no code implementations • 28 May 2023 • Utku Ayvaz, Chih-Hong Cheng, Hao Shen
While autonomous vehicles (AVs) may perform remarkably well in generic real-life cases, their irrational action in some unforeseen cases leads to critical safety concerns.
no code implementations • 10 May 2023 • Ran Shen, Gang Sun, Hao Shen, Yiling Li, Liangfeng Jin, Han Jiang
Then, we construct data formats of different subtasks based on existing data and improve the accuracy of the overall model by improving the accuracy of each submodel.
no code implementations • 16 Apr 2023 • Jianzhang Zheng, Hao Shen, Jian Yang, Xuan Tang, Mingsong Chen, Hui Yu, Jielong Guo, Xian Wei
Motivated by the important role of ID, in this paper, we propose a novel deep representation learning approach with autoencoder, which incorporates regularization of the global and local ID constraints into the reconstruction of data representations.
no code implementations • CVPR 2023 • Yinzhen Xu, Weikang Wan, Jialiang Zhang, Haoran Liu, Zikang Shan, Hao Shen, Ruicheng Wang, Haoran Geng, Yijia Weng, Jiayi Chen, Tengyu Liu, Li Yi, He Wang
Trained on our synthesized large-scale dexterous grasp dataset, this model enables us to sample diverse and high-quality dexterous grasp poses for the object point cloud. For the second stage, we propose to replace the motion planning used in parallel gripper grasping with a goal-conditioned grasp policy, due to the complexity involved in dexterous grasping execution.
1 code implementation • 22 Nov 2022 • Hao Shen, Zhong-Qiu Zhao, Wandi Zhang
To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features.
no code implementations • 4 Nov 2022 • Zhengyong Huang, Sijuan Zou, Guoshuai Wang, Zixiang Chen, Hao Shen, HaiYan Wang, Na Zhang, Lu Zhang, Fan Yang, Haining Wangg, Dong Liang, Tianye Niu, Xiaohua Zhuc, Zhanli Hua
In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information.
no code implementations • 10 May 2022 • Julian Wörmann, Daniel Bogdoll, Etienne Bührle, Han Chen, Evaristus Fuh Chuo, Kostadin Cvejoski, Ludger van Elst, Philip Gottschall, Stefan Griesche, Christian Hellert, Christian Hesels, Sebastian Houben, Tim Joseph, Niklas Keil, Johann Kelsch, Hendrik Königshof, Erwin Kraft, Leonie Kreuser, Kevin Krone, Tobias Latka, Denny Mattern, Stefan Matthes, Mohsin Munir, Moritz Nekolla, Adrian Paschke, Maximilian Alexander Pintz, Tianming Qiu, Faraz Qureishi, Syed Tahseen Raza Rizvi, Jörg Reichardt, Laura von Rueden, Stefan Rudolph, Alexander Sagel, Tobias Scholl, Gerhard Schunk, Hao Shen, Hendrik Stapelbroek, Vera Stehr, Gurucharan Srinivas, Anh Tuan Tran, Abhishek Vivekanandan, Ya Wang, Florian Wasserrab, Tino Werner, Christian Wirth, Stefan Zwicklbauer
Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios.
1 code implementation • CVPR 2022 • Junyu Luo, Jiahui Fu, Xianghao Kong, Chen Gao, Haibing Ren, Hao Shen, Huaxia Xia, Si Liu
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description.
no code implementations • 11 Mar 2022 • Jianzhang Zheng, Fan Yang, Hao Shen, Xuan Tang, Mingsong Chen, Liang Song, Xian Wei
We propose an algorithmic framework that leverages the advantages of the DNNs for data self-expression and task-specific predictions, to improve image classification.
2 code implementations • 4 Mar 2022 • Hao Shen, Weikang Wan, He Wang
Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes.
1 code implementation • CVPR 2022 • Yunze Liu, Yun Liu, Che Jiang, Kangbo Lyu, Weikang Wan, Hao Shen, Boqiang Liang, Zhoujie Fu, He Wang, Li Yi
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
no code implementations • NeurIPS 2021 • Jinxin Liu, Hao Shen, Donglin Wang, Yachen Kang, Qiangxing Tian
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy.
no code implementations • 13 Jul 2021 • Shiqing Wu, Weihua Li, Hao Shen, Quan Bai
To tackle the aforementioned challenges, in this paper, we propose a novel algorithm for exploring influential users in unknown networks, which can estimate the influential relationships among users based on their historical behaviors and without knowing the topology of the network.
no code implementations • 1 Jul 2021 • Mi Tian, Qiong Nie, Hao Shen, Xiahua Xia
Meanwhile an attention mechanism is introduced for the benefit of localization performance.
no code implementations • 16 Jun 2021 • Martin Gottwald, Sven Gronauer, Hao Shen, Klaus Diepold
First, we conduct a critical point analysis of the error function and provide technical insights on optimisation and design choices for neural networks.
no code implementations • 4 Feb 2021 • Hao Shen, Rongchan Zhu, Xiangchan Zhu
We prove tightness of the invariant measures in the large N limit.
