1 code implementation • COLING 2022 • Tianshu Yu, Min Yang, Xiaoyan Zhao
This paper presents a novel dependency-aware prototype learning (DAPL) method for few-shot relation classification.
no code implementations • ECCV 2020 • Tianshu Yu, Yikang Li, Baoxin Li
We study the behavior of RhyRNN and empirically show that our method works well even when mph{only event-level labels are available} in the training stage (compared to algorithms requiring sub-activity labels for recognition), and thus is more practical when the sub-activity labels are missing or difficult to obtain.
no code implementations • 3 Mar 2024 • Zihan Zhou, Ruiying Liu, Jiachen Zheng, Xiaoxue Wang, Tianshu Yu
Sampling viable 3D structures (e. g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized by the inter-point distance manifold.
no code implementations • 26 Feb 2024 • Xinjian Zhao, Chaolong Ying, Tianshu Yu
Graph Neural Networks (GNNs) learn from graph-structured data by passing local messages between neighboring nodes along edges on certain topological layouts.
no code implementations • 26 Feb 2024 • Chaolong Ying, Xinjian Zhao, Tianshu Yu
Recently, there has been an emerging trend to integrate persistent homology (PH) into graph neural networks (GNNs) to enrich expressive power.
no code implementations • 23 Feb 2024 • Weichen Zhao, Chenguang Wang, Xinyan Wang, Congying Han, Tiande Guo, Tianshu Yu
This paper presents a novel study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs).
no code implementations • 23 Feb 2024 • Chenguang Wang, Xuanhao Pan, Tianshu Yu
This paper presents a novel approach to task grouping in Multitask Learning (MTL), advancing beyond existing methods by addressing key theoretical and practical limitations.
no code implementations • 10 Oct 2023 • Tianshu Yu, Ting-En Lin, Yuchuan Wu, Min Yang, Fei Huang, Yongbin Li
This limitation leads to suboptimal performance, even when ample training data is available.
1 code implementation • 9 Oct 2023 • Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, Tianshu Yu
Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (e. g., language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved.
Ranked #1 on Multimodal Sentiment Analysis on CMU-MOSEI (Acc-7 metric)
no code implementations • 7 Oct 2023 • Zihan Zhou, Ruiying Liu, Tianshu Yu
Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps.
no code implementations • 12 Sep 2023 • Zihan Zhou, Ruiying Liu, Chaolong Ying, Ruimao Zhang, Tianshu Yu
Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule.
no code implementations • 9 Aug 2023 • Zhang-Hua Fu, Sipeng Sun, Jintong Ren, Tianshu Yu, Haoyu Zhang, Yuanyuan Liu, Lingxiao Huang, Xiang Yan, Pinyan Lu
Fair comparisons based on nineteen famous large-scale instances (with 10, 000 to 10, 000, 000 cities) show that HDR is highly competitive against existing state-of-the-art TSP algorithms, in terms of both efficiency and solution quality.
no code implementations • 31 Jul 2023 • Tianshu Yu, Changqun Xia, Jia Li
That is, motion of different parts of the portraits is unbalanced.
1 code implementation • 19 May 2023 • Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, Yongbin Li
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #1 on Multimodal Sentiment Analysis on MOSI
Emotion Recognition in Conversation Multimodal Intent Recognition +1
no code implementations • 10 May 2023 • Chenguang Wang, Tianshu Yu
Efficiently training a multi-task neural solver for various combinatorial optimization problems (COPs) has been less studied so far.
1 code implementation • 1 Mar 2023 • Chenguang Wang, Zhouliang Yu, Stephen Mcaleer, Tianshu Yu, Yaodong Yang
Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy.
no code implementations • 3 Feb 2023 • Zihan Zhou, Tianshu Yu
In this paper, we propose a sequential learning approach under this setting by decoupling a complex system for handling irregularly sampled and cluttered sequential observations.
1 code implementation • 1 Feb 2023 • Weihuang Wen, Tianshu Yu
The Boolean Satisfiability (SAT) problem stands out as an attractive NP-complete problem in theoretic computer science and plays a central role in a broad spectrum of computing-related applications.
no code implementations • 27 Sep 2022 • Junjie Wu, Changqun Xia, Tianshu Yu, Jia Li
Inspired by humans' observing process, we propose a view-aware salient object detection method based on a Sample Adaptive View Transformer (SAVT) module with two sub-modules to mitigate these issues.
1 code implementation • 18 Oct 2021 • Shanchao Yang, Kaili Ma, Baoxiang Wang, Tianshu Yu, Hongyuan Zha
In this case, GNNs can barely learn useful information, resulting in prohibitive difficulty in making actions for successively rewiring edges under a reinforcement learning context.
no code implementations • 1 Jan 2021 • Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
Graph matching (GM) has been traditionally modeled as a deterministic optimization problem characterized by an affinity matrix under pre-defined graph topology.
no code implementations • CVPR 2021 • Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, Xiaokang Yang
This paper presents a hybrid approach by combing the interpretability of traditional search-based techniques for producing the edit path, as well as the efficiency and adaptivity of deep embedding models to achieve a cost-effective GED solver.
no code implementations • CVPR 2020 • Tianshu Yu, Junchi Yan, Baoxin Li
Graph matching refers to finding vertex correspondence for a pair of graphs, which plays a fundamental role in many vision and learning related tasks.
no code implementations • ICLR 2020 • Tianshu Yu, Yikang Li, Baoxin Li
Determinantal point processes (DPPs) is an effective tool to deliver diversity on multiple machine learning and computer vision tasks.
1 code implementation • 14 Jan 2020 • Yikang Li, Tianshu Yu, Baoxin Li
In this paper, we investigate the problem of recognizing long and complex events with varying action rhythms, which has not been considered in the literature but is a practical challenge.
no code implementations • ICLR 2020 • Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
Graph matching aims to establishing node-wise correspondence between two graphs, which is a classic combinatorial problem and in general NP-complete.
Ranked #15 on Graph Matching on PASCAL VOC (matching accuracy metric)
no code implementations • 2 Dec 2018 • Yantian Zha, Yikang Li, Tianshu Yu, Subbarao Kambhampati, Baoxin Li
We build an event recognition system, ER-PRN, which takes Pixel Dynamics Network as a subroutine, to recognize events based on observations augmented by plan-recognition-driven attention.
no code implementations • NeurIPS 2018 • Tianshu Yu, Junchi Yan, Yilin Wang, Wei Liu, Baoxin Li
Graph matching has received persistent attention over decades, which can be formulated as a quadratic assignment problem (QAP).
no code implementations • ECCV 2018 • Tianshu Yu, Junchi Yan, Wei Liu, Baoxin Li
In this paper, we present an incremental multi-graph matching approach, which deals with the arriving graph utilizing the previous matching results under the global consistency constraint.
no code implementations • 1 May 2018 • Zhiyuan Fang, Shu Kong, Tianshu Yu, Yezhou Yang
Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction.
no code implementations • CVPR 2018 • Tianshu Yu, Junchi Yan, Jieyi Zhao, Baoxin Li
As two fundamental problems, graph cuts and graph matching have been investigated over decades, resulting in vast literature in these two topics respectively.