1 code implementation • 25 Mar 2024 • Lingdong Kong, Xiang Xu, Jun Cen, Wenwei Zhang, Liang Pan, Kai Chen, Ziwei Liu
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models.
no code implementations • 15 Feb 2024 • Runlong Yu, Robert Ladwig, Xiang Xu, Peijun Zhu, Paul C. Hanson, Yiqun Xie, Xiaowei Jia
Using these simulated labels, we implement a multi-population cognitive evolutionary search, where models, mirroring natural organisms, adaptively evolve to select relevant feature interactions within populations for different lake types and tasks.
no code implementations • 28 Jan 2024 • Xiang Xu, Joseph G. Lambourne, Pradeep Kumar Jayaraman, Zhengqing Wang, Karl D. D. Willis, Yasutaka Furukawa
Starting from the root and progressing to the leaf, BrepGen employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information.
2 code implementations • 7 Dec 2023 • Xiang Xu, Lingdong Kong, Hui Shuai, Qingshan Liu
Firstly, a frustum feature encoder module is used to extract per-point features within the frustum region, which preserves scene consistency and is crucial for point-level predictions.
Ranked #2 on 3D Semantic Segmentation on nuScenes
1 code implementation • 6 Nov 2023 • Mingjia Yin, Hao Wang, Xiang Xu, Likang Wu, Sirui Zhao, Wei Guo, Yong liu, Ruiming Tang, Defu Lian, Enhong Chen
To this end, we propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR), that incorporates adaptive and personalized global collaborative information into sequential recommendation systems.
2 code implementations • KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2023 • Runlong Yu, Xiang Xu, Yuyang Ye, Qi Liu, Enhong Chen
Inspired by natural evolution, we propose a general Cognitive EvoLutionary Search (CELS) framework, where cognitive ability refers to the malleability of organisms to orientate to the environment.
Ranked #3 on Click-Through Rate Prediction on Avazu
1 code implementation • 30 Jun 2023 • Xiang Xu, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Karl D. D. Willis, Yasutaka Furukawa
This paper presents a novel generative model for Computer Aided Design (CAD) that 1) represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes, from global part arrangement down to local curve geometry; and 2) controls the generation or completion of CAD models by specifying the target design using a code tree.
no code implementations • 16 Jun 2023 • Jingsong Yang, Guanzhou Han, Deqing Yang, Jingping Liu, Yanghua Xiao, Xiang Xu, Baohua Wu, Shenghua Ni
In this paper, we propose a novel Multi-Modal Model for POI Tagging, namely M3PT, which achieves enhanced POI tagging through fusing the target POI's textual and visual features, and the precise matching between the multi-modal representations.
no code implementations • 13 Nov 2022 • Shana Li, Xiang Xu, Canjun Li, Ziyan Xu, Qiong Ye, Yan Zhang, Chunlei Cang, Jie Wen
Developing in vivo neuronal labeling and imaging techniques is crucial for studying the structure and function of neural circuits.
no code implementations • 11 Jul 2022 • Xiang Xu, Karl D. D. Willis, Joseph G. Lambourne, Chin-Yi Cheng, Pradeep Kumar Jayaraman, Yasutaka Furukawa
We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations.
2 code implementations • 19 Aug 2021 • Xiang Xu, Hanbyul Joo, Greg Mori, Manolis Savva
We evaluate this approach on our dataset, demonstrating that human-object relations can significantly reduce the ambiguity of articulated object reconstructions from challenging real-world videos.
1 code implementation • ICCV 2021 • Fuyang Zhang, Xiang Xu, Nelson Nauata, Yasutaka Furukawa
This paper presents an explore-and-classify framework for structured architectural reconstruction from an aerial image.
1 code implementation • ICCV 2021 • Tianchen Zhao, Xiang Xu, Mingze Xu, Hui Ding, Yuanjun Xiong, Wei Xia
We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images.
1 code implementation • 6 Jul 2020 • Xiang Xu, Megha Nawhal, Greg Mori, Manolis Savva
We present a mutual information-based framework for unsupervised image-to-image translation.
no code implementations • 11 Jun 2020 • Xiang Xu, Yuanjun Xiong, Wei Xia
In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system.
Ranked #4 on Face Anti-Spoofing on SiW (Protocol 3)
no code implementations • 11 Jun 2020 • Xiang Xu, Nikolaos Sarafianos, Ioannis A. Kakadiaris
In this paper, we address a key limitation of existing 2D face recognition methods: robustness to occlusions.
no code implementations • ICCV 2019 • Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem.
1 code implementation • CVPR 2019 • Xiang Xu, Xiong Zhou, Ragav Venkatesan, Gurumurthy Swaminathan, Orchid Majumder
On the one hand, deep neural networks are effective in learning large datasets.
Ranked #4 on Domain Adaptation on SVNH-to-MNIST
2 code implementations • 29 May 2019 • Xiang Xu, Xiong Zhou, Ragav Venkatesan, Gurumurthy Swaminathan, Orchid Majumder
Deep neural networks often require copious amount of labeled-data to train their scads of parameters.
no code implementations • 27 Jan 2019 • Xiang Xu, Ioannis A. Kakadiaris
Biometrics-related research has been accelerated significantly by deep learning technology.
no code implementations • 6 Jan 2019 • Yundong Zhang, Xiang Xu, Xiaotao Liu
In recent years, face detection has experienced significant performance improvement with the boost of deep convolutional neural networks.
no code implementations • 6 Aug 2018 • Xiang Xu, Xiaofang Wang, Kris M. Kitani
We propose to use the concept of the Hamming bound to derive the optimal criteria for learning hash codes with a deep network.
2 code implementations • ECCV 2018 • Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris
For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem.
no code implementations • 3 Jul 2018 • Jie Liu, Cheng Sun, Xiang Xu, Baomin Xu, Shuangyuan Yu
In this paper we propose a novel Spatial and Temporal Features Mixture Model (STFMM) based on convolutional neural network (CNN) and recurrent neural network (RNN), in which the human body is split into $N$ parts in horizontal direction so that we can obtain more specific features.
no code implementations • 17 Mar 2018 • Yuhang Wu, Le Anh Vu Ha, Xiang Xu, Ioannis A. Kakadiaris
The method relies on Convolutional Point-set Representation (CPR), a carefully designed matrix representation to summarize different layers of information encoded in the set of detected points in the annotated image.
no code implementations • 6 Feb 2018 • Changzheng Zhang, Xiang Xu, Dandan Tu
Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection.
Ranked #9 on Face Detection on WIDER Face (Hard)
no code implementations • 19 Sep 2017 • Xiang Xu, Pengfei Dou, Ha A. Le, Ioannis A. Kakadiaris
Extensive experiments are conducted on the UHDB31 and IJB-A, demonstrating that UR2D outperforms existing 2D face recognition systems such as VGG-Face, FaceNet, and a commercial off-the-shelf software (COTS) by at least 9% on the UHDB31 dataset and 3% on the IJB-A dataset on average in face identification tasks.