no code implementations • 29 Mar 2024 • Shuangjian Li, Tao Zhu, Furong Duan, Liming Chen, Huansheng Ning, Christopher Nugent, Yaping Wan
Wearable sensor-based human activity recognition (HAR) is a critical research domain in activity perception.
no code implementations • 25 Mar 2024 • Xiaoyan Kui, Haonan Yan, Qinsong Li, Liming Chen, Beiji Zou
In this paper, we present a novel architecture named ChebMixer, a newly graph MLP Mixer that uses fast Chebyshev polynomials-based spectral filtering to extract a sequence of tokens.
no code implementations • 14 Mar 2024 • Wenyong Han, Tao Zhu Member, Liming Chen, Huansheng Ning, Yang Luo, Yaping Wan
Based on this strategy, we introduce MCformer, a multivariate time-series forecasting model with mixed channel features.
no code implementations • 13 Mar 2024 • Shuangjian Li, Tao Zhu, Mingxing Nie, Huansheng Ning, Zhenyu Liu, Liming Chen
Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data.
1 code implementation • 7 Dec 2023 • Mingwu Zheng, Haiyu Zhang, Hongyu Yang, Liming Chen, Di Huang
Accurate representations of 3D faces are of paramount importance in various computer vision and graphics applications.
1 code implementation • 3 Dec 2023 • Ruochen Chen, Liming Chen, Shaifali Parashar
Recent neural, physics-based modeling of garment deformations allows faster and visually aesthetic results as opposed to the existing methods.
no code implementations • 24 Aug 2023 • Nyothiri Aung, Tahar Kechadi, Liming Chen, Sahraoui Dhelim
IP-UNet is a UNet-based model that performs multi-class segmentation on Intensity Projection (IP) of 3D volumetric data instead of the memory-consuming 3D volumes.
no code implementations • 23 Mar 2023 • Muhammad Aaqib, Aftab Ali, Liming Chen, Omar Nibouche
In this paper, we carry out a comprehensive literature review on state-of-the-art research on the trust and reputation of IoT devices and systems.
no code implementations • 20 Mar 2023 • Furong Duan, Tao Zhu, Jinqiang Wang, Liming Chen, Huansheng Ning, Yaping Wan
Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years.
1 code implementation • 10 Jan 2023 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Deep neural networks do not discriminate between spurious and causal patterns, and will only learn the most predictive ones while ignoring the others.
no code implementations • 17 Oct 2022 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Indeed, test-time adaptation methods usually have to rely on a limited representation because of the shortcut learning phenomenon: only a subset of the available predictive patterns is learned with standard training.
no code implementations • 15 Oct 2022 • Lingkun Luo, Liming Chen, Shiqiang Hu
In this paper, starting from our previous DGA-DA, we propose a novel DA method, namely Attention Regularized Laplace Graph-based Domain Adaptation (ARG-DA), to remedy the aforementioned issues.
no code implementations • 13 Apr 2022 • Sahraoui Dhelim, Tahar Kechadi, Liming Chen, Nyothiri Aung, Huansheng Ning, Luigi Atzori
The Metaverse is a virtual environment where users are represented by avatars to navigate a virtual world, which has strong links with the physical one.
2 code implementations • CVPR 2022 • Mingwu Zheng, Hongyu Yang, Di Huang, Liming Chen
Precise representations of 3D faces are beneficial to various computer vision and graphics applications.
Ranked #2 on Face Alignment on FaceScape
no code implementations • 23 Mar 2022 • Jinqiang Wang, Tao Zhu, Liming Chen, Huansheng Ning, Yaping Wan
Compared with SimCLR, it redefines the negative pairs in the contrastive loss function by using unsupervised clustering methods to generate soft labels that mask other samples of the same cluster to avoid regarding them as negative samples.
1 code implementation • 20 Feb 2022 • Xiangnan Yin, Liming Chen
This paper presents a novel image inpainting framework for face mask removal.
no code implementations • 22 Jan 2022 • Sahraoui Dhelim, Liming Chen, Huansheng Ning, Chris Nugent
Death by suicide is the seventh leading death cause worldwide.
