no code implementations • Findings (EMNLP) 2021 • Guimin Hu, Guangming Lu, Yi Zhao
Moreover, we quantify the effect of context on emotion cause extraction and provide the visualization of the interactions between candidate cause clauses and contexts.
Ranked #3 on
Emotion Cause Extraction
on ECE
1 code implementation • 28 Jul 2024 • Shuang Wu, Songlin Tang, Guangming Lu, Jianzhuang Liu, Wenjie Pei
In this work we design a Unified Voxelization framework for explicit learning of scene representations, dubbed UniVoxel, which allows for efficient modeling of the geometry, materials and illumination jointly, thereby accelerating the inverse rendering significantly.
1 code implementation • 28 Jul 2024 • Jingjing Wu, Zhengyao Fang, Pengyuan Lyu, Chengquan Zhang, Fanglin Chen, Guangming Lu, Wenjie Pei
In this work, we formulate this challenging problem as a Weakly Supervised Cross-modality Contrastive Learning problem, and design a simple yet effective model dubbed WeCromCL that is able to detect each transcription in a scene image in a weakly supervised manner.
1 code implementation • CVPR 2024 • Jiapeng Su, Qi Fan, Guangming Lu, Fanglin Chen, Wenjie Pei
Instead, our key idea is to adapt a small adapter for rectifying diverse target domain styles to the source domain.
1 code implementation • 23 Jan 2024 • Feng Lin, Hanling Yi, Hongbin Li, Yifan Yang, Xiaotian Yu, Guangming Lu, Rong Xiao
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency.
no code implementations • 15 Jan 2024 • Yihan Cao, Xu Chen, Lun Du, Hao Chen, Qiang Fu, Shi Han, Yushu Du, Yanbin Kang, Guangming Lu, Zi Li
Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation.
no code implementations • 1 Jan 2024 • Wenjie Pei, Weina Xu, Zongze Wu, Weichao Li, Jinfan Wang, Guangming Lu, Xiangrong Wang
In this work, we propose the Saliency-Aware Regularized Graph Neural Network (SAR-GNN) for graph classification, which consists of two core modules: 1) a traditional graph neural network serving as the backbone for learning node features and 2) the Graph Neural Memory designed to distill a compact graph representation from node features of the backbone.
no code implementations • 19 Dec 2023 • Hao Chen, Lun Du, Yuxuan Lu, Qiang Fu, Xu Chen, Shi Han, Yanbin Kang, Guangming Lu, Zi Li
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions.
no code implementations • 17 Dec 2023 • Jingwen Zhang, Zikun Zhou, Guangming Lu, Jiandong Tian, Wenjie Pei
Considering that, we propose to construct a synthetic target representation composed of dense and complete point clouds depicting the target shape precisely by shape completion for robust 3D tracking.
1 code implementation • 16 Dec 2023 • Wenjie Pei, Tongqi Xia, Fanglin Chen, Jinsong Li, Jiandong Tian, Guangming Lu
Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an input image as a flattened sequence of token embeddings and then learns a set of unordered parameterized tokens prefixed to the sequence representation as the visual prompts for task adaptation of large vision models.
1 code implementation • 3 Dec 2023 • Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian
In particular, we devise the anisotropic Deformable Spatio-Temporal Attention module as the core component of D$^2$ST-Adapter, which can be tailored with anisotropic sampling densities along spatial and temporal domains to learn spatial and temporal features specifically in corresponding pathways, allowing our D$^2$ST-Adapter to encode features in a global view in 3D spatio-temporal space while maintaining a lightweight design.
1 code implementation • 13 Sep 2023 • Xianghao Zhan, Qinmei Xu, Yuanning Zheng, Guangming Lu, Olivier Gevaert
This method capitalizes on a small set of accurately labeled training data and leverages ICP-calculated reliability metrics to rectify mislabeled data and outliers within vast quantities of noisy training data.
1 code implementation • ICCV 2023 • Xin Feng, Yifeng Xu, Guangming Lu, Wenjie Pei
Detecting corrupted regions by learning the contrastive distinctions rather than the semantic patterns of corruptions, our model has well generalization ability across different corruption patterns.
no code implementations • 9 Aug 2023 • Songlin Tang, Wenjie Pei, Xin Tao, Tanghui Jia, Guangming Lu, Yu-Wing Tai
Existing methods for interactive segmentation in radiance fields entail scene-specific optimization and thus cannot generalize across different scenes, which greatly limits their applicability.
