no code implementations • 2 Apr 2025 • Zaipeng Duan, Xuzhong Hu, Pei An, Jie Ma
Therefore, we introduce a spatial difference-driven adaptive filtering module that selectively extracts valuable pseudo points from these virtual points based on density and distance, enhancing the density of medium-range targets.
1 code implementation • 1 Apr 2025 • Jie Ma, Zhitao Gao, Qi Chai, Jun Liu, Pinghui Wang, Jing Tao, Zhou Su
The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+4
no code implementations • 25 Mar 2025 • Xiaohui Sun, Jiangwei Mo, Hanlin Wu, Jie Ma
In the first stage, we pretrain a residual autoencoder to encode the differential information between high-resolution (HR) and low-resolution (LR) images, transitioning the diffusion process into a latent space to reduce computational costs.
no code implementations • 12 Mar 2025 • Xuzhong Hu, Zaipeng Duan, Pei An, Jun Zhang, Jie Ma
The output voxel features are injected into the BEV space to compensate for the loss of 3D details caused by height compression.
no code implementations • 11 Mar 2025 • Mingyue Cheng, Yucong Luo, Jie Ouyang, Qi Liu, Huijie Liu, Li Li, Shuo Yu, Bohou Zhang, Jiawei Cao, Jie Ma, Daoyu Wang
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models.
1 code implementation • 28 Feb 2025 • Chenxu Dang, Zaipeng Duan, Pei An, Xinmin Zhang, Xuzhong Hu, Jie Ma
However, indiscriminate sampling and fusion often overlook the varying contributions of individual points and lead to exponentially increased complexity as the number of input frames grows.
no code implementations • 9 Feb 2025 • Yuchen Zhang, Pinjun Zheng, Jie Ma, Henk Wymeersch, Tareq Y. Al-Naffouri
We investigate a multi-low Earth orbit (LEO) satellite system that simultaneously provides positioning and communication services to terrestrial user terminals.
no code implementations • 21 Nov 2024 • Jie Ma, Pinjun Zheng, Xing Liu, Yuchen Zhang, Tareq Y. Al-Naffouri
Low Earth orbit (LEO) satellites, as a prominent technology in the 6G non-terrestrial network, offer both positioning and communication capabilities.
no code implementations • 30 Oct 2024 • Hanlin Wu, Jiangwei Mo, Xiaohui Sun, Jie Ma
In the second stage, a conditional diffusion model is learned within the latent space to predict the true differential prior encoding.
no code implementations • 16 Oct 2024 • Yuxuan Cheng, Chenxi Shao, Jie Ma, Guoliang Li
Although weak-to-strong consistency is a prevalent method in semi-supervised image segmentation, there is a scarcity of research on perturbation strategies specifically tailored for semi-supervised medical image segmentation tasks.
no code implementations • 11 Oct 2024 • Qin Liu, Chao Shang, Ling Liu, Nikolaos Pappas, Jie Ma, Neha Anna John, Srikanth Doss, Lluis Marquez, Miguel Ballesteros, Yassine Benajiba
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone.
1 code implementation • 10 Oct 2024 • Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, Jie Ma, Miguel Ballesteros, William Yang Wang
Moreover, creating realistic MIA evaluation benchmarks is difficult as training and test data distributions are often unknown.
no code implementations • 8 Oct 2024 • Yang Li, Jie Ma, Miguel Ballesteros, Yassine Benajiba, Graham Horwood
Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones.
1 code implementation • 5 Sep 2024 • Jie Ma, Zhitao Gao, Qi Chai, Wangchun Sun, Pinghui Wang, Hongbin Pei, Jing Tao, Lingyun Song, Jun Liu, Chen Zhang, Lizhen Cui
Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.
1 code implementation • 3 Sep 2024 • Muye Huang, Han Lai, Xinyu Zhang, Wenjun Wu, Jie Ma, Lingling Zhang, Jun Liu
Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension.
1 code implementation • 16 Aug 2024 • Xinyu Xiong, Zihuang Wu, Shuangyi Tan, Wenxue Li, Feilong Tang, Ying Chen, Siying Li, Jie Ma, Guanbin Li
Image segmentation plays an important role in vision understanding.
Ranked #1 on
Image Segmentation
on PMD
2 code implementations • CVPR 2024 • Duojun Huang, Xinyu Xiong, Jie Ma, Jichang Li, Zequn Jie, Lin Ma, Guanbin Li
In this paper, we propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context through reinforcement learning.
1 code implementation • 28 May 2024 • Yizhi Wang, Minjia Chen, Chunhui Yao, Jie Ma, Ting Yan, Richard Penty, Qixiang Cheng
However, the training of PNN is known to be challenging, where the device-to-device and system-to-system variations create imperfect knowledge of the PNN.
1 code implementation • 26 May 2024 • Shutong Chen, Tianyi Zhou, Guodong Long, Jie Ma, Jing Jiang, Chengqi Zhang
For every mid-level, it learns multiple models each assigned to a subgroup of clients, as clustered FL.
1 code implementation • 21 May 2024 • Xiaofei Yu, Yitong Li, Jie Ma
In training process, we construct a noise predictor conditioned on cross modal features to learn the distribution from the real caption distribution to the standard Gaussian distribution under the Markov chain.
no code implementations • 30 Apr 2024 • Robert Vacareanu, Anurag Pratik, Evangelia Spiliopoulou, Zheng Qi, Giovanni Paolini, Neha Anna John, Jie Ma, Yassine Benajiba, Miguel Ballesteros
Many of the recent capabilities demonstrated by Large Language Models (LLMs) arise primarily from their ability to exploit contextual information.
1 code implementation • 18 Apr 2024 • Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, Youtian Du
The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+4
no code implementations • 10 Aug 2023 • Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, Jie Ma, Patrick Ng, Zhiguo Wang, Bonan Min, William Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang
We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data.
no code implementations • 21 Jul 2023 • Jie Ma, Pinghui Wang, Dechen Kong, Zewei Wang, Jun Liu, Hongbin Pei, Junzhou Zhao
Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives.
no code implementations • 27 May 2023 • Sijia Wang, Alexander Hanbo Li, Henry Zhu, Sheng Zhang, Chung-Wei Hang, Pramuditha Perera, Jie Ma, William Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng
Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables.
no code implementations • 22 May 2023 • Karthikeyan K, Yogarshi Vyas, Jie Ma, Giovanni Paolini, Neha Anna John, Shuai Wang, Yassine Benajiba, Vittorio Castelli, Dan Roth, Miguel Ballesteros
We experiment with 6 diverse datasets and show that PLM consistently performs better than most other approaches (0. 5 - 2. 5 F1), including in novel settings for taxonomy expansion not considered in prior work.
1 code implementation • 20 May 2023 • Mengze Xu, Jie Ma, Yuanyuan Zhu
In our work, we introduce conditional denoising diffusion probabilistic models (DDPM) from two aspects: kernel estimation progress and re-construction progress, named as the dual-diffusion.
1 code implementation • 18 May 2023 • Yitong Li, Chang Liu, Jie Ma
Weakly supervised learning based on scribble annotations in target extraction of remote sensing images has drawn much interest due to scribbles' flexibility in denoting winding objects and low cost of manually labeling.
no code implementations • 18 May 2023 • Sharon Levy, Neha Anna John, Ling Liu, Yogarshi Vyas, Jie Ma, Yoshinari Fujinuma, Miguel Ballesteros, Vittorio Castelli, Dan Roth
As a result, it is critical to examine biases within each language and attribute.
1 code implementation • 10 May 2023 • Lingfeng He, Mengze Xu, Jie Ma
ROI extraction is an active but challenging task in remote sensing because of the complicated landform, the complex boundaries and the requirement of annotations.
1 code implementation • 6 May 2023 • Jie Ma, Pinghui Wang, Zewei Wang, Dechen Kong, Min Hu, Ting Han, Jun Liu
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering).
Extractive Question-Answering
Machine Reading Comprehension
+2
no code implementations • 21 Mar 2023 • Ming Shen, Jie Ma, Shuai Wang, Yogarshi Vyas, Kalpit Dixit, Miguel Ballesteros, Yassine Benajiba
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews.
no code implementations • 15 Mar 2023 • Likun Tang, Jie Ma, Yongming Li
Machine learning-based processing of data collected from the human with movement disorders using wearable sensors is an effective method currently available for health monitoring.
no code implementations • ICCV 2023 • Jie Ma, Chuan Wang, Yang Liu, Liang Lin, Guanbin Li
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks.
no code implementations • 20 Nov 2022 • Xuzhong Hu, Zaipeng Duan, Jie Ma
For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data.
no code implementations • 25 Oct 2022 • Chuanyan Zhou, Jie Ma, Fan Li, Yongming Li, Pin Wang, Xiaoheng Zhang
Second, an embedded stack autoencoder (ESAE) is proposed and trained in each layer of sample space to consider the original samples during training and in the network structure, thereby better finding the relationship between original feature samples and deep feature samples.
2 code implementations • 21 Sep 2022 • Yue Tan, Guodong Long, Jie Ma, Lu Liu, Tianyi Zhou, Jing Jiang
To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch.
1 code implementation • Findings (ACL) 2022 • Jie Ma, Miguel Ballesteros, Srikanth Doss, Rishita Anubhai, Sunil Mallya, Yaser Al-Onaizan, Dan Roth
We study the problem of few shot learning for named entity recognition.
no code implementations • 11 Mar 2022 • Jie Ma, Yalong Bai, Bineng Zhong, Wei zhang, Ting Yao, Tao Mei
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions.
