no code implementations • 9 Nov 2024 • Shukun Jia, Yichao Cao, Feng Yang, Xin Lu, Xiaobo Lu
Multi-object tracking is advancing through two dominant paradigms: traditional tracking by detection and newly emerging tracking by query.
no code implementations • 29 May 2024 • Sifan Zhou, Zhihang Yuan, Dawei Yang, Xubin Wen, Xing Hu, Yuguang Shi, Ziyu Zhao, Xiaobo Lu
To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance.
1 code implementation • 29 Jan 2024 • Sifan Zhou, Liang Li, Xinyu Zhang, Bo Zhang, Shipeng Bai, Miao Sun, Ziyu Zhao, Xiaobo Lu, Xiangxiang Chu
To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying $3\times$ inference speedup.
no code implementations • 10 Nov 2023 • Xin Lu, Shikun Chen, Yichao Cao, Xin Zhou, Xiaobo Lu
To handle this limitation, we substitute convolutional descriptors for attention-guided features and propose an Attributes Grouping and Mining Hashing (AGMH), which groups and embeds the category-specific visual attributes in multiple descriptors to generate a comprehensive feature representation for efficient fine-grained image retrieval.
1 code implementation • NeurIPS 2023 • Yichao Cao, Qingfei Tang, Xiu Su, Chen Song, Shan You, Xiaobo Lu, Chang Xu
We conduct a deep analysis of the three hierarchical features inherent in visual HOI detectors and propose a method for high-level relation extraction aimed at VL foundation models, which we call HO prompt-based learning.
no code implementations • ICCV 2023 • Yichao Cao, Qingfei Tang, Feng Yang, Xiu Su, Shan You, Xiaobo Lu, Chang Xu
Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets.
1 code implementation • 5 Feb 2023 • Sifan Zhou, Zhi Tian, Xiangxiang Chu, Xinyu Zhang, Bo Zhang, Xiaobo Lu, Chengjian Feng, Zequn Jie, Patrick Yin Chiang, Lin Ma
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios.
no code implementations • ICCV 2023 • Xuan Wei, Zhidan Ran, Xiaobo Lu
The accuracy of the visual tasks for top-view fisheye cameras is limited by the Euclidean geometry for pose-distorted objects in images.
no code implementations • 2 Aug 2021 • Yang Zhang, Xin Yu, Xiaobo Lu, Ping Liu
Specifically, we design a novel cross-modal transformer module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively.
2 code implementations • 10 Nov 2020 • Yichao Cao, Qingfei Tang, Xiaobo Lu, Fan Li, Jinde Cao
To overcome these problems, a novel Spatio-Temporal Cross Network (STCNet) is proposed to recognize industrial smoke emissions.
no code implementations • 12 Sep 2020 • Yaohua Bu, Weijun Li, Tianyi Ma, Shengqi Chen, Jia Jia, Kun Li, Xiaobo Lu
To provide more discriminative feedback for the second language (L2) learners to better identify their mispronunciation, we propose a method for exaggerated visual-speech feedback in computer-assisted pronunciation training (CAPT).
1 code implementation • 31 Aug 2020 • Tjerk Benschop, Tobias A. de Jong, Petr Stepanov, Xiaobo Lu, Vincent Stalman, Sense Jan van der Molen, Dmitri K. Efetov, Milan P. Allan
We introduce a new method to continuously map inhomogeneities of a moir\'e lattice and apply it to large-area topographic images we measure on open-device twisted bilayer graphene (TBG).
Mesoscale and Nanoscale Physics Strongly Correlated Electrons
no code implementations • 8 Apr 2020 • Yang Zhang, Changhui Hu, Xiaobo Lu
The technology of vehicle and driver detection in Intelligent Transportation System(ITS) is a hot topic in recent years.
no code implementations • 7 Apr 2020 • Yang Zhang, Changhui Hu, Xiaobo Lu
Then, the illumination level is referenced to construct the high performance LEF as well realize adaptive fusion for multiple scales LEFs for the face image, performing JLEF-feature.
no code implementations • 7 Apr 2020 • Yang Zhang, Changhui Hu, Xiaobo Lu
In addition, due to the adversarial learning framework can reliably produce high quality natural images, the specified content loss as well as the adversarial loss are back-propagated to optimize the training of model.
no code implementations • 18 Mar 2020 • Chen Zhang, Xiaobo Lu, Zhiliang Huang
Researches show that fatigue driving is one of the important causes of road traffic accidents, so it is of great significance to study the driver fatigue recognition algorithm to improve road traffic safety.
no code implementations • CVPR 2020 • Yang Zhang, Ivor Tsang, Yawei Luo, Changhui Hu, Xiaobo Lu, Xin Yu
This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination.
no code implementations • 9 Feb 2020 • Yang Zhang, Ivor W. Tsang, Jun Li, Ping Liu, Xiaobo Lu, Xin Yu
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
1 code implementation • 6 Feb 2020 • Simone Lisi, Xiaobo Lu, Tjerk Benschop, Tobias A. de Jong, Petr Stepanov, Jose R. Duran, Florian Margot, Irène Cucchi, Edoardo Cappelli, Andrew Hunter, Anna Tamai, Viktor Kandyba, Alessio Giampietri, Alexei Barinov, Johannes Jobst, Vincent Stalman, Maarten Leeuwenhoek, Kenji Watanabe, Takashi Taniguchi, Louk Rademaker, Sense Jan van der Molen, Milan Allan, Dmitri K. Efetov, Felix Baumberger
Transport experiments in twisted bilayer graphene revealed multiple superconducting domes separated by correlated insulating states.
Strongly Correlated Electrons Materials Science
no code implementations • 18 Dec 2018 • Shengqin Jiang, Xiaobo Lu, Yinjie Lei, Lingqiao Liu
Our rationale is that the mask prediction could be better modeled as a binary segmentation problem and the difficulty of estimating the density could be reduced if the mask is known.
no code implementations • 3 Dec 2018 • Yaocong Hu, MingQi Lu, Xiaobo Lu
Abnormal driving behaviour is one of the leading cause of terrible traffic accidents endangering human life.