Quantization Probability Mathematical Physics Analysis of PDEs Mathematical Physics
1 code implementation • 1 Feb 2021 • Alexander Sagel, Julian Wörmann, Hao Shen
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data.
no code implementations • 21 Dec 2020 • Alexander Sagel, Amit Sahu, Stefan Matthes, Holger Pfeifer, Tianming Qiu, Harald Rueß, Hao Shen, Julian Wörmann
This white paper provides an introduction and discussion of this emerging field in machine learning research.
3 code implementations • CVPR 2021 • Yuqing Wang, Zhaoliang Xu, Xinlong Wang, Chunhua Shen, Baoshan Cheng, Hao Shen, Huaxia Xia
Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem.
Ranked #23 on Video Instance Segmentation on YouTube-VIS validation
no code implementations • 18 Nov 2020 • Feng Gao, Jincheng Yu, Hao Shen, Yu Wang, Huazhong Yang
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots.
1 code implementation • 22 Oct 2020 • Muhammad Umer Anwaar, Zhiwei Han, Shyam Arumugaswamy, Rayyan Ahmad Khan, Thomas Weber, Tianming Qiu, Hao Shen, Yuanting Liu, Martin Kleinsteuber
In this paper, we employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs, which explicitly capture sequential semantics in graph structures.
Ranked #1 on Link Prediction on Yelp
no code implementations • 13 May 2020 • Mi Tian, Qiong Nie, Hao Shen
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control.
no code implementations • CVPR 2020 • Yuqing Wang, Zhaoliang Xu, Hao Shen, Baoshan Cheng, Lirong Yang
Accordingly, we decompose the instance segmentation into two parallel subtasks: Local Shape prediction that separates instances even in overlapping conditions, and Global Saliency generation that segments the whole image in a pixel-to-pixel manner.
no code implementations • Proceedings of the AAAI Conference on Artificial Intelligence 2020 • Yinglu Liu, Hailin Shi, Hao Shen, Yue Si, Xiaobo Wang, Tao Mei
The dataset is publicly accessible to the community for boosting the advance of face parsing. 1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.
Ranked #8 on Face Parsing on LaPa
no code implementations • 13 May 2019 • Yinglu Liu, Hailin Shi, Yue Si, Hao Shen, Xiaobo Wang, Tao Mei
Each image is provided with accurate annotation of a 11-category pixel-level label map along with coordinates of 106-point landmarks.
no code implementations • 9 May 2019 • Yinglu Liu, Hao Shen, Yue Si, Xiaobo Wang, Xiangyu Zhu, Hailin Shi, Zhibin Hong, Hanqi Guo, Ziyuan Guo, Yanqin Chen, Bi Li, Teng Xi, Jun Yu, Haonian Xie, Guochen Xie, Mengyan Li, Qing Lu, Zengfu Wang, Shenqi Lai, Zhenhua Chai, Xiaoming Wei
However, previous competitions on facial landmark localization (i. e., the 300-W, 300-VW and Menpo challenges) aim to predict 68-point landmarks, which are incompetent to depict the structure of facial components.
no code implementations • 24 Mar 2019 • Xian Wei, Hao Shen, Yuanxiang Li, Xuan Tang, Bo Jin, Lijun Zhao, Yi Lu Murphey
There are some inadequacies in the language description of this paper that require further improvement.
1 code implementation • 18 Feb 2019 • Mingpan Guo, Stefan Matthes, Jiaojiao Ye, Hao Shen
For localization, we show that Generative Map achieves comparable performance with current regression models.
no code implementations • 26 Nov 2018 • Hao Shen
Among many unsolved puzzles in theories of Deep Neural Networks (DNNs), there are three most fundamental challenges that highly demand solutions, namely, expressibility, optimisability, and generalisability.
no code implementations • 8 Oct 2018 • Xian Wei, Hao Shen, Martin Kleinsteuber
We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i. e., sparse representation and the trace quotient criterion.
1 code implementation • 20 Mar 2018 • Alexander Sagel, Hao Shen
This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences.
no code implementations • CVPR 2018 • Hao Shen
Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex.
no code implementations • 22 Oct 2016 • Dominik Meyer, Johannes Feldmaier, Hao Shen
In this work, we investigate the application of Reinforcement Learning to two well known decision dilemmas, namely Newcomb's Problem and Prisoner's Dilemma.
no code implementations • 5 Oct 2016 • Dominik Meyer, Hao Shen, Klaus Diepold
In this paper, we study the Temporal Difference (TD) learning with linear value function approximation.
no code implementations • CVPR 2016 • Xian Wei, Hao Shen, Martin Kleinsteuber
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner.
no code implementations • 16 Jun 2015 • Vahid Abolghasemi, Hao Shen, Yaochun Shen, Lu Gan
In this paper, the problem of terahertz pulsed imaging and reconstruction is addressed.
no code implementations • 12 Jan 2015 • Alexander Sagel, Dominik Meyer, Hao Shen
Our approach employs a recently developed method, the so-called Scattering transform, for the process of feature extraction in texture retrieval.
no code implementations • 19 Dec 2013 • Xian Wei, Hao Shen, Martin Kleinsteuber
Video representation is an important and challenging task in the computer vision community.