1 code implementation • 6 Aug 2023 • Zhenhua Ning, Zhuotao Tian, Guangming Lu, Wenjie Pei
Although extensive research has been conducted on 3D point cloud segmentation, effectively adapting generic models to novel categories remains a formidable challenge.
1 code implementation • Signal Processing: Image Communication 2023 • Le Zhang, Yao Lu, Tong Li, Guangming Lu
Thus, the security and quality of stego and revealed secret images still have much room for promotion, especially for large-capacity image steganography.
1 code implementation • 1 Jun 2023 • Hong-Yu Zhou, Yizhou Yu, Chengdi Wang, Shu Zhang, Yuanxu Gao, Jia Pan, Jun Shao, Guangming Lu, Kang Zhang, Weimin Li
During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results.
1 code implementation • 24 Feb 2023 • Guimin Hu, Yi Zhao, Guangming Lu
Emotion-cause pair extraction (ECPE) task aims to extract all the pairs of emotions and their causes from an unannotated emotion text.
Ranked #1000000000 on
Emotion-Cause Pair Extraction
on ECPE
1 code implementation • Neural Computing and Applications 2023 • Le Zhang, Yao Lu, Jinxing Li, Fanglin Chen, Guangming Lu, David Zhang
Image hiding secures information security in multimedia communication.
1 code implementation • 19 Dec 2022 • Feng Lin, Wenze Hu, YaoWei Wang, Yonghong Tian, Guangming Lu, Fanglin Chen, Yong Xu, Xiaoyu Wang
In this study, our focus is on a specific challenge: the large-scale, multi-domain universal object detection problem, which contributes to the broader goal of achieving a universal vision system.
no code implementations • 2 Dec 2022 • Dianwen Mei, Wei Zhuo, Jiandong Tian, Guangming Lu, Wenjie Pei
To circumvent these two challenges, we propose to activate the discriminability of novel classes explicitly in both the feature encoding stage and the prediction stage for segmentation.
no code implementations • 27 Nov 2022 • Jiatong Zhang, Zengwei Yao, Fanglin Chen, Guangming Lu, Wenjie Pei
Second, instead of only performing local self-attention within local windows as Swin Transformer does, the proposed SALG performs both 1) local intra-region self-attention for learning fine-grained features within each region and 2) global inter-region feature propagation for modeling global dependencies among all regions.
Ranked #931 on
Image Classification
on ImageNet
1 code implementation • 21 Nov 2022 • Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, Yongbin Li
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.
Ranked #2 on
Multimodal Sentiment Analysis
on CMU-MOSI
no code implementations • 22 Oct 2022 • Feifan Li, Lun Du, Qiang Fu, Shi Han, Yushu Du, Guangming Lu, Zi Li
Furthermore, based on the dynamic user intent representations, we propose a meta predictor to perform differentiated user engagement forecasting.
1 code implementation • CVPR 2022 • Xinyu Lin, Jinxing Li, Zeyu Ma, Huafeng Li, Shuang Li, Kaixiong Xu, Guangming Lu, David Zhang
Based on our constructed dataset, we prove that with the increase of frames in a tracklet, the performance does meet more enhancement, demonstrating the significance of video-to-video matching in RGB-IR person Re-ID.
no code implementations • 25 Jul 2022 • Wenjie Pei, Shuang Wu, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu
In this work we design a novel knowledge distillation framework to guide the learning of the object detector and thereby restrain the overfitting in both the pre-training stage on base classes and fine-tuning stage on novel classes.
no code implementations • 25 Jul 2022 • Fengjun Li, Xin Feng, Fanglin Chen, Guangming Lu, Wenjie Pei
The real-world degradations can be beyond the simulation scope by the handcrafted degradations, which are referred to as novel degradations.
1 code implementation • 22 Jul 2022 • Shuang Wu, Wenjie Pei, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy.
1 code implementation • 20 Jul 2022 • Wenjie Pei, Xin Feng, Canmiao Fu, Qiong Cao, Guangming Lu, Yu-Wing Tai
The key challenge of sequence representation learning is to capture the long-range temporal dependencies.
1 code implementation • 16 Jul 2022 • Xin Feng, Haobo Ji, Wenjie Pei, Fanglin Chen, Guangming Lu
While the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e. g., 4K) images remains an extremely challenging task due to the explosion of computational complexity and memory usage, as well as the deficiency of annotated data.
