no code implementations • 24 Jul 2019 • Chia-Hung Huang, Hang Yin, Yu-Wing Tai, Chi-Keung Tang
Video stabilization algorithms are of greater importance nowadays with the prevalence of hand-held devices which unavoidably produce videos with undesirable shaky motions.
no code implementations • 11 Sep 2019 • Shahbaz Abdul Khader, Hang Yin, Pietro Falco, Danica Kragic
Learning dynamics models is an essential component of model-based reinforcement learning.
Robotics
1 code implementation • 19 Mar 2020 • Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasiia Varava, Hang Yin, Alessandro Marino, Danica Kragic
We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects.
no code implementations • 12 Jan 2021 • Wei Min, Weiming Liang, Hang Yin, Zhurong Wang, Mei Li, Alok Lal
To utilize the behavior sequence data, we treat click stream data as event sequence, use time attention based Bi-LSTM to learn the sequence embedding in an unsupervised fashion, and combine them with intuitive features generated by risk experts to form a hybrid feature representation.
no code implementations • 13 Jan 2021 • Hang Yin, Xinyue Liu, Xiangnan Kong
Existing works mainly focus on unimodal distributions, where it is usually assumed that the observed activities aregenerated from asingleGaussian distribution (i. e., one graph). However, this assumption is too strong for many real-worldapplications.
1 code implementation • 3 Mar 2021 • Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasia Varava, Hang Yin, Alessandro Marino, Danica Kragic
We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects.
1 code implementation • 4 Mar 2021 • Zehang Weng, Fabian Paus, Anastasiia Varava, Hang Yin, Tamim Asfour, Danica Kragic
In an ablation study, we show the benefits of the two-stage model for single time step prediction and the effectiveness of the mixed-horizon model for long-term prediction tasks.
Robotics
no code implementations • 7 Apr 2021 • Wenjie Yin, Hang Yin, Danica Kragic, Mårten Björkman
Data-driven approaches for modeling human skeletal motion have found various applications in interactive media and social robotics.
1 code implementation • 12 Sep 2021 • Yifei Ming, Hang Yin, Yixuan Li
Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
2 code implementations • 18 Sep 2021 • ZiHao Wang, Hang Yin, Yangqiu Song
Besides, our work, for the first time, provides a benchmark to evaluate and analyze the impact of different operators and normal forms by using (a) 7 choices of the operator systems and (b) 9 forms of complex queries.
1 code implementation • 7 Oct 2021 • Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva
This work addresses the problem of sensing the world: how to learn a multimodal representation of a reinforcement learning agent's environment that allows the execution of tasks under incomplete perceptual conditions.
1 code implementation • 7 Feb 2022 • Petra Poklukar, Miguel Vasco, Hang Yin, Francisco S. Melo, Ana Paiva, Danica Kragic
Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels.
no code implementations • 8 Jul 2022 • Gustaf Tegnér, Alfredo Reichlin, Hang Yin, Mårten Björkman, Danica Kragic
In this work we provide an analysis of the distribution of the post-adaptation parameters of Gradient-Based Meta-Learning (GBML) methods.
no code implementations • 18 Jul 2022 • Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Ali Ghadirzadeh, Danica Kragic
However, a major challenge is a distributional shift between the states in the training dataset and the ones visited by the learned policy at the test time.
no code implementations • 19 Aug 2022 • Wenjie Yin, Hang Yin, Kim Baraka, Danica Kragic, Mårten Björkman
We present CycleDance, a dance style transfer system to transform an existing motion clip in one dance style to a motion clip in another dance style while attempting to preserve motion context of the dance.
no code implementations • 13 Oct 2022 • Hang Yin, Zitao Zhang, Zhurong Wang, Yilmazcan Ozyurt, Weiming Liang, Wenyu Dong, Yang Zhao, Yinan Shan
Our experiments show that embedding features learned from similarity based behavioral graph have achieved significant performance increase to the baseline fraud detection model in various business scenarios.
no code implementations • 3 Apr 2023 • Wenjie Yin, Ruibo Tu, Hang Yin, Danica Kragic, Hedvig Kjellström, Mårten Björkman
Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics.
1 code implementation • 14 Apr 2023 • Hang Yin, ZiHao Wang, Yangqiu Song
Moreover, we develop a new dataset containing ten new types of queries with features that have never been considered and therefore can provide a thorough investigation of complex queries.
1 code implementation • 6 May 2023 • ZiHao Wang, Weizhi Fei, Hang Yin, Yangqiu Song, Ginny Y. Wong, Simon See
In contrast to existing scoring functions motivated by local comparison or global transport, this work investigates the local and global trade-off with unbalanced optimal transport theory.
1 code implementation • 15 Jul 2023 • Hang Yin, ZiHao Wang, Weizhi Fei, Yangqiu Song
Learning-based methods are essential because they are capable of generalizing over unobserved knowledge.
1 code implementation • 11 Sep 2023 • Alfredo Reichlin, Giovanni Luca Marchetti, Hang Yin, Anastasiia Varava, Danica Kragic
We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with.
1 code implementation • 30 Sep 2023 • Wenjie Yin, Qingyuan Yao, Yi Yu, Hang Yin, Danica Kragic, Mårten Björkman
To complement it, we introduce JustLMD, a new multimodal dataset of 3D dance motion with music and lyrics.
1 code implementation • 17 Oct 2023 • Hang Yin, Pinren Lu, Ziang Li, Bin Sun, Kan Li
The need for high-quality data has been a key issue hindering the research of dialogue tasks.
no code implementations • 4 Nov 2023 • Hang Yin, Yao Su, Xinyue Liu, Thomas Hartvigsen, Yanhua Li, Xiangnan Kong
We refer to such brain networks as multi-state, and this mixture can help us understand human behavior.
no code implementations • 14 Nov 2023 • Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen
In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.
no code implementations • 14 Nov 2023 • Hang Yin, Kuang-Hung Liu, Mengying Sun, Yuxin Chen, Buyun Zhang, Jiang Liu, Vivek Sehgal, Rudresh Rajnikant Panchal, Eugen Hotaj, Xi Liu, Daifeng Guo, Jamey Zhang, Zhou Wang, Shali Jiang, Huayu Li, Zhengxing Chen, Wen-Yen Chen, Jiyan Yang, Wei Wen
The large scale of models and tight production schedule requires AutoML to outperform human baselines by only using a small number of model evaluation trials (around 100).
no code implementations • 12 Dec 2023 • Wenjie Yin, Yi Yu, Hang Yin, Danica Kragic, Mårten Björkman
Current training of motion style transfer systems relies on consistency losses across style domains to preserve contents, hindering its scalable application to a large number of domains and private data.
no code implementations • 16 Feb 2024 • Alfredo Reichlin, Miguel Vasco, Hang Yin, Danica Kragic
Experimentally, we show how our method consistently outperforms other offline RL baselines in learning from sub-optimal offline datasets.
no code implementations • 3 Mar 2024 • Weizhi Fei, ZiHao Wang, Hang Yin, Yang Duan, Hanghang Tong, Yangqiu Song
To bridge this gap, we study the setting of soft queries on uncertain knowledge, which is motivated by the establishment of soft constraint programming.
no code implementations • 14 Mar 2024 • Wenjie Yin, Xuejiao Zhao, Yi Yu, Hang Yin, Danica Kragic, Mårten Björkman
First, we propose LM2D, a novel probabilistic architecture that incorporates a multimodal diffusion model with consistency distillation, designed to create dance conditioned on both music and lyrics in one diffusion generation step.
no code implementations • 14 Mar 2024 • Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Martín-Martín, Chen Wang, Gabrael Levine, Wensi Ai, Benjamin Martinez, Hang Yin, Michael Lingelbach, Minjune Hwang, Ayano Hiranaka, Sujay Garlanka, Arman Aydin, Sharon Lee, Jiankai Sun, Mona Anvari, Manasi Sharma, Dhruva Bansal, Samuel Hunter, Kyu-Young Kim, Alan Lou, Caleb R Matthews, Ivan Villa-Renteria, Jerry Huayang Tang, Claire Tang, Fei Xia, Yunzhu Li, Silvio Savarese, Hyowon Gweon, C. Karen Liu, Jiajun Wu, Li Fei-Fei
We present BEHAVIOR-1K, a comprehensive simulation benchmark for human-centered robotics.
no code implementations • 15 Mar 2024 • Hang Yin, ZiHao Wang, Yangqiu Song
To answer complex queries under incomplete knowledge, learning-based Complex Query Answering (CQA) models are proposed to directly learn from the query-answer samples to avoid the direct traversal of incomplete graph data.
no code implementations • 16 Mar 2024 • Hang Yin, Dong Ding, Liyao Xiang, Yuheng He, Yihan Wu, Xinbing Wang, Chenghu Zhou
We investigate the entity alignment problem with unlabeled dangling cases, meaning that there are entities in the source or target graph having no counterparts in the other, and those entities remain unlabeled.