1 code implementation • COLING 2022 • Weijie Yu, Liang Pang, Jun Xu, Bing Su, Zhenhua Dong, Ji-Rong Wen
Enjoying the partial transport properties of OPT, the selected key sentences can not only effectively enhance the matching accuracy, but also be explained as the rationales for the matching results.
1 code implementation • 30 May 2024 • Jinxia Yang, Bing Su, Wayne Xin Zhao, Ji-Rong Wen
In this paper, we introduce the Med-ST framework for fine-grained spatial and temporal modeling to exploit information from multiple spatial views of chest radiographs and temporal historical records.
no code implementations • 2 May 2024 • Jingyao Wang, Wenwen Qiang, Zeen Song, Lingyu Si, Jiangmeng Li, Changwen Zheng, Bing Su
Based on the definition and measurement, we propose a general SSL framework, called GeSSL, to explicitly model universality into SSL.
2 code implementations • 5 Apr 2024 • Wenyi Mo, Tianyu Zhang, Yalong Bai, Bing Su, Ji-Rong Wen, Qing Yang
Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images.
no code implementations • 14 Feb 2024 • Jiexin Wang, Jiahao Chen, Bing Su
Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i. e., the prediction confidences cannot truly reflect the accuracy.
1 code implementation • 10 Aug 2023 • Zezhong Lv, Bing Su, Ji-Rong Wen
Finally, by suppressing the unimodal effect of masked query, we can rectify the reconstructions of video proposals to perform reasonable contrastive learning.
1 code implementation • 7 Aug 2023 • Yujie Zhou, Wenwen Qiang, Anyi Rao, Ning Lin, Bing Su, Jiaqi Wang
Specifically, 1) we maximize the MI between visual and semantic space for distribution alignment; 2) we leverage the temporal information for estimating the MI by encouraging MI to increase as more frames are observed.
1 code implementation • 3 Aug 2023 • Zhao Yang, Bing Su, Ji-Rong Wen
Firstly, they cannot directly generate coherent motions and require additional operations such as interpolation to process the generated actions.
1 code implementation • 2 Aug 2023 • Jiexin Wang, Yujie Zhou, Wenwen Qiang, Ying Ba, Bing Su, Ji-Rong Wen
Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses.
no code implementations • 22 May 2023 • Jiahao Chen, Yurou Liu, Jiangmeng Li, Bing Su, JiRong Wen
In this paper, we introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA), which addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information.
no code implementations • 17 Apr 2023 • Jiexin Wang, Jiahao Chen, Bing Su
Auto-evaluation aims to automatically evaluate a trained model on any test dataset without human annotations.
1 code implementation • CVPR 2023 • Jiahao Chen, Bing Su
We adaptively transfer knowledge from head classes to get the target probability density of tail classes.
1 code implementation • 17 Feb 2023 • Yujie Zhou, Haodong Duan, Anyi Rao, Bing Su, Jiaqi Wang
Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM).
no code implementations • 17 Jan 2023 • Bing Su, Fukang Zhu, Ke Zhu
For the log-SHE model, its spatial near-epoch dependence (NED) property is investigated, and a systematic statistical inference procedure is provided, including the maximum likelihood and generalized method of moments estimators, the Wald, Lagrange multiplier and likelihood-ratio-type D tests for model parameter constraints, and the overidentification test for the model diagnostic checking.
1 code implementation • CVPR 2023 • Heng Zhang, Daqing Liu, Qi Zheng, Bing Su
Specifically, we enforce the embeddings of the frame sequence of interest to approximate a goal-oriented stochastic process, i. e., Brownian bridge, in the latent space via a process-based contrastive loss.
no code implementations • ICCV 2023 • Heng Zhang, Daqing Liu, Zezhong Lv, Bing Su, DaCheng Tao
Paired video and language data is naturally temporal concurrency, which requires the modeling of the temporal dynamics within each modality and the temporal alignment across modalities simultaneously.
2 code implementations • 16 Sep 2022 • Jiangmeng Li, Wenwen Qiang, Yanan Zhang, Wenyi Mo, Changwen Zheng, Bing Su, Hui Xiong
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample.
2 code implementations • 16 Sep 2022 • Jiangmeng Li, Wenwen Qiang, Changwen Zheng, Bing Su, Farid Razzak, Ji-Rong Wen, Hui Xiong
To this end, we propose a methodology, specifically consistency and complementarity network (CoCoNet), which avails of strict global inter-view consistency and local cross-view complementarity preserving regularization to comprehensively learn representations from multiple views.
4 code implementations • 12 Sep 2022 • Bing Su, Dazhao Du, Zhao Yang, Yujie Zhou, Jiangmeng Li, Anyi Rao, Hao Sun, Zhiwu Lu, Ji-Rong Wen
Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality.