1 code implementation • 13 Feb 2022 • Jie Ma, Guodong Long, Tianyi Zhou, Jing Jiang, Chengqi Zhang
Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL).
no code implementations • ICLR 2022 • Yijun Yang, Jing Jiang, Tianyi Zhou, Jie Ma, Yuhui Shi
Model-based offline RL instead trains an environment model using a dataset of pre-collected experiences so online RL methods can learn in an offline manner by solely interacting with the model.
no code implementations • CVPR 2021 • Yuxing Tang, Zhenjie Cao, Yanbo Zhang, Zhicheng Yang, Zongcheng Ji, Yiwei Wang, Mei Han, Jie Ma, Jing Xiao, Peng Chang
Starting with a fully supervised model trained on the data with pixel-level masks, the proposed framework iteratively refines the model itself using the entire weakly labeled data (image-level soft label) in a self-training fashion.
no code implementations • 12 Jun 2021 • Yujiao Wu, Jie Ma, Xiaoshui Huang, Sai Ho Ling, Steven Weidong Su
To improve the survival prediction accuracy and help prognostic decision-making in clinical practice for medical experts, we for the first time propose a multimodal deep learning method for non-small cell lung cancer (NSCLC) survival analysis, named DeepMMSA.
no code implementations • 8 Feb 2021 • Binlong Li, Jie Ma, Bo Ning
Many years ago, Erd\H{o}s, Faudree, Schelp and Simonovits proposed the study of the function $\phi(n, d, k)$, and conjectured that for any positive integers $n>d\geq k$, it holds that $\phi(n, d, k)\leq \lfloor\frac{k-1}{2}\rfloor\lfloor\frac{n}{d+1}\rfloor+\epsilon$, where $\epsilon=1$ if $k$ is odd and $\epsilon=2$ otherwise.
Combinatorics
2 code implementations • ICLR 2021 • Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos santos, Bing Xiang, Stefano Soatto
We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking.
Ranked #3 on
Relation Classification
on TACRED
no code implementations • 11 Jan 2021 • Jialin He, Jie Ma, Lilu Zhao
al. Our second result considers infinitely many pairs $(m, f)$ of special forms, whose exact values of $\sigma(m, f)$ were conjectured by Erd\H{o}s et.
Combinatorics
no code implementations • ICCV 2021 • Bingli Wu, Jie Ma, Gaojie Chen, Pei An
Point cloud registration is the process of using the common structures in two point clouds to splice them together.
no code implementations • COLING 2020 • Yipeng Yu, Ran Guan, Jie Ma, Zhuoxuan Jiang, Jingchang Huang
In online customer service applications, multiple chatbots that are specialized in various topics are typically developed separately and are then merged with other human agents to a single platform, presenting to the users with a unified interface.
1 code implementation • 25 Nov 2020 • Jie Ma, Qi Chai, Jun Liu, Qingyu Yin, Pinghui Wang, Qinghua Zheng
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
no code implementations • EMNLP 2020 • Kasturi Bhattacharjee, Miguel Ballesteros, Rishita Anubhai, Smaranda Muresan, Jie Ma, Faisal Ladhak, Yaser Al-Onaizan
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general representations that can then be further fine-tuned for downstream tasks to much success.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Jie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros, Yaser Al-Onaizan
(2) Capturing the long-range dependency, specifically, the connection between an event trigger and a distant event argument.
no code implementations • 27 Jun 2020 • Qian Li, Qingyuan Hu, Yong Qi, Saiyu Qi, Jie Ma, Jian Zhang
SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples.
no code implementations • EMNLP 2020 • Miguel Ballesteros, Rishita Anubhai, Shuai Wang, Nima Pourdamghani, Yogarshi Vyas, Jie Ma, Parminder Bhatia, Kathleen McKeown, Yaser Al-Onaizan
In this paper, we propose a neural architecture and a set of training methods for ordering events by predicting temporal relations.
no code implementations • 2 Dec 2019 • Jialin He, Jie Ma, Tianchi Yang
A longstanding conjecture of Erd\H{o}s and Simonovits states that every $n$-vertex graph with $ex(n, C_4)+1$ edges contains at least $(1+o(1))\sqrt{n}$ 4-cycles.
Combinatorics
no code implementations • 25 Sep 2019 • Yufei Li, Xiangyu Zhou, Jie Ma, Yu Long, Xuan Wang, Chen Li
Coreference resolution is an important task for gaining more complete understanding about texts by artificial intelligence.
no code implementations • WS 2019 • Zhuoxuan Jiang, Xian-Ling Mao, Ziming Huang, Jie Ma, Shaochun Li
Learning an efficient manager of dialogue agent from data with little manual intervention is important, especially for goal-oriented dialogues.
no code implementations • 21 Jan 2018 • Liang Shen, Zihan Yue, Quan Chen, Fan Feng, Jie Ma
On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil.
no code implementations • 7 Nov 2017 • Liang Shen, Zihan Yue, Fan Feng, Quan Chen, Shihao Liu, Jie Ma
In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed.