1 code implementation • COLING 2022 • Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li, Peng Fu, Weiping Wang
Despite the significant progress on this task, it is extremely time-consuming and budget-unfriendly to collect sufficient high-quality labeled data for every new target under fully-supervised learning, whereas unlabeled data can be collected easier.
1 code implementation • COLING 2022 • Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie zhou
The knowledge selector generally constructs a query based on the dialogue context and selects the most appropriate knowledge to help response generation.
1 code implementation • Findings (EMNLP) 2021 • Jiangnan Li, Zheng Lin, Peng Fu, Weiping Wang
Furthermore, we utilize CSK to enrich edges with knowledge representations and process the SKAIG with a graph transformer.
Ranked #9 on
Emotion Recognition in Conversation
on DailyDialog
1 code implementation • 10 Jun 2025 • Mingyu Zheng, Zhifan Feng, Jia Wang, Lanrui Wang, Zheng Lin, Yang Hao, Weiping Wang
Despite the commendable progress of recent LLM-based data synthesis methods, they face two limitations in generating table instruction tuning data.
no code implementations • 30 May 2025 • Naibin Gu, Yilong Chen, Zhenyu Zhang, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang
In this paper, we propose Advantageous Parameter EXpansion Training (APEX), a method that progressively expands advantageous parameters into the space of disadvantageous ones, thereby increasing their proportion and enhancing training effectiveness.
no code implementations • 26 May 2025 • Wei Li, Dezhao Luo, Dongbao Yang, Zhenhang Li, Weiping Wang, Yu Zhou
Based on this observation, the information enhancement strategy is proposed to enhance the informative content of the generated samples from two aspects: the environments and the characters.
1 code implementation • 26 May 2025 • Dingyu Yao, Bowen Shen, Zheng Lin, Wei Liu, Jian Luan, Bin Wang, Weiping Wang
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead.
no code implementations • 12 May 2025 • Zexian Yang, Dian Li, Dayan Wu, Gang Liu, Weiping Wang
Despite significant advancements in multimodal reasoning tasks, existing Large Vision-Language Models (LVLMs) are prone to producing visually ungrounded responses when interpreting associated images.
no code implementations • 9 May 2025 • Rong Yin, Ruyue Liu, Xiaoshuai Hao, Xingrui Zhou, Yong liu, Can Ma, Weiping Wang
The multi-modal molecular representation learning module collaboratively processes information from different modalities of the same molecule to overcome intermodal differences and generate a unified molecular embedding.
1 code implementation • 22 Apr 2025 • Chenxu Yang, Qingyi Si, Yongjie Duan, Zheliang Zhu, Chenyu Zhu, Qiaowei Li, Zheng Lin, Li Cao, Weiping Wang
Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks.
no code implementations • 9 Apr 2025 • Lanrui Wang, Mingyu Zheng, Hongyin Tang, Zheng Lin, Yanan Cao, Jingang Wang, Xunliang Cai, Weiping Wang
Processing structured tabular data, particularly lengthy tables, constitutes a fundamental yet challenging task for large language models (LLMs).
no code implementations • 19 Feb 2025 • Naibin Gu, Zhenyu Zhang, Xiyu Liu, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang
Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods.
no code implementations • 19 Feb 2025 • Ruyue Liu, Rong Yin, Yong liu, Xiaoshuai Hao, Haichao Shi, Can Ma, Weiping Wang
To our knowledge, we are the first to encode augmentation views of the spectral domain using asymmetric encoders.
no code implementations • 18 Dec 2024 • Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong liu, Can Ma, Weiping Wang
By utilizing low-rank and sparse parameters along with compression techniques, CEFGL significantly reduces communication complexity.
no code implementations • 22 Nov 2024 • Xunyu Zhu, Jian Li, Can Ma, Weiping Wang
In addition, we propose a multi-round distillation paradigm to iteratively enrich the distillation datasets, thereby progressively improving the mathematical reasoning abilities of SLMs.