Ranked #7 on Molecule Captioning on ChEBI-20
no code implementations • 29 Jun 2022 • Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Bing Su, Hui Xiong
Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner.
1 code implementation • 21 Jun 2022 • Gang Li, Heliang Zheng, Daqing Liu, Chaoyue Wang, Bing Su, Changwen Zheng
In this paper, we explore a potential visual analogue of words, i. e., semantic parts, and we integrate semantic information into the training process of MAE by proposing a Semantic-Guided Masking strategy.
1 code implementation • 26 May 2022 • Dazhao Du, Bing Su, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan
Most state-of-the-art methods focus on designing temporal convolution-based models, but the inflexibility of temporal convolutions and the difficulties in modeling long-term temporal dependencies restrict the potential of these models.
Ranked #1 on Action Segmentation on 50Salads
no code implementations • 23 May 2022 • Jiangmeng Li, Wenyi Mo, Wenwen Qiang, Bing Su, Changwen Zheng
Vision-language models are pre-trained by aligning image-text pairs in a common space so that the models can deal with open-set visual concepts by learning semantic information from textual labels.
1 code implementation • 19 May 2022 • Zihan Li, Wentao Chen, Zhiqing Wei, Xingqi Luo, Bing Su
In addition, to cope with new attacks in real-world deployment, we propose an Active Adaption Resampling (AAR) method, which can better discover the distribution of unseen sample data and adapt the parameters of encoder.
2 code implementations • 10 Mar 2022 • Jiangmeng Li, Wenwen Qiang, Changwen Zheng, Bing Su, Hui Xiong
We perform a meta learning technique to build the augmentation generator that updates its network parameters by considering the performance of the encoder.
no code implementations • 8 Mar 2022 • Wenwen Qiang, Jiangmeng Li, Changwen Zheng, Bing Su, Hui Xiong
We conduct theoretical analysis on the robustness of the proposed RLPGA and prove that the robust informative-theoretic-based loss and the local preserving module are beneficial to reduce the empirical risk of the target domain.
1 code implementation • 23 Feb 2022 • Dazhao Du, Bing Su, Zhewei Wei
In this way, if a key segment has a high correlation score with the query segment, its successive segment contributes more to the prediction of the query segment.
no code implementations • 29 Sep 2021 • Dazhao Du, Bing Su, Zhewei Wei
Long-term time series forecasting is widely used in real-world applications such as financial investment, electricity management and production planning.
no code implementations • 29 Sep 2021 • Jiahao Chen, Bing Su
We apply STG to samples of tail classes for augmentation in the classifier-tuning stage.
1 code implementation • ICLR 2022 • Bing Su, Ji-Rong Wen
Explainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances.
no code implementations • 29 Sep 2021 • Bing Su, Ji-Rong Wen
Convolutional neural networks use regular quadrilateral convolution kernels to extract features.
no code implementations • 29 Sep 2021 • Wenwen Qiang, Jiangmeng Li, Jie Hu, Bing Su, Changwen Zheng, Hui Xiong
In this paper, we give an analysis of the existing representation learning framework of unsupervised domain adaptation and show that the learned feature representations of the source domain samples are with discriminability, compressibility, and transferability.
no code implementations • 6 Sep 2021 • Jiangmeng Li, Wenwen Qiang, Hang Gao, Bing Su, Farid Razzak, Jie Hu, Changwen Zheng, Hui Xiong
To this end, we rethink the existing multi-view learning paradigm from the information theoretical perspective and then propose a novel information theoretical framework for generalized multi-view learning.
1 code implementation • 26 Jul 2021 • Bing Su, Ji-Rong Wen
Convolutional neural networks use regular quadrilateral convolution kernels to extract features.
no code implementations • 19 Jul 2021 • Jiahuan Zhou, Yansong Tang, Bing Su, Ying Wu
We justify that the performance limitation is caused by the gradient vanishing on these sample outliers.
no code implementations • ICCV 2019 • Bing Su, Jiahuan Zhou, Ying Wu
Supervised dimensionality reduction for sequence data projects the observations in sequences onto a low-dimensional subspace to better separate different sequence classes.
no code implementations • ICML 2018 • Bing Su, Ying Wu
Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace.
no code implementations • CVPR 2018 • Jiahuan Zhou, Bing Su, Ying Wu
Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification.
no code implementations • CVPR 2017 • Bing Su, Gang Hua
We present a new distance measure between sequences that can tackle local temporal distortion and periodic sequences with arbitrary starting points.
no code implementations • CVPR 2015 • Bing Su, Xiaoqing Ding, Changsong Liu, Ying Wu
Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem.