suite, APT beats all baselines in terms of asymptotic performance and data efficiency and dramatically improves performance on tasks that are extremely difficult for training from scratch.
3 code implementations • ACL 2021 • Wei Li, Can Gao, guocheng niu, Xinyan Xiao, Hao liu, Jiachen Liu, Hua Wu, Haifeng Wang
Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other.
Ranked #3 on
Image Captioning
on COCO
no code implementations • 31 Dec 2020 • Jaan Kasak, James Creswell, Hao liu, Pavel Naselsky
We show that the total number density of non-polarized points of the E- and B-families is closely related to the presence of lensing and the tensor-to-scalar ratio $r$.
Cosmology and Nongalactic Astrophysics
no code implementations • 30 Dec 2020 • Jindong Han, Hao liu, HengShu Zhu, Hui Xiong, Dejing Dou
Specifically, we first propose a heterogeneous recurrent graph neural network to model the spatiotemporal autocorrelation among air quality and weather monitoring stations.
no code implementations • 24 Dec 2020 • Shu-Yu Liu, Shuang-Xing Zhu, Qi-Yi Wu, Chen Zhang, Peng-Bo Song, You-Guo Shi, Hao liu, Zi-Teng Liu, Jiao-Jiao Song, Fan-Ying Wu, Yin-Zou Zhao, Xiao-Fang Tang, Ya-Hua Yuan, Han Huang, Jun He, H. Y. Liu, Yu-Xia Duan, Jian-Qiao Meng
Two distinct carrier and coherent phonons relaxation processes were identified in the 5 K - 300 K range.
Materials Science Superconductivity
no code implementations • 13 Nov 2020 • Yu Yun, Xin Li, Arashdeep Singh Thind, Yuewei Yin, Hao liu, Qiang Li, Wenbin Wang, Alpha T. N Diaye, Corbyn Mellinger, Xuanyuan Jiang, Rohan Mishra, Xiaoshan Xu
The coupling between ferroelectric and magnetic orders in multiferroic materials and the nature of magnetoelectric (ME) effects are enduring experimental challenges.
Materials Science Other Condensed Matter
no code implementations • 3 Nov 2020 • Minshuo Chen, Hao liu, Wenjing Liao, Tuo Zhao
Our theory shows that deep neural networks are adaptive to the low-dimensional geometric structures of the covariates, and partially explains the success of deep learning for causal inference.
no code implementations • 2 Oct 2020 • Wei Fan, Kunpeng Liu, Hao liu, Yong Ge, Hui Xiong, Yanjie Fu
In this journal version, we propose a novel interactive and closed-loop architecture to simultaneously model interactive reinforcement learning (IRL) and decision tree feedback (DTF).
no code implementations • 2 Sep 2020 • Lufan Chang, Wenjing Zhuang, Richeng Wu, Sai Feng, Hao liu, Jing Yu, Jia Ding, Ziteng Wang, Jia-Qi Zhang
Our platform is consists of a radiomics module and a deep learning module.
no code implementations • 27 Aug 2020 • Wei Fan, Kunpeng Liu, Hao liu, Pengyang Wang, Yong Ge, Yanjie Fu
Motivated by such a computational dilemma, this study is to develop a novel feature space navigation method.
4 code implementations • 27 Aug 2020 • Haodi Jiang, Jiasheng Wang, Chang Liu, Ju Jing, Hao liu, Jason T. L. Wang, Haimin Wang
Deep learning has drawn a lot of interest in recent years due to its effectiveness in processing big and complex observational data gathered from diverse instruments.
no code implementations • 19 Aug 2020 • Hao Liu, Xue-Cheng Tai, Ron Kimmel, Roland Glowinski
Here, we introduce an addition to the Polyakov action for color images that minimizes the color manifold curvature.
no code implementations • IEEE 2020 • Hao liu, Y ulan Guo, Y anni Ma, Yinjie Lei, and Gongjian Wen
In this paper, we propose a simple yet effective Point Context Encoding (PointCE) module to capture semantic contexts of a point cloud and adaptively highlight intermediate feature maps.
