no code implementations • ECCV 2020 • Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu
Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches.
no code implementations • 12 Feb 2024 • Yijun Tian, Chuxu Zhang, Ziyi Kou, Zheyuan Liu, Xiangliang Zhang, Nitesh V. Chawla
In light of this, we propose UGMAE, a unified framework for graph masked autoencoders to address these issues from the perspectives of adaptivity, integrity, complementarity, and consistency.
no code implementations • 6 Oct 2022 • Huimin Zeng, Zhenrui Yue, Ziyi Kou, Lanyu Shang, Yang Zhang, Dong Wang
Moreover, we leverage the power of domain adversarial examples to establish an intermediate domain mixup, where the latent representations of the input text from both domains could be mixed during the training process.
no code implementations • 3 Oct 2022 • Huimin Zeng, Zhenrui Yue, Yang Zhang, Ziyi Kou, Lanyu Shang, Dong Wang
In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems.
1 code implementation • COLING 2022 • Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang, Dong Wang
In this work, we investigate the potential benefits of question classification for QA domain adaptation.
2 code implementations • 20 Aug 2022 • Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang, Dong Wang
However, early misinformation often demonstrates both conditional and label shifts against existing misinformation data (e. g., class imbalance in COVID-19 datasets), rendering such methods less effective for detecting early misinformation.
1 code implementation • 19 Jul 2022 • Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang, Dong Wang
Additionally, we design an adversarial training method tailored for sequential recommender systems.
no code implementations • 29 Mar 2022 • Zhenrui Yue, Huimin Zeng, Ziyi Kou, Lanyu Shang, Dong Wang
Modern smart sensor-based energy management systems leverage non-intrusive load monitoring (NILM) to predict and optimize appliance load distribution in real-time.
1 code implementation • 16 Jul 2020 • Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu
When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information.
no code implementations • 7 Jun 2020 • Weiguo Pian, Yingbo Wu, Ziyi Kou
As an economical and healthy mode of shared transportation, Bike Sharing System (BSS) develops quickly in many big cities.
no code implementations • 7 Jun 2020 • Weiguo Pian, Yingbo Wu, Xiangmou Qu, Junpeng Cai, Ziyi Kou
However, existing GCN-based ride-hailing demand prediction methods only assign the same importance to different neighbor regions, and maintain a fixed graph structure with static spatial relationships throughout the timeline when extracting the irregular non-Euclidean spatial correlations.
1 code implementation • 7 May 2020 • Lele Chen, Guofeng Cui, Ziyi Kou, Haitian Zheng, Chenliang Xu
In this work, we present a carefully-designed benchmark for evaluating talking-head video generation with standardized dataset pre-processing strategies.
no code implementations • 17 Nov 2019 • Ziyi Kou, Guofeng Cui, Shaojie Wang, Wentian Zhao, Chenliang Xu
In this paper, we propose a confidence segmentation (ConfSeg) module that builds confidence score for each pixel in CAM without introducing additional hyper-parameters.
no code implementations • 9 Sep 2019 • Ziyi Kou, Wentian Zhao, Guofeng Cui, Shaojie Wang
Weakly Supervised Object Localization (WSOL) methodsusually rely on fully convolutional networks in order to ob-tain class activation maps(CAMs) of targeted labels.
no code implementations • 2 Dec 2018 • Shaojie Wang, Wentian Zhao, Ziyi Kou, Chenliang Xu
Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding.