1 code implementation • EMNLP 2021 • Yunbin Tu, Liang Li, Chenggang Yan, Shengxiang Gao, Zhengtao Yu
In this paper, we propose a Relation-embedded Representation Reconstruction Network (Rˆ3Net) to explicitly distinguish the real change from the large amount of clutter and irrelevant changes.
no code implementations • 6 Sep 2023 • Liang Li, Qingyuan Li, Bo Zhang, Xiangxiang Chu
On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones.
1 code implementation • 31 Aug 2023 • Chengyang Fang, Jiangnan Li, Liang Li, Can Ma, Dayong Hu
To tackle these problems, we propose a novel method named Separate and Locate (SaL) that explores text contextual cues and designs spatial position embedding to construct spatial relations between OCR texts.
no code implementations • 30 Aug 2023 • Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao, Bo Zhang, Xiangxiang Chu, Yerui Sun, Li Du, Yuchen Xie
In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.
no code implementations • 24 Aug 2023 • Jianan Li, Liang Li, Shiyu Zhao
The comprehension of how local interactions arise in global collective behavior is of utmost importance in both biological and physical research.
no code implementations • 20 Jun 2023 • Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
no code implementations • 21 Mar 2023 • Liang Li, Pengfei Zhao
Adaptive network pruning approach has recently drawn significant attention due to its excellent capability to identify the importance and redundancy of layers and filters and customize a suitable pruning solution.
1 code implementation • 6 Mar 2023 • Yunbin Tu, Liang Li, Li Su, Ke Lu, Qingming Huang
Change captioning is to describe the semantic change between a pair of similar images in natural language.
1 code implementation • 10 Feb 2023 • Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Binhua Li, Yongbin Li
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
no code implementations • CVPR 2023 • Yang Wang, Long Peng, Liang Li, Yang Cao, Zheng-Jun Zha
To this end, we inject the addition/difference operation into the convolution process and devise a Contrast Aware (CA) unit and a Detail Aware (DA) unit to facilitate the statistical and structural regularities modeling.
2 code implementations • 16 Dec 2022 • Yue Liu, Xihong Yang, Sihang Zhou, Xinwang Liu, Zhen Wang, Ke Liang, Wenxuan Tu, Liang Li, Jingcan Duan, Cancan Chen
Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.
1 code implementation • CVPR 2023 • Gaoxiang Cong, Liang Li, Yuankai Qi, ZhengJun Zha, Qi Wu, Wenyu Wang, Bin Jiang, Ming-Hsuan Yang, Qingming Huang
Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference.
no code implementations • 3 Dec 2022 • Xiangxiang Chu, Liang Li, Bo Zhang
The tradeoff between performance and inference speed is critical for practical applications.
no code implementations • 27 Nov 2022 • Zhihuang Zhang, Meng Xu, Wenqiang Zhou, Tao Peng, Liang Li, Stefan Poslad
Then a cross-model transformer associates the BEV features and semantic map queries.
no code implementations • COLING 2022 • Liang Li, Ruiying Geng, Bowen Li, Can Ma, Yinliang Yue, Binhua Li, Yongbin Li
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism.
7 code implementations • 7 Sep 2022 • Chuyi Li, Lulu Li, Hongliang Jiang, Kaiheng Weng, Yifei Geng, Liang Li, Zaidan Ke, Qingyuan Li, Meng Cheng, Weiqiang Nie, Yiduo Li, Bo Zhang, Yufei Liang, Linyuan Zhou, Xiaoming Xu, Xiangxiang Chu, Xiaoming Wei, Xiaolin Wei
The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios.
Ranked #15 on
Object Detection
on COCO-O
1 code implementation • 23 Aug 2022 • Feng Xie, Zhong Zhang, Liang Li, Bin Zhou, Yusong Tan
Epidemic forecasting is the key to effective control of epidemic transmission and helps the world mitigate the crisis that threatens public health.
no code implementations • 15 Aug 2022 • Liang Li, Chenpei Huang, Dian Shi, Hao Wang, Xiangwei Zhou, Minglei Shu, Miao Pan
Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i. e., iterative local computing + multi-round communications) of mobile devices in FL.
1 code implementation • 18 Jul 2022 • Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Zechao Li, Qi Tian, Qingming Huang
Second, most previous weakly supervised REG methods ignore the discriminative location and context of the referent, causing difficulties in distinguishing the target from other same-category objects.
no code implementations • 13 Jul 2022 • Shaoru Wang, Zeming Li, Jin Gao, Liang Li, Weiming Hu
However, when facing various resource budgets in real-world applications, it costs a huge computation burden to pretrain multiple networks of various sizes one by one.
no code implementations • 13 Jul 2022 • Junpu Zhang, Liang Li, Siwei Wang, Jiyuan Liu, Yue Liu, Xinwang Liu, En Zhu
As a representative, late fusion MKC first decomposes the kernels into orthogonal partition matrices, then learns a consensus one from them, achieving promising performance recently.
no code implementations • 12 Jul 2022 • Yufan Liu, Jiajiong Cao, Bing Li, Weiming Hu, Jingting Ding, Liang Li
However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN.
no code implementations • 9 Jul 2022 • Liang Li, Baihua Zheng, Weiwei Sun
We introduce structural semantic metrics based on graph adjacency relations during the semantic reconstruction and correlation mining stage and meanwhile align the structure semantics in the hash space with an asymmetric binary optimization process.
1 code implementation • 5 Jul 2022 • Liang Li, Siwei Wang, Xinwang Liu, En Zhu, Li Shen, Kenli Li, Keqin Li
Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels.
1 code implementation • CVPR 2022 • Shaofei Cai, Liang Li, Xinzhe Han, Jiebo Luo, Zheng-Jun Zha, Qingming Huang
However, the currently used graph search space overemphasizes learning node features and neglects mining hierarchical relational information.
Ranked #1 on
Link Prediction
on TSP/HCP Benchmark set
no code implementations • 2 Apr 2022 • Zhenhuan Liu, Jincan Deng, Liang Li, Shaofei Cai, Qianqian Xu, Shuhui Wang, Qingming Huang
Conditional image generation is an active research topic including text2image and image translation.
no code implementations • 2 Apr 2022 • Zhenhuan Liu, Liang Li, Huajie Jiang, Xin Jin, Dandan Tu, Shuhui Wang, Zheng-Jun Zha
Furthermore, we devise the spatio-temporal correlative map as a style-independent, global-aware regularization on the perceptual motion consistency.
1 code implementation • CVPR 2022 • Lizhen Wang, ZhiYuan Chen, Tao Yu, Chenguang Ma, Liang Li, Yebin Liu
In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc.
1 code implementation • CVPR 2022 • Zongyang Ma, Guan Luo, Jin Gao, Liang Li, Yuxin Chen, Shaoru Wang, Congxuan Zhang, Weiming Hu
Open-vocabulary object detection aims to detect novel object categories beyond the training set.
Ranked #17 on
Open Vocabulary Object Detection
on MSCOCO
1 code implementation • CVPR 2022 • Jiayu Xiao, Liang Li, Chaofei Wang, Zheng-Jun Zha, Qingming Huang
A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption.
no code implementations • 3 Mar 2022 • Zhipeng Huang, Jiawei Liu, Liang Li, Kecheng Zheng, Zheng-Jun Zha
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images.
no code implementations • 3 Mar 2022 • Jiawei Liu, Zhipeng Huang, Liang Li, Kecheng Zheng, Zheng-Jun Zha
In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Generalizable Person Re-identification
Representation Learning
2 code implementations • 1 Mar 2022 • Xiang Hu, Haitao Mi, Liang Li, Gerard de Melo
We propose to use a top-down parser as a model-based pruning method, which also enables parallel encoding during inference.
2 code implementations • CVPR 2020 • Jin Gao, Yan Lu, Xiaojuan Qi, Yutong Kou, Bing Li, Liang Li, Shan Yu, Weiming Hu
In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.
1 code implementation • 27 Nov 2021 • Kecheng Zheng, Jiawei Liu, Wei Wu, Liang Li, Zheng-Jun Zha
The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.
Domain Generalization
Generalizable Person Re-identification
1 code implementation • 20 Oct 2021 • Yunbin Tu, Liang Li, Chenggang Yan, Shengxiang Gao, Zhengtao Yu
In this paper, we propose a Relation-embedded Representation Reconstruction Network (R$^3$Net) to explicitly distinguish the real change from the large amount of clutter and irrelevant changes.
no code implementations • 3 Sep 2021 • Shaofei Cai, Liang Li, Xinzhe Han, Zheng-Jun Zha, Qingming Huang
Recently, researchers study neural architecture search (NAS) to reduce the dependence of human expertise and explore better GNN architectures, but they over-emphasize entity features and ignore latent relation information concealed in the edges.
no code implementations • 26 Aug 2021 • Hao Wang, Zheng-Jun Zha, Liang Li, Xuejin Chen, Jiebo Luo
We propose a novel MultiModulation Network (M2N) to learn the above correlation and leverage it as semantic guidance to modulate the related auditory, visual, and fused features.
1 code implementation • ACL 2021 • Liang Li, Can Ma, Yinliang Yue, Dayong Hu
However, it is hard for a vanilla encoder to capture these.
Ranked #1 on
Table-to-Text Generation
on RotoWire
1 code implementation • 13 Jul 2021 • Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, Qi Tian
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.
no code implementations • CVPR 2021 • Hao Wang, Zheng-Jun Zha, Liang Li, Dong Liu, Jiebo Luo
In particular, for cross-modal interaction, we interact the sentence-level query with the whole moment while interact the word-level query with content and boundary, as in a coarse-to-fine manner.
1 code implementation • 26 May 2021 • Xue Jiang, Zhuoran Zheng, Chen Lyu, Liang Li, Lei Lyu
In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks.
no code implementations • 25 May 2021 • Zeheng Wang, Liang Li, Ross C. C. Leon, Jinlin Yang, Junjie Shi, Timothy van der Laan, Muhammad Usman
The inherent flexibility of our approach allows easy adaptation to various tasks, thus making it highly relevant to many applications of the semiconductor industry.
1 code implementation • 20 Apr 2021 • Jianhao Jiao, Huaiyang Huang, Liang Li, Zhijian He, Yilong Zhu, Ming Liu
This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM).
1 code implementation • CVPR 2021 • Shaofei Cai, Liang Li, Jincan Deng, Beichen Zhang, Zheng-Jun Zha, Li Su, Qingming Huang
Inspired by the strong searching capability of neural architecture search (NAS) in CNN, this paper proposes Graph Neural Architecture Search (GNAS) with novel-designed search space.
no code implementations • 9 Feb 2021 • Bing Zhang, Yu Wang, Liang Li
The jet composition and radiative efficiency of GRBs are poorly constrained from the data.
High Energy Astrophysical Phenomena
no code implementations • 18 Jan 2021 • Changlong Hu, Liang Li, Xiaolei Wen, Yuliang Chen, Bowen Li, Hui Ren, Shanguang Zhao, Chongwen Zou
Manipulating the strain induced poly-domains and phase transition in correlated oxide material are important for high performance devices fabrication.
Materials Science Strongly Correlated Electrons
no code implementations • 13 Jan 2021 • Dian Shi, Liang Li, Rui Chen, Pavana Prakash, Miao Pan, Yuguang Fang
The continuous convergence of machine learning algorithms, 5G and beyond (5G+) wireless communications, and artificial intelligence (AI) hardware implementation hastens the birth of federated learning (FL) over 5G+ mobile devices, which pushes AI functions to mobile devices and initiates a new era of on-device AI applications.
no code implementations • 22 Dec 2020 • Liang Li, Dian Shi, Ronghui Hou, Hui Li, Miao Pan, Zhu Han
Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile applications.
no code implementations • 21 Dec 2020 • Rui Chen, Liang Li, Kaiping Xue, Chi Zhang, Miao Pan, Yuguang Fang
To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices.
no code implementations • 15 Oct 2020 • Liang Li, Can Ma, Yinliang Yue, Linjun Shou, Dayong Hu
Secondly, the target texts in training dataset may contain redundant information or facts do not exist in the input tables.
no code implementations • 15 Oct 2020 • Bin-Bin Zhao, Liang Li, Hui-Dong Zhang
Extracting entity pairs along with relation types from unstructured texts is a fundamental subtask of information extraction.
1 code implementation • 10 Oct 2020 • Qikui Zhu, Liang Li, Jiangnan Hao, Yunfei Zha, Yan Zhang, Yanxiang Cheng, Fei Liao, Pingxiang Li
However, not all the feature maps transmitted by those connections contribute positively to the network performance.
no code implementations • 23 Jun 2020 • Xingwen Zheng, Wei Wang, Liang Li, Guangming Xie
Then four typical regression methods, including random forest algorithm, support vector regression, back propagation neural network, and multiple linear regression method are used for establishing regression models between the ALLS-measured HPVs and the relative states.
1 code implementation • 11 May 2020 • Baiming Chen, Mengdi Xu, Zuxin Liu, Liang Li, Ding Zhao
We also test the proposed algorithm in traffic scenarios that require coordination of all autonomous vehicles to show the practical value of delay-awareness.