no code implementations • 4 Nov 2024 • Siyuan Chen, Qingyi Si, Chenxu Yang, Yunzhi Liang, Zheng Lin, Huan Liu, Weiping Wang
The advent of large language models (LLMs) has significantly propelled the advancement of Role-Playing Agents (RPAs).
no code implementations • 11 Oct 2024 • Yufan Liu, Jinyang An, Wanqian Zhang, Ming Li, Dayan Wu, Jingzi Gu, Zheng Lin, Weiping Wang
The remarkable development of text-to-image generation models has raised notable security concerns, such as the infringement of portrait rights and the generation of inappropriate content.
no code implementations • 23 Sep 2024 • Chenxu Yang, Ruipeng Jia, Naibin Gu, Zheng Lin, Siyuan Chen, Chao Pang, Weichong Yin, Yu Sun, Hua Wu, Weiping Wang
Hence, we introduce orthogonal finetuning for DPO via a weight-Rotated Preference Optimization (RoPO) method, which merely conducts rotational and magnitude-stretching updates on the weight parameters to maintain the hyperspherical energy invariant, thereby preserving the knowledge encoded in the angle between neurons.
no code implementations • 27 Aug 2024 • Xiyu Liu, Zhengxiao Liu, Naibin Gu, Zheng Lin, Wanli Ma, Ji Xiang, Weiping Wang
The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights.
1 code implementation • 1 Aug 2024 • Huishan Ji, Qingyi Si, Zheng Lin, Weiping Wang
Throughout rapid development of multimodal large language models, a crucial ingredient is a fair and accurate evaluation of their multimodal comprehension abilities.
no code implementations • 14 Jul 2024 • Xunyu Zhu, Jian Li, Can Ma, Weiping Wang
Distilling LLM mathematical reasoning into Smaller Language Models (SLMs) has emerged as a solution to this challenge, although these smaller models often suffer from errors in calculation and semantic understanding.
1 code implementation • 11 Jul 2024 • Yufan Liu, Wanqian Zhang, Dayan Wu, Zheng Lin, Jingzi Gu, Weiping Wang
Model inversion (MI) attack reconstructs the private training data of a target model given its output, posing a significant threat to deep learning models and data privacy.
1 code implementation • 8 Jul 2024 • Bowen Shen, Zheng Lin, Daren Zha, Wei Liu, Jian Luan, Bin Wang, Weiping Wang
However, as the coarse-grained structured pruning poses large damage to the highly interconnected model, achieving a high compression ratio for scaled-up LLMs remains a challenge.
no code implementations • 8 Jul 2024 • Chenxu Yang, Zheng Lin, Chong Tian, Liang Pang, Lanrui Wang, Zhengyang Tong, Qirong Ho, Yanan Cao, Weiping Wang
Grounding external knowledge can enhance the factuality of responses in dialogue generation.
1 code implementation • 12 Jun 2024 • Mingyu Zheng, Xinwei Feng, Qingyi Si, Qiaoqiao She, Zheng Lin, Wenbin Jiang, Weiping Wang
Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text sequence (such as Markdown or HTML) to serve as model input.
no code implementations • 7 Jun 2024 • Jiangnan Li, Zheng Lin, Lanrui Wang, Qingyi Si, Yanan Cao, Mo Yu, Peng Fu, Weiping Wang, Jie zhou
Besides, EDEN can help LLMs achieve better recognition of emotions and causes, which explores a new research direction of explainable emotion understanding in dialogues.
1 code implementation • 6 Jun 2024 • Naibin Gu, Peng Fu, Xiyu Liu, Bowen Shen, Zheng Lin, Weiping Wang
The Light-PEFT framework allows for the simultaneous estimation of redundant parameters in both the foundation model and PEFT modules during the early stage of training.
1 code implementation • 3 Jun 2024 • Hansong Zhang, Shikun Li, Fanzhao Lin, Weiping Wang, Zhenxing Qian, Shiming Ge
Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing.
1 code implementation • 31 May 2024 • Yisu Liu, Jinyang An, Wanqian Zhang, Dayan Wu, Jingzi Gu, Zheng Lin, Weiping Wang
In this paper, we propose DisDiff (Disrupting Diffusion), a novel adversarial attack method to disrupt the diffusion model outputs.
1 code implementation • 3 Mar 2024 • Renjie Xu, Guangwei Wu, Weiping Wang, Xing Gao, An He, Zhengpeng Zhang
To the best of our knowledge, it is the first GNN-based self-supervised method for the multiclass classification of network flows in NIDS.
no code implementations • 11 Feb 2024 • Jiangnan Li, Qiujing Wang, Liyan Xu, Wenjie Pang, Mo Yu, Zheng Lin, Weiping Wang, Jie zhou
Similar to the "previously-on" scenes in TV shows, recaps can help book reading by recalling the readers' memory about the important elements in previous texts to better understand the ongoing plot.
1 code implementation • 4 Feb 2024 • Hanwen Zhang, Qingyi Si, Peng Fu, Zheng Lin, Weiping Wang
Finally, we analyze some possible directions to promote the accuracy of TFV via LLMs, which is beneficial to further research of table reasoning.
no code implementations • 22 Jan 2024 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance.
1 code implementation • 5 Jan 2024 • Jian Li, Yong liu, Wei Wang, Haoran Wu, Weiping Wang
We provide convergence analysis based on statistical learning for the federated Newton sketch approaches.
no code implementations • CVPR 2024 • Zexian Yang, Dayan Wu, Chenming Wu, Zheng Lin, Jingzi Gu, Weiping Wang
Whiteness the impressive capabilities in multimodal understanding of Vision Language Foundation Model CLIP a recent two-stage CLIP-based method employs automated prompt engineering to obtain specific textual labels for classifying pedestrians.
no code implementations • 10 Dec 2023 • Ruyue Liu, Rong Yin, Yong liu, Weiping Wang
Graph Comparative Learning (GCL) is a self-supervised method that combines the advantages of Graph Convolutional Networks (GCNs) and comparative learning, making it promising for learning node representations.
1 code implementation • 26 Nov 2023 • Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang
Recently, there has been a heightened interest in building chatbots based on Large Language Models (LLMs) to emulate human-like qualities in multi-turn conversations.
no code implementations • 13 Oct 2023 • Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context.
1 code implementation • 11 Oct 2023 • Qingyi Si, Tong Wang, Zheng Lin, Xu Zhang, Yanan Cao, Weiping Wang
This paper will release a powerful Chinese LLMs that is comparable to ChatGLM.
no code implementations • 15 Aug 2023 • Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang
This paper presents a survey of model compression techniques for LLMs.
no code implementations • 14 Aug 2023 • Xugong Qin, Pengyuan Lyu, Chengquan Zhang, Yu Zhou, Kun Yao, Peng Zhang, Hailun Lin, Weiping Wang
Different from existing methods which integrate multiple-granularity features or multiple outputs, we resort to the perspective of representation learning in which auxiliary tasks are utilized to enable the encoder to jointly learn robust features with the main task of per-pixel classification during optimization.
no code implementations • 18 May 2023 • Bochao Liu, Pengju Wang, Weijia Guo, Yong Li, Liansheng Zhuang, Weiping Wang, Shiming Ge
In this work, we present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network.
1 code implementation • 10 May 2023 • Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang
Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features.
no code implementations • 6 Apr 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
Neural Architectures Search (NAS) becomes more and more popular over these years.
1 code implementation • 11 Feb 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.
no code implementations • 11 Feb 2023 • Xunyu Zhu, Jian Li, Yong liu, Weiping Wang
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.
1 code implementation • ICCV 2023 • Bo Fang, Wenhao Wu, Chang Liu, Yu Zhou, Yuxin Song, Weiping Wang, Xiangbo Shu, Xiangyang Ji, Jingdong Wang
In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation.
1 code implementation • ICCV 2023 • Xiaohua Chen, Yucan Zhou, Dayan Wu, Chule Yang, Bo Li, QinGhua Hu, Weiping Wang
Consequently, we estimate the size of the spanned space for each category, namely effective area, by detailedly analyzing its samples' distribution.