1 code implementation • 17 Jul 2020 • Hao Liu, Pieter Abbeel
In this paper we show that through the perspective of hybrid discriminative-generative training of energy-based models we can make a direct connection between contrastive learning and supervised learning.
no code implementations • 11 Jul 2020 • Hao Liu, Ying Li, Yanjie Fu, Huaibo Mei, Jingbo Zhou, Xu Ma, Hui Xiong
Then, we introduce a general route search algorithm coupled with an efficient station binding method for efficient route candidate generation.
no code implementations • IEEE 2020 • Y anni Ma, Y ulan Guo, Hao liu, Yinjie Lei
In this paper, we propose a Point Global Context Reasoning (PointGCR) module to capture global contextual information along the channel dimension.
6 code implementations • ACL 2020 • Hao Tian, Can Gao, Xinyan Xiao, Hao liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu
In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.
no code implementations • 8 May 2020 • Hao Liu, Yan Xu, Jiasheng Wang, Ju Jing, Chang Liu, Jason T. L. Wang, Haimin Wang
By learning the latent patterns in the training data prepared by the physics-based ME tool, the proposed CNN method is able to infer vector magnetic fields from the Stokes profiles of GST/NIRIS.
Solar and Stellar Astrophysics
no code implementations • 26 Feb 2020 • Hao Liu, Antai Guo, Deqiang Jiang, Yiqing Hu, Bo Ren
Recently, a series of decomposition-based scene text detection methods has achieved impressive progress by decomposing challenging text regions into pieces and linking them in a bottom-up manner.
3 code implementations • 22 Feb 2020 • Hao Liu, Chang Liu, Jason T. L. Wang, Haimin Wang
We present two recurrent neural networks (RNNs), one based on gated recurrent units and the other based on long short-term memory, for predicting whether an active region (AR) that produces an M- or X-class flare will also produce a coronal mass ejection (CME).
no code implementations • 22 Jan 2020 • Hao Liu, Wenjing Liao
The estimation error of this variance quantity is also given in this paper.
no code implementations • 22 Jan 2020 • Yuchen He, Sung Ha Kang, Hao Liu
We propose a variational functional and fast algorithms to reconstruct implicit surface from point cloud data with a curvature constraint.
no code implementations • TRANSACTION 2020 • Yazhou Hu, Wenxue Wang, Hao liu, and Lianqing Liu, Member, IEEE
In this algorithm, a reward function is defined according to the features of tracking control in order to speed up the learning process, and then an RL tracking controller with a kernel-based transition dynamic model is proposed.
3 code implementations • 27 Dec 2019 • Yulan Guo, Hanyun Wang, Qingyong Hu, Hao liu, Li Liu, Mohammed Bennamoun
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
no code implementations • 20 Dec 2019 • Hao Liu, Hui Yuan, Qi Liu, Junhui Hou, Ju Liu
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
no code implementations • 16 Dec 2019 • Congcong Zhu, Hao liu, Zhenhua Yu, Xuehong Sun
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos.
1 code implementation • 24 Nov 2019 • Weijia Zhang, Hao liu, Yanchi Liu, Jingbo Zhou, Hui Xiong
However, it is a non-trivial task for predicting citywide parking availability because of three major challenges: 1) the non-Euclidean spatial autocorrelation among parking lots, 2) the dynamic temporal autocorrelation inside of and between parking lots, and 3) the scarcity of information about real-time parking availability obtained from real-time sensors (e. g., camera, ultrasonic sensor, and GPS).
no code implementations • 13 Nov 2019 • Anqi Liu, Hao liu, Anima Anandkumar, Yisong Yue
Ours is a general approach that can be used to augment any existing OPE method that utilizes the direct method.
no code implementations • 25 Sep 2019 • Hao liu, Richard Socher, Caiming Xiong
In this work, we propose a guided adaptive credit assignment method to do effectively credit assignment for policy gradient methods.
1 code implementation • 24 Jun 2019 • Feng Dai, Hao liu, Yike Ma, Juan Cao, Qiang Zhao, Yongdong Zhang
The key component of our network is the dense dilated convolution block, in which each dilation layer is densely connected with the others to preserve information from continuously varied scales.
no code implementations • CVPR 2019 • Hao Liu, Xiangyu Zhu, Zhen Lei, Stan Z. Li
Training large-scale unbalanced data is the central topic in face recognition.