1 code implementation • 20 Jan 2022 • Xiangnan Yin, Liming Chen
Occlusions often occur in face images in the wild, troubling face-related tasks such as landmark detection, 3D reconstruction, and face recognition.
no code implementations • 15 Dec 2021 • Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Chen
The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module.
no code implementations • 4 Nov 2021 • Hugues Moreau, Andréa Vassilev, Liming Chen
Multimodal problems are omnipresent in the real world: autonomous driving, robotic grasping, scene understanding, etc... We draw from the well-developed analysis of similarity to provide an example of a problem where neural networks are trained from different sensors, and where the features extracted from these sensors still carry similar information.
no code implementations • 16 Sep 2021 • Hugues Moreau, Andréa Vassilev, Liming Chen
Transport mode detection is a classification problem aiming to design an algorithm that can infer the transport mode of a user given multimodal signals (GPS and/or inertial sensors).
no code implementations • 5 Sep 2021 • Jinqiang Wang, Tao Zhu, Jingyuan Gan, Liming Chen, Huansheng Ning, Yaping Wan
The experiment results show that the resampling augmentation method outperforms all state-of-the-art methods under a small amount of labeled data, on SimCLRHAR and MoCoHAR, with mean F1-score as the evaluation metric.
1 code implementation • 25 Jun 2021 • Quentin Gallouédec, Nicolas Cazin, Emmanuel Dellandréa, Liming Chen
This technical report presents panda-gym, a set Reinforcement Learning (RL) environments for the Franka Emika Panda robot integrated with OpenAI Gym.
no code implementations • 15 Jun 2021 • Thomas Duboudin, Emmanuel Dellandréa, Corentin Abgrall, Gilles Hénaff, Liming Chen
Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data.
no code implementations • 14 Jun 2021 • Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Chen
Missing textures in the incomplete UV map are further full-filled by the UV generator.
no code implementations • 14 Jun 2021 • Xiangnan Yin, Di Huang, Hongyu Yang, Zehua Fu, Yunhong Wang, Liming Chen
The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc.
1 code implementation • 31 May 2021 • Hugues Moreau, Andréa Vassilev, Liming Chen
In Transport Mode Detection, a great diversity of methodologies exist according to the choice made on sensors, preprocessing, model used, etc.
no code implementations • 19 Mar 2021 • Dimitri Gominski, Valérie Gouet-Brunet, Liming Chen
Pick a training dataset, pick a backbone network for feature extraction, and voil\`a ; this usually works for a variety of use cases.
no code implementations • 17 Mar 2021 • Wenxi Wang, Huansheng Ning, Feifei Shi, Sahraoui Dhelim, Weishan Zhang, Liming Chen
In particular with the boom of artificial intelligence (AI), social computing is significantly influenced by AI.
no code implementations • 26 Feb 2021 • Dimitri Gominski, Valérie Gouet-Brunet, Liming Chen
Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated dataset-specific methods.
no code implementations • 21 Feb 2021 • Sahraoui Dhelim, Huansheng Ning, Fadi Farha, Liming Chen, Luigi Atzori, Mahmoud Daneshmand
With the recent advances of the Internet of Things, and the increasing accessibility of ubiquitous computing resources and mobile devices, the prevalence of rich media contents, and the ensuing social, economic, and cultural changes, computing technology and applications have evolved quickly over the past decade.
no code implementations • 9 Jan 2021 • Lingkun Luo, Liming Chen, Shiqiang Hu
Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains.
no code implementations • 18 Dec 2020 • Richard T. Marriott, Sami Romdhani, Stéphane Gentric, Liming Chen
Face-morphing attacks have been a cause for concern for a number of years.
no code implementations • 18 Dec 2020 • Richard T. Marriott, Safa Madiouni, Sami Romdhani, Stéphane Gentric, Liming Chen
Generative Adversarial Networks (GANs) are now capable of producing synthetic face images of exceptionally high visual quality.