1 code implementation • 2 Nov 2022 • Yifei Zhang, Chang Liu, Yu Zhou, Weiping Wang, Qixiang Ye, Xiangyang Ji
In this paper, we present relation-aware contrastive self-supervised learning (ReCo) to integrate instance relations, i. e., global distribution relation and local interpolation relation, into the CSL framework in a plug-and-play fashion.
1 code implementation • 27 Oct 2022 • Bowen Shen, Zheng Lin, Yuanxin Liu, Zhengxiao Liu, Lei Wang, Weiping Wang
Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.
1 code implementation • 26 Oct 2022 • Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu, Weiping Wang
To this end, we systematically study the design of a training and compression pipeline to search the subnetworks, as well as the assignment of sparsity to different modality-specific modules.
no code implementations • 26 Oct 2022 • Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie zhou
Although these tasks are effective, there are still urging problems: (1) randomly masking speakers regardless of the question cannot map the speaker mentioned in the question to the corresponding speaker in the dialogue, and ignores the speaker-centric nature of utterances.
1 code implementation • 21 Oct 2022 • Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie zhou
We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response.
no code implementations • 17 Oct 2022 • Zexian Yang, Dayan Wu, Wanqian Zhang, Bo Li, Weiping Wang
Specifically, new data collected from new cameras may probably contain an unknown proportion of identities seen before.
1 code implementation • 11 Oct 2022 • Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
In response to the efficiency problem, recent studies show that dense PLMs can be replaced with sparse subnetworks without hurting the performance.
1 code implementation • 10 Oct 2022 • Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
However, these models reveal a trade-off that the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data (which is dominated by the biased samples).
1 code implementation • 10 Oct 2022 • Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
To overcome this limitation, we propose a new dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
no code implementations • 6 Jun 2022 • Yuzhe Li, Yong liu, Bo Li, Weiping Wang, Nan Liu
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
no code implementations • 10 May 2022 • Youhui Guo, Yu Zhou, Xugong Qin, Enze Xie, Weiping Wang
Recent scene text detection methods are almost based on deep learning and data-driven.
1 code implementation • 2 May 2022 • Jiangnan Li, Fandong Meng, Zheng Lin, Rui Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation.
Ranked #1 on
Causal Emotion Entailment
on RECCON
1 code implementation • NAACL 2022 • Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie zhou
Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability.
no code implementations • 22 Apr 2022 • Yilin Kang, Yong liu, Jian Li, Weiping Wang
In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.
no code implementations • 11 Apr 2022 • Yilin Kang, Yong liu, Jian Li, Weiping Wang
To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.
no code implementations • 24 Mar 2022 • Chengyang Fang, Gangyan Zeng, Yu Zhou, Daiqing Wu, Can Ma, Dayong Hu, Weiping Wang
Texts in scene images convey critical information for scene understanding and reasoning.
Optical Character Recognition
Optical Character Recognition (OCR)
+4
1 code implementation • 15 Dec 2021 • Xiaohua Chen, Yucan Zhou, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang
Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.
Ranked #50 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
1 code implementation • 25 Oct 2021 • Wei Wang, Yu Zhou, Jiahao Lv, Dayan Wu, Guoqing Zhao, Ning Jiang, Weiping Wang
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem.
Ranked #5 on
Text Spotting
on SCUT-CTW1500
no code implementations • 16 Sep 2021 • Xiaoni Li, Yu Zhou, Yifei Zhang, Aoting Zhang, Wei Wang, Ning Jiang, Haiying Wu, Weiping Wang
Concretely, these downstream tasks require more accurate representation, in other words, the pixels from the same object must belong to a shared semantic category, which is lacking in the previous methods.
1 code implementation • 9 Sep 2021 • Zhi Qiao, Yu Zhou, Jin Wei, Wei Wang, Yuan Zhang, Ning Jiang, Hongbin Wang, Weiping Wang
In this paper, we propose a Parallel, Iterative and Mimicking Network (PIMNet) to balance accuracy and efficiency.
no code implementations • 8 Sep 2021 • Xugong Qin, Yu Zhou, Youhui Guo, Dayan Wu, Zhihong Tian, Ning Jiang, Hongbin Wang, Weiping Wang
We propose to use an MLP decoder instead of the "deconv-conv" decoder in the mask head, which alleviates the issue and promotes robustness significantly.
no code implementations • 8 Sep 2021 • Youhui Guo, Yu Zhou, Xugong Qin, Weiping Wang
In this paper, we propose a simple yet effective method for accurate arbitrary-shaped nearby scene text detection.
1 code implementation • ACL 2021 • Qingyi Si, Zheng Lin, Ming yu Zheng, Peng Fu, Weiping Wang
Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.
no code implementations • 8 Jul 2021 • Wei Li, Dezhao Luo, Bo Fang, Yu Zhou, Weiping Wang
As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target.
no code implementations • 5 Jul 2021 • Dongbao Yang, Yu Zhou, Weiping Wang
Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data.
no code implementations • 2 Jul 2021 • Xiaoni Li, Yucan Zhou, Yu Zhou, Weiping Wang
Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes.
1 code implementation • ACL 2021 • Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie zhou
In this paper, however, we observe that although distilling the teacher's hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled.
1 code implementation • 8 Jun 2021 • Qingyi Si, Zheng Lin, Mingyu Zheng, Peng Fu, Weiping Wang
Besides, they only explore the interaction between image and question, ignoring the semantics of candidate answers.
1 code implementation • 7 May 2021 • Yifei Zhang, Yu Zhou, Weiping Wang
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting positive sample pairs and repelling negative sample pairs in the embedding space, while neglecting to systematically explore instance relations.
no code implementations • 7 May 2021 • Yilin Kang, Yong liu, Jian Li, Weiping Wang
Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.
no code implementations • 1 Feb 2021 • Shu Zhao, Dayan Wu, Yucan Zhou, Bo Li, Weiping Wang
The proposed gradient amplifier and error-aware quantization loss are compatible with a variety of deep hashing methods.
no code implementations • 27 Jan 2021 • Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
1 code implementation • 29 Dec 2020 • Jiangnan Li, Zheng Lin, Peng Fu, Qingyi Si, Weiping Wang
It can be regarded as a personalized and interactive emotion recognition task, which is supposed to consider not only the semantic information of text but also the influences from speakers.
Ranked #39 on
Emotion Recognition in Conversation
on IEMOCAP
1 code implementation • 3 Dec 2020 • Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang
A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Hongliang Pan, Zheng Lin, Peng Fu, Yatao Qi, Weiping Wang
Inspired by this, we propose a BERT architecture-based model, which concentrates on both intra and inter-modality incongruity for multi-modal sarcasm detection.
1 code implementation • 19 Oct 2020 • Zhi Qiao, Xugong Qin, Yu Zhou, Fei Yang, Weiping Wang
In this paper, we propose Gaussian Constrained Attention Network to deal with this problem.
no code implementations • 16 Oct 2020 • Wei Chen, Weiping Wang, Li Liu, Michael S. Lew
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.
1 code implementation • 15 Oct 2020 • Wei Chen, Yu Liu, Weiping Wang, Tinne Tuytelaars, Erwin M. Bakker, Michael Lew
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
no code implementations • 12 Sep 2020 • Weiping Wang, Ce Xu
In this paper, we study the alternating Euler $T$-sums and $\S$-sums, which are infinite series involving (alternating) odd harmonic numbers, and have similar forms and close relations to the Dirichlet beta functions.
Number Theory
no code implementations • 6 Aug 2020 • Dezhao Luo, Bo Fang, Yu Zhou, Yucan Zhou, Dayan Wu, Weiping Wang
Then a designed sampling strategy is used to model relations for video clips.
no code implementations • 27 Jul 2020 • Dongbao Yang, Yu Zhou, Dayan Wu, Can Ma, Fei Yang, Weiping Wang
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data.
no code implementations • 13 Jul 2020 • Yucan Zhou, Yu Wang, Jianfei Cai, Yu Zhou, QinGhua Hu, Weiping Wang
Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better.
no code implementations • 10 Jul 2020 • Xugong Qin, Yu Zhou, Dayan Wu, Yinliang Yue, Weiping Wang
Accurate detection of multi-oriented text with large variations of scales, orientations, and aspect ratios is of great significance.