1 code implementation • 11 May 2020 • Baiming Chen, Mengdi Xu, Liang Li, Ding Zhao
Action delays degrade the performance of reinforcement learning in many real-world systems.
no code implementations • 14 Apr 2020 • Baiming Chen, Xiang Chen, Wu Qiong, Liang Li
Results show that the adversarial scenarios generated by our method significantly degrade the performance of the tested vehicles.
no code implementations • CVPR 2020 • Yukun Huang, Zheng-Jun Zha, Xueyang Fu, Richang Hong, Liang Li
Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e. g., low-resolution, weak illumination, blurring and adverse weather.
no code implementations • 10 Apr 2020 • Chaochao Chen, Liang Li, Wenjing Fang, Jun Zhou, Li Wang, Lei Wang, Shuang Yang, Alex Liu, Hao Wang
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.
1 code implementation • CVPR 2020 • Dechao Meng, Liang Li, Xuejing Liu, Yadong Li, Shijie Yang, Zheng-Jun Zha, Xingyu Gao, Shuhui Wang, Qingming Huang
Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario.
1 code implementation • CVPR 2020 • Beichen Zhang, Liang Li, Shijie Yang, Shuhui Wang, Zheng-Jun Zha, Qingming Huang
In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples.
2 code implementations • CVPR 2020 • Shuhao Cui, Shuhui Wang, Junbao Zhuo, Liang Li, Qingming Huang, Qi Tian
We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix.
no code implementations • 6 Feb 2020 • Chaochao Chen, Liang Li, Bingzhe Wu, Cheng Hong, Li Wang, Jun Zhou
It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems.
no code implementations • 24 Dec 2019 • Yimin Huang, Weiran Huang, Liang Li, Zhenguo Li
In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model's uncertainty to improve the reliability and accuracy of inferences.
no code implementations • 19 Nov 2019 • Ping-Ping Wang, Liang Li, Guang-Hui Cheng
While the sparse regularizer is imposed by a $\ell_{1}$-norm in a discrete cosine transformation (DCT) domain, which can better employ the local sparse property of completed data.
no code implementations • 19 Nov 2019 • Yu-Xuan Li, Jin-Yuan Liu, Liang Li, Xiang Guan
Recurrent neural networks have been widely used in sequence learning tasks.
1 code implementation • 15 Sep 2019 • Ye Yuan, Junlin Li, Liang Li, Frank Jiang, Xiuchuan Tang, Fumin Zhang, Sheng Liu, Jorge Goncalves, Henning U. Voss, Xiuting Li, Jürgen Kurths, Han Ding
The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data.
1 code implementation • 5 Sep 2019 • Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Li Su, Qingming Huang
Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage.
1 code implementation • ICCV 2019 • Xuejing Liu, Liang Li, Shuhui Wang, Zheng-Jun Zha, Dechao Meng, Qingming Huang
It builds the correspondence between image region proposal and query in an adaptive manner: adaptive grounding and collaborative reconstruction.
no code implementations • 12 Mar 2019 • Yaoqi Sun, Liang Li, Liang Zheng, Ji Hu, Yatong Jiang, Chenggang Yan
In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data.
no code implementations • 6 Nov 2018 • Feifan Xu, Fei He, Enze Xie, Liang Li
Ordered binary decision diagrams (OBDDs) are an efficient data structure for representing and manipulating Boolean formulas.
no code implementations • EMNLP 2018 • Changliang Li, Liang Li, Ji Qi
In this work, we propose a novel self-attentive model with gate mechanism to fully utilize the semantic correlation between slot and intent.
no code implementations • 12 Sep 2018 • Yuanzhe Yao, Zeheng Wang, Liang Li, Kun Lu, Runyu Liu, Zhiyuan Liu, Jing Yan
In this work, an ontology-based model for AI-assisted medicine side-effect (SE) prediction is developed, where three main components, including the drug model, the treatment model, and the AI-assisted prediction model, of proposed model are presented.
no code implementations • 4 May 2018 • Weiran Huang, Jungseul Ok, Liang Li, Wei Chen
Each decision has a reward according to the distributions of arms.
1 code implementation • CVPR 2017 • Shijie Yang, Liang Li, Shuhui Wang, Weigang Zhang, Qingming Huang
Deep Auto-Encoder (DAE) has shown its promising power in high-level representation learning.
no code implementations • 9 May 2017 • Liang Li, Pengyu Li, Yifan Liu, Tao Wan, Zengchang Qin
Under our learning policy, the Seq2Seq model can learn mappings gradually with noises.
no code implementations • 29 Jul 2016 • Hanming Zhang, Liang Li, Kai Qiao, Linyuan Wang, Bin Yan, Lei LI, Guoen Hu
The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography.
no code implementations • CVPR 2013 • Liang Li, Wei Feng, Liang Wan, Jiawan Zhang
For this purpose, we aim at constructing maximum cohesive SP-grid, which is composed of real nodes, i. e. SPs, and dummy nodes that are meaningless in the image with only position-taking function in the grid.