1 code implementation • 15 Jul 2022 • Jingjing Wu, Pengyuan Lyu, Guangming Lu, Chengquan Zhang, Wenjie Pei
Typical text spotters follow the two-stage spotting paradigm which detects the boundary for a text instance first and then performs text recognition within the detected regions.
Ranked #5 on
Text Spotting
on ICDAR 2015
no code implementations • 4 Jul 2022 • Canran Li, Dongnan Liu, Haoran Li, Zheng Zhang, Guangming Lu, Xiaojun Chang, Weidong Cai
In this work, we propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification.
1 code implementation • 21 Mar 2022 • Xiaotian Yu, Yifan Yang, Aibo Wang, Ling Xing, Hanling Yi, Guangming Lu, Xiaoyu Wang
Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management.
no code implementations • 4 Dec 2021 • Haobo Ji, Xin Feng, Wenjie Pei, Jinxing Li, Guangming Lu
While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration.
Ranked #20 on
Image Dehazing
on SOTS Indoor
no code implementations • 17 Nov 2021 • Zebin Lin, Wenjie Pei, Fanglin Chen, David Zhang, Guangming Lu
Instead of learning each of these diverse pedestrian appearance features individually as most existing methods do, we propose to perform contrastive learning to guide the feature learning in such a way that the semantic distance between pedestrians with different appearances in the learned feature space is minimized to eliminate the appearance diversities, whilst the distance between pedestrians and background is maximized.
Ranked #1 on
Pedestrian Detection
on TJU-Ped-campus
no code implementations • 10 Oct 2021 • Zengwei Yao, Wenjie Pei, Fanglin Chen, Guangming Lu, David Zhang
Existing methods for speech separation either transform the speech signals into frequency domain to perform separation or seek to learn a separable embedding space by constructing a latent domain based on convolutional filters.
Ranked #8 on
Speech Separation
on WHAMR!
no code implementations • 1 Oct 2021 • Xin Feng, Wenjie Pei, Fengjun Li, Fanglin Chen, David Zhang, Guangming Lu
Most existing methods for image inpainting focus on learning the intra-image priors from the known regions of the current input image to infer the content of the corrupted regions in the same image.
1 code implementation • 12 Jul 2021 • Bingzhi Chen, Yishu Liu, Zheng Zhang, Guangming Lu, Adams Wai Kin Kong
Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry.
1 code implementation • 26 Jun 2021 • Huafeng Li, Kaixiong Xu, Jinxing Li, Guangming Lu, Yong Xu, Zhengtao Yu, David Zhang
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set.
1 code implementation • 12 Jun 2021 • Ailiang Lin, Bingzhi Chen, Jiayu Xu, Zheng Zhang, Guangming Lu
To alleviate these problems, we propose a novel deep medical image segmentation framework called Dual Swin Transformer U-Net (DS-TransUNet), which might be the first attempt to concurrently incorporate the advantages of hierarchical Swin Transformer into both encoder and decoder of the standard U-shaped architecture to enhance the semantic segmentation quality of varying medical images.
1 code implementation • CVPR 2021 • Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu
However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure problem but seldom studied in hashing-based retrieval field.
1 code implementation • 9 Oct 2020 • Xin Feng, Wenjie Pei, Zihui Jia, Fanglin Chen, David Zhang, Guangming Lu
In this work we present the Deep-Masking Generative Network (DMGN), which is a unified framework for background restoration from the superimposed images and is able to cope with different types of noise.
1 code implementation • NeurIPS 2020 • Fanxu Meng, Hao Cheng, Ke Li, Huixiang Luo, Xiaowei Guo, Guangming Lu, Xing Sun
Through extensive experiments, we demonstrate that SWP is more effective compared to the previous FP-based methods and achieves the state-of-art pruning ratio on CIFAR-10 and ImageNet datasets without obvious accuracy drop.
1 code implementation • 26 Apr 2020 • Hao Cheng, Fanxu Meng, Ke Li, Yuting Gao, Guangming Lu, Xing Sun, Rongrong Ji
To gain a universal improvement on both valid and invalid filters, we compensate grafting with distillation (\textbf{Cultivation}) to overcome the drawback of grafting .
1 code implementation • 25 Jan 2018 • Jinxing Li, Bob Zhang, Guangming Lu, David Zhang
The deep hash functions are then learned through two networks by minimizing the gap between the learned features and discrete codes.