1 code implementation • 6 Jul 2020 • Yifei Zhang, Chang Liu, Yu Zhou, Wei Wang, Weiping Wang, Qixiang Ye
In this work, we propose a novel clustering based method, which, by iteratively excluding class inconsistent samples during progressive cluster formation, alleviates the impact of noise samples in a simple-yet-effective manner.
no code implementations • 18 Jun 2020 • Jian Li, Yong liu, Jiankun Liu, Weiping Wang
The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.
no code implementations • 23 May 2020 • Yudi Chen, Wei Wang, Yu Zhou, Fei Yang, Dongbao Yang, Weiping Wang
To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images.
3 code implementations • CVPR 2020 • Zhi Qiao, Yu Zhou, Dongbao Yang, Yucan Zhou, Weiping Wang
Scene text recognition is a hot research topic in computer vision.
no code implementations • 22 Apr 2020 • Rui Liu, Zheng Lin, Weiping Wang
Considering the different characteristics of extractive and generative methods, we propose to divide the keyphrase prediction into two subtasks, i. e., present keyphrase extraction (PKE) and absent keyphrase generation (AKG), to fully exploit their respective advantages.
no code implementations • 9 Mar 2020 • Yong Liu, Lizhong Ding, Weiping Wang
In this paper, we study the statistical properties of kernel $k$-means and obtain a nearly optimal excess clustering risk bound, substantially improving the state-of-art bounds in the existing clustering risk analyses.
no code implementations • 9 Mar 2020 • Yong Liu, Lizhong Ding, Weiping Wang
However, the studies on learning theory for general loss functions and hypothesis spaces remain limited.
no code implementations • 28 Feb 2020 • Jian Li, Yong liu, Weiping Wang
Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.
no code implementations • 20 Feb 2020 • Yilin Kang, Jian Li, Yong liu, Weiping Wang
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).
1 code implementation • 20 Feb 2020 • Yilin Kang, Yong liu, Ben Niu, Xin-Yi Tong, Likun Zhang, Weiping Wang
By adding noise to the original training data and training with the `perturbed data', we achieve ($\epsilon$,$\delta$)-differential privacy on the final model, along with some kind of privacy on the original data.
1 code implementation • 2 Jan 2020 • Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, Weiping Wang
As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning.
Ranked #11 on
Self-supervised Video Retrieval
on HMDB51
no code implementations • IJCNLP 2019 • Yanfu Xu, Zheng Lin, Yuanxin Liu, Rui Liu, Weiping Wang, Dan Meng
Open-domain question answering (OpenQA) aims to answer questions based on a number of unlabeled paragraphs.
no code implementations • 23 Oct 2019 • Yilin Kang, Yong liu, Weiping Wang
By detailed theoretical analysis, we show that in distributed setting, the noise bound and the excess empirical risk bound can be improved by considering different weights held by multiple parties.
1 code implementation • 11 Sep 2019 • Jian Li, Yong liu, Weiping Wang
Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-task learning and transfer learning.
1 code implementation • 11 Sep 2019 • Jian Li, Yong liu, Weiping Wang
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.
no code implementations • 27 Aug 2019 • Xugong Qin, Yu Zhou, Dongbao Yang, Weiping Wang
The performance of the proposed method is comparable with the state-of-the-art methods with only 10% pixel-level annotated data and 90% rectangle-level weakly annotated data.
1 code implementation • 7 Jun 2019 • Jian Li, Yong liu, Weiping Wang
In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.
no code implementations • 13 Feb 2019 • Yong Liu, Jian Li, Guangjun Wu, Lizhong Ding, Weiping Wang
In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).
no code implementations • 19 Dec 2018 • Yong Liu, Jian Li, Weiping Wang
We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.
no code implementations • NeurIPS 2018 • Jian Li, Yong liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang
In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.