2 code implementations • CVPR 2021 • Richard T. Marriott, Sami Romdhani, Liming Chen
Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images.
no code implementations • 22 Oct 2020 • Kexin Lv, Fan He, Xiaolin Huang, Jie Yang, Liming Chen
Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy.
no code implementations • 30 Jul 2020 • Maxime Petit, Emmanuel Dellandrea, Liming Chen
In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects.
no code implementations • 24 Feb 2020 • Mathilde Guillemot, Catherine Heusele, Rodolphe Korichi, Sylvianne Schnebert, Liming Chen
The relevance spreads backward from the last to the first layer of the Deep Neural Network.
no code implementations • 3 Feb 2020 • Amaury Depierre, Emmanuel Dellandréa, Liming Chen
Therefore, in this paper, we extend a state-of-the-art neural network with a scorer that evaluates the graspability of a given position, and introduce a novel loss function which correlates regression of grasp parameters with graspability score.
no code implementations • 19 Sep 2019 • Dimitri Gominski, Martyna Poreba, Valérie Gouet-Brunet, Liming Chen
This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for content-based image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view Permission to make digital
1 code implementation • 10 Jul 2019 • Thomas Duboudin, Maxime Petit, Liming Chen
We propose a procedural fruit tree rendering framework, based on Blender and Python scripts allowing to generate quickly labeled dataset (i. e. including ground truth semantic segmentation).
no code implementations • 18 Jun 2019 • Matthieu Grard, Emmanuel Dellandréa, Liming Chen
We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets.
no code implementations • 27 Nov 2018 • Richard T. Marriott, Sami Romdhani, Liming Chen
For example, given only labels of ambient / non-ambient lighting, our method is able to learn multivariate lighting models disentangled from other factors such as the identity and pose.
no code implementations • 24 Oct 2018 • Erinc Merdivan, Anastasios Vafeiadis, Dimitrios Kalatzis, Sten Hanke, Johannes Kropf, Konstantinos Votis, Dimitrios Giakoumis, Dimitrios Tzovaras, Liming Chen, Raouf Hamzaoui, Matthieu Geist
We propose a new approach to natural language understanding in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations ofthe visual patterns of words.
no code implementations • 26 Sep 2018 • Maxime Petit, Amaury Depierre, Xiaofang Wang, Emmanuel Dellandréa, Liming Chen
In simulation, we demonstrate the benefit of the transfer learning based on visual similarity, as opposed to an amnesic learning (i. e. learning from scratch all the time).
1 code implementation • 30 Mar 2018 • Amaury Depierre, Emmanuel Dellandréa, Liming Chen
Jacquard is built on a subset of ShapeNet, a large CAD models dataset, and contains both RGB-D images and annotations of successful grasping positions based on grasp attempts performed in a simulated environment.
no code implementations • 4 Mar 2018 • Asim Jan, Huaxiong Ding, Hongy-ing Meng, Liming Chen, Huibin Li
In particular, each textured 3D face scan is firstly represented as a 2D texture map and a depth map with one-to-one dense correspondence.
no code implementations • 22 Feb 2018 • Ismini Psychoula, Erinc Merdivan, Deepika Singh, Liming Chen, Feng Chen, Sten Hanke, Johannes Kropf, Andreas Holzinger, Matthieu Geist
In the era of Internet of Things (IoT) technologies the potential for privacy invasion is becoming a major concern especially in regards to healthcare data and Ambient Assisted Living (AAL) environments.
no code implementations • 21 Feb 2018 • Lingkun Luo, Liming Chen, Ying Lu, Shiqiang Hu
Domain adaptation (DA) is transfer learning which aims to learn an effective predictor on target data from source data despite data distribution mismatch between source and target.
no code implementations • 17 Jan 2018 • Ying Lu, Liming Chen, Alexandre Saidi, Xianfeng GU
Correctly estimating the discrepancy between two data distributions has always been an important task in Machine Learning.
no code implementations • 9 Jan 2018 • Yu-Xing Tang, Josiah Wang, Xiaofang Wang, Boyang Gao, Emmanuel Dellandrea, Robert Gaizauskas, Liming Chen
This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations.
no code implementations • 4 Jan 2018 • Matthieu Grard, Romain Brégier, Florian Sella, Emmanuel Dellandréa, Liming Chen
We thus propose a step towards a practical interactive application for generating an object-oriented robotic grasp, requiring as inputs only one depth map of the scene and one user click on the next object to extract.
no code implementations • 28 Dec 2017 • Lingkun Luo, Liming Chen, Shiqiang Hu, Ying Lu, Xiaofang Wang
Domain adaptation (DA) aims to generalize a learning model across training and testing data despite the mismatch of their data distributions.
no code implementations • 13 Oct 2017 • Wuming Zhang, Xi Zhao, Jean-Marie Morvan, Liming Chen
2D face analysis techniques, such as face landmarking, face recognition and face verification, are reasonably dependent on illumination conditions which are usually uncontrolled and unpredictable in the real world.
no code implementations • 13 Sep 2017 • Huaxiong Ding, Liming Chen
3D face dense tracking aims to find dense inter-frame correspondences in a sequence of 3D face scans and constitutes a powerful tool for many face analysis tasks, e. g., 3D dynamic facial expression analysis.
no code implementations • 9 Sep 2017 • Ying Lu, Liming Chen, Alexandre Saidi
By adding an Optimal Transport loss (OT loss) between source and target classifier predictions as a constraint on the source classifier, the proposed Joint Transfer Learning Network (JTLN) can effectively learn useful knowledge for target classification from source data.
no code implementations • 8 Sep 2017 • Wuming Zhang, Zhixin Shu, Dimitris Samaras, Liming Chen
Heterogeneous face recognition between color image and depth image is a much desired capacity for real world applications where shape information is looked upon as merely involved in gallery.
no code implementations • 13 Jun 2017 • Md. Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Results show the effectiveness and excellent generalization ability of the proposed approach as it achieves state-of-the-art results on the LFW, YouTube faces and CACD datasets and competitive results on the IJB-A dataset.
no code implementations • 24 May 2017 • Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Liming Chen
Domain adaptation (DA) is transfer learning which aims to leverage labeled data in a related source domain to achieve informed knowledge transfer and help the classification of unlabeled data in a target domain.
no code implementations • 13 Apr 2017 • Lingkun Luo, Xiaofang Wang, Shiqiang Hu, Chao Wang, Yu-Xing Tang, Liming Chen
Most previous research tackle this problem in seeking a shared feature representation between source and target domains while reducing the mismatch of their data distributions.
no code implementations • 24 Mar 2017 • Abul Hasnat, Julien Bohné, Jonathan Milgram, Stéphane Gentric, Liming Chen
Although CNNs are mostly trained by optimizing the softmax loss, the recent trend shows an improvement of accuracy with different strategies, such as task-specific CNN learning with different loss functions, fine-tuning on target dataset, metric learning and concatenating features from multiple CNNs.
Ranked #6 on Age-Invariant Face Recognition on CACDVS
no code implementations • CVPR 2016 • Yu-Xing Tang, Josiah Wang, Boyang Gao, Emmanuel Dellandrea, Robert Gaizauskas, Liming Chen
This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations.
no code implementations • 10 Nov 2015 • Huibin Li, Jian Sun, Dong Wang, Zongben Xu, Liming Chen
In this paper, we present a novel approach to automatic 3D Facial Expression Recognition (FER) based on deep representation of facial 3D geometric and 2D photometric attributes.
3D Facial Expression Recognition Facial Expression Recognition
no code implementations • 15 Dec 2014 • Walid Mahdi, Liming Chen, Mohsen Ardebilian
With ever increasing computing power and data storage capacity, the potential for large digital video libraries is growing rapidly. However, the massive use of video for the moment is limited by its opaque characteristics.
no code implementations • CVPR 2014 • Baptiste Chu, Sami Romdhani, Liming Chen
Specifically, given a probe with expression, a novel view of the face is generated where the pose is rectified and the expression neutralized.