no code implementations • 15 Mar 2024 • Zhiyong Wang, Jize Xie, Yi Chen, John C. S. Lui, Dongruo Zhou
We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round.
no code implementations • 26 Feb 2024 • Hantao Yang, Xutong Liu, Zhiyong Wang, Hong Xie, John C. S. Lui, Defu Lian, Enhong Chen
We study the problem of federated contextual combinatorial cascading bandits, where $|\mathcal{U}|$ agents collaborate under the coordination of a central server to provide tailored recommendations to the $|\mathcal{U}|$ corresponding users.
no code implementations • 26 Jan 2024 • Dai Shi, Andi Han, Lequan Lin, Yi Guo, Zhiyong Wang, Junbin Gao
Physics-informed Graph Neural Networks have achieved remarkable performance in learning through graph-structured data by mitigating common GNN challenges such as over-smoothing, over-squashing, and heterophily adaption.
no code implementations • 11 Jan 2024 • Weibo Jiang, Weihong Ren, Jiandong Tian, Liangqiong Qu, Zhiyong Wang, Honghai Liu
In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection.
Human-Object Interaction Detection Knowledge Distillation +2
1 code implementation • 29 Dec 2023 • Xingqiao Li, Jindong Gu, Zhiyong Wang, Yancheng Yuan, Bo Du, Fengxiang He
To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data.
2 code implementations • 22 Dec 2023 • Wenxi Yue, Jing Zhang, Kun Hu, Qiuxia Wu, ZongYuan Ge, Yong Xia, Jiebo Luo, Zhiyong Wang
Specifically, we achieve this by proposing (1) Collaborative Prompts that describe instrument structures via collaborating category-level and part-level texts; (2) Cross-Modal Prompt Encoder that encodes text prompts jointly with visual embeddings into discriminative part-level representations; and (3) Part-to-Whole Adaptive Fusion and Hierarchical Decoding that adaptively fuse the part-level representations into a whole for accurate instrument segmentation in surgical scenarios.
1 code implementation • 23 Nov 2023 • Peng Xia, Xingtong Yu, Ming Hu, Lie Ju, Zhiyong Wang, Peibo Duan, ZongYuan Ge
We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category.
Fine-Grained Visual Recognition Graph Representation Learning
1 code implementation • 7 Sep 2023 • Zhuqiang Lu, Kun Hu, Chaoyue Wang, Lei Bai, Zhiyong Wang
A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene.
no code implementations • 1 Sep 2023 • Xin Qi, Xiaopeng Wang, Zhiyong Wang, Wang Liu, Mingming Ding, Shuchen Shi
The evaluation results of our system showed a quality MOS score of 3. 6 for the Hub task and 3. 4 for the Spoke task, placing our system at an average level among all participating teams.
no code implementations • 31 Aug 2023 • Zexin Hu, Kun Hu, Clinton Mo, Lei Pan, Zhiyong Wang
Sketch-based terrain generation seeks to create realistic landscapes for virtual environments in various applications such as computer games, animation and virtual reality.
no code implementations • 25 Aug 2023 • Jiaming Shen, Kun Hu, Wei Bao, Chang Wen Chen, Zhiyong Wang
The 2D animation workflow is typically initiated with the creation of keyframes using sketch-based drawing.
1 code implementation • 18 Aug 2023 • Penghui Wen, Kun Hu, Wenxi Yue, Sen Zhang, Wanlei Zhou, Zhiyong Wang
Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques.
1 code implementation • 17 Aug 2023 • Wenxi Yue, Jing Zhang, Kun Hu, Yong Xia, Jiebo Luo, Zhiyong Wang
However, we observe two problems with this naive pipeline: (1) the domain gap between natural objects and surgical instruments leads to inferior generalisation of SAM; and (2) SAM relies on precise point or box locations for accurate segmentation, requiring either extensive manual guidance or a well-performing specialist detector for prompt preparation, which leads to a complex multi-stage pipeline.
no code implementations • 14 Aug 2023 • Chenwei Wang, Jifang Pei, Zhiyong Wang, Yulin Huang, Junjie Wu, Haiguang Yang, Jianyu Yang
In this paper, we propose a new multi-task learning approach for SAR ATR, which could obtain the accurate category and precise shape of the targets simultaneously.
1 code implementation • NeurIPS 2023 • Zhenfei Yin, Jiong Wang, JianJian Cao, Zhelun Shi, Dingning Liu, Mukai Li, Lu Sheng, Lei Bai, Xiaoshui Huang, Zhiyong Wang, Jing Shao, Wanli Ouyang
To the best of our knowledge, we present one of the very first open-source endeavors in the field, LAMM, encompassing a Language-Assisted Multi-Modal instruction tuning dataset, framework, and benchmark.
1 code implementation • 6 Jun 2023 • Peggy Tang, Junbin Gao, Lei Zhang, Zhiyong Wang
Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation.
no code implementations • 23 May 2023 • Jianing Li, Bowen Chen, Zhiyong Wang, Honghai Liu
Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions.
no code implementations • 9 Apr 2023 • Changjie Qiu, Zhiyong Wang, Xiuhong Lin, Yu Zang, Cheng Wang, Weiquan Liu
Second, we propose an modeling evaluation method based on HPMB for object-level modeling to overcome this limitation.
Point Cloud Registration Simultaneous Localization and Mapping
1 code implementation • CVPR 2023 • Clinton Ansun Mo, Kun Hu, Chengjiang Long, Zhiyong Wang
Deriving sophisticated 3D motions from sparse keyframes is a particularly challenging problem, due to continuity and exceptionally skeletal precision.
no code implementations • 3 Mar 2023 • Lintao Wang, Kun Hu, Lei Bai, Yu Ding, Wanli Ouyang, Zhiyong Wang
As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase.
1 code implementation • 1 Mar 2023 • Zhiyong Wang, Xutong Liu, Shuai Li, John C. S. Lui
To tackle these issues, we first propose ``ConLinUCB", a general framework for conversational bandits with better information incorporation, combining arm-level and key-term-level feedback to estimate user preference in one step at each time.
no code implementations • 18 Jan 2023 • Jianfeng Weng, Kun Hu, Tingting Yao, Jingya Wang, Zhiyong Wang
Thus, in this work, a federated unsupervised cluster-contrastive (FedUCC) learning method is proposed for Person ReID.
no code implementations • ICCV 2023 • Zhiheng Fu, Longguang Wang, Lian Xu, Zhiyong Wang, Hamid Laga, Yulan Guo, Farid Boussaid, Mohammed Bennamoun
In this paper, we thus propose an unsupervised viewpoint representation learning scheme for 3D point cloud completion without explicit viewpoint estimation.
no code implementations • 21 Dec 2022 • Rusheng Pan, Zhiyong Wang, Yating Wei, Han Gao, Gongchang Ou, Caleb Chen Cao, Jingli Xu, Tong Xu, Wei Chen
A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators.
no code implementations • 16 Oct 2022 • Peggy Tang, Kun Hu, Lei Zhang, Jiebo Luo, Zhiyong Wang
Multimodal summarisation with multimodal output is drawing increasing attention due to the rapid growth of multimedia data.
no code implementations • 22 Sep 2022 • Kun Hu, Shaohui Mei, Wei Wang, Kaylena A. Ehgoetz Martens, Liang Wang, Simon J. G. Lewis, David D. Feng, Zhiyong Wang
The proposed scheme also sheds light on improving subject-level clinical studies from other scenarios as it can be integrated with many existing deep architectures.
no code implementations • 13 Sep 2022 • Zhen Yu, Toan Nguyen, Yaniv Gal, Lie Ju, Shekhar S. Chandra, Lei Zhang, Paul Bonnington, Victoria Mar, Zhiyong Wang, ZongYuan Ge
Accordingly, the learned prototypes preserve the semantic class relations in the embedding space and we can predict the label of an image by assigning its feature to the nearest hyperbolic class prototype.