2 code implementations • 17 May 2019 • Hao Liu, Chang Liu, Jason T. L. Wang, Haimin Wang
The essence of our approach is to model data samples in an AR as time series and use LSTMs to capture temporal information of the data samples.
no code implementations • ICLR 2019 • Xuanyang Zhang, Hao liu, Zhanxing Zhu, Zenglin Xu
Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources.
no code implementations • ICLR 2019 • Hao Liu, Alexander Trott, Richard Socher, Caiming Xiong
We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents.
no code implementations • 20 Nov 2018 • Hao Liu, Jingjing Wu, Jianguo Jiang, Meibin Qi, Bo Ren
Attribute recognition has become crucial because of its wide applications in many computer vision tasks, such as person re-identification.
1 code implementation • NeurIPS 2018 • Dilin Wang, Hao liu, Qiang Liu
Variational inference with {\alpha}-divergences has been widely used in modern probabilistic machine learning.
no code implementations • 27 Sep 2018 • Yihao Feng, Hao liu, Jian Peng, Qiang Liu
Deep reinforcement learning has achieved remarkable successes in solving various challenging artificial intelligence tasks.
no code implementations • COLING 2018 • Yanchao Hao, Hao liu, Shizhu He, Kang Liu, Jun Zhao
Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks.
no code implementations • 8 Jun 2018 • Xiangyu Zhu, Hao liu, Zhen Lei, Hailin Shi, Fan Yang, Dong Yi, Guo-Jun Qi, Stan Z. Li
In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition.
no code implementations • 25 Dec 2017 • Bai Li, Changyou Chen, Hao liu, Lawrence Carin
Significant success has been realized recently on applying machine learning to real-world applications.
no code implementations • WS 2017 • Jianbo Zhao, Hao liu, Zuyi Bao, Xiaopeng Bai, Si Li, Zhiqing Lin
Detection and correction of Chinese grammatical errors have been two of major challenges for Chinese automatic grammatical error diagnosis. This paper presents an N-gram model for automatic detection and correction of Chinese grammatical errors in NLPTEA 2017 task.
2 code implementations • 30 Oct 2017 • Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
5 code implementations • 13 Oct 2017 • Oscar Li, Hao liu, Chaofan Chen, Cynthia Rudin
This architecture contains an autoencoder and a special prototype layer, where each unit of that layer stores a weight vector that resembles an encoded training input.
1 code implementation • NeurIPS 2017 • Zhe Gan, Liqun Chen, Wei-Yao Wang, Yunchen Pu, Yizhe Zhang, Hao liu, Chunyuan Li, Lawrence Carin
The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs.
Image-to-Image Translation
Semi-Supervised Image Classification
+1
5 code implementations • NeurIPS 2017 • Chunyuan Li, Hao liu, Changyou Chen, Yunchen Pu, Liqun Chen, Ricardo Henao, Lawrence Carin
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching.
no code implementations • ICCV 2017 • Hao Liu, Jiashi Feng, Zequn Jie, Karlekar Jayashree, Bo Zhao, Meibin Qi, Jianguo Jiang, Shuicheng Yan
We investigate the problem of person search in the wild in this work.
Ranked #4 on
Person Re-Identification
on CUHK-SYSU
1 code implementation • 13 Jun 2017 • Hao liu, Zequn Jie, Karlekar Jayashree, Meibin Qi, Jianguo Jiang, Shuicheng Yan, Jiashi Feng
Video based person re-identification plays a central role in realistic security and video surveillance.
no code implementations • 24 May 2017 • Hao Liu, Haoli Bai, Lirong He, Zenglin Xu
Inheriting these advantages of stochastic neural sequential models, we propose a structured and stochastic sequential neural network, which models both the long-term dependencies via recurrent neural networks and the uncertainty in the segmentation and labels via discrete random variables.
no code implementations • 17 Apr 2017 • Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao liu, Zequn Jie, Jiashi Feng
This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input.
no code implementations • 21 Jan 2017 • Manjesh K. Hanawal, Hao liu, Henghui Zhu, Ioannis Ch. Paschalidis
We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs.
no code implementations • 1 Jan 2017 • Hao Liu, Zequn Jie, Karlekar Jayashree, Meibin Qi, Jianguo Jiang, Shuicheng Yan, Jiashi Feng
Video based person re-identification plays a central role in realistic security and video surveillance.
no code implementations • 15 Dec 2016 • Hao Liu, Yang Yang, Fumin Shen, Lixin Duan, Heng Tao Shen
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a. k. a., image description, has been remarkably advanced in recent years.