1 code implementation • 25 Jul 2022 • Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Tom Drummond, Zhiyong Wang, ZongYuan Ge
The self-attention mechanism, successfully employed with the transformer structure is shown promise in many computer vision tasks including image recognition, and object detection.
no code implementations • TIP 2022 • Peiqin Zhuang, Yu Guo, Zhipeng Yu, Luping Zhou, Lei Bai, Ding Liang, Zhiyong Wang, Yali Wang, Wanli Ouyang
To address this issue, we introduce a Motion Diversification and Selection (MoDS) module to generate diversified spatio-temporal motion features and then select the suitable motion representation dynamically for categorizing the input video.
Ranked #18 on Action Recognition on Something-Something V1
no code implementations • SemEval (NAACL) 2022 • Zhiyong Wang, Ge Zhang, Nineli Lashkarashvili
This paper describes our system for the SemEval2022 task of matching dictionary glosses to word embeddings.
1 code implementation • Findings (NAACL) 2022 • Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang
Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions.
no code implementations • CVPR 2022 • Jialian Li, Jingyi Zhang, Zhiyong Wang, Siqi Shen, Chenglu Wen, Yuexin Ma, Lan Xu, Jingyi Yu, Cheng Wang
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
Ranked #3 on 3D Human Pose Estimation on SLOPER4D (using extra training data)
no code implementations • 14 Nov 2021 • Jichao Kan, Kun Hu, Markus Hagenbuchner, Ah Chung Tsoi, Mohammed Bennamounm, Zhiyong Wang
Therefore, in this paper, these unique characteristics of sign languages are formulated as hierarchical spatio-temporal graph representations, including high-level and fine-level graphs of which a vertex characterizes a specified body part and an edge represents their interactions.
no code implementations • 27 Mar 2021 • Kun Hu, Zhiyong Wang, Guy Coleman, Asher Bender, Tingting Yao, Shan Zeng, Dezhen Song, Arnold Schumann, Michael Walsh
Weeds are a significant threat to the agricultural productivity and the environment.
4 code implementations • CVPR 2020 • Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang
Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics.
Ranked #4 on 3D Action Recognition on Assembly101
no code implementations • 15 Nov 2019 • Dai Shi, Junbin Gao, Xia Hong, S. T. Boris Choy, Zhiyong Wang
These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems.
no code implementations • 21 Sep 2019 • Zehui Yao, Boyan Zhang, Zhiyong Wang, Wanli Ouyang, Dong Xu, Dagan Feng
For example, given two image domains $X_1$ and $X_2$ with certain attributes, the intersection $X_1 \cap X_2$ denotes a new domain where images possess the attributes from both $X_1$ and $X_2$ domains.
1 code implementation • IEEE Transactions on Visualization and Computer Graphics ( Early Access ) 2019 • Zhiyong Wang, Jinxiang Chai, Shihong Xia
A comparison against Wang et al.[3] shows that our method advances the state of the art in 3D eye tracking using a single RGB camera.
no code implementations • 15 Jan 2016 • Junbin Gao, Yi Guo, Zhiyong Wang
This process can be problematic.
no code implementations • 12 Jan 2014 • Jianzhu Ma, Sheng Wang, Zhiyong Wang, Jinbo Xu
A sequence profile is usually represented as a position-specific scoring matrix (PSSM) or an HMM (Hidden Markov Model) and accordingly PSSM-PSSM or HMM-HMM comparison is used for homolog detection.
no code implementations • 10 Dec 2013 • Jianzhu Ma, Sheng Wang, Zhiyong Wang, Jinbo Xu
To further improve the accuracy of the estimated precision matrices, we employ a supervised learning method to predict contact probability from a variety of evolutionary and non-evolutionary information and then incorporate the predicted probability as prior into our GGL framework.
no code implementations • 8 Aug 2013 • Zhiyong Wang, Jinbo Xu
Most existing methods predict the contact map matrix element-by-element, ignoring correlation among contacts and physical feasibility of the whole contact map.