1 code implementation • EMNLP 2020 • Abdul Rafae Khan, Jia Xu, Weiwei Sun
Natural Language Processing (NLP) tasks are usually performed word by word on textual inputs.
no code implementations • COLING 2022 • Yu Yu, Shahram Khadivi, Jia Xu
This paper introduces our Diversity Advanced Actor-Critic reinforcement learning (A2C) framework (DAAC) to improve the generalization and accuracy of Natural Language Processing (NLP).
1 code implementation • COLING 2022 • Mengjiao Zhang, Jia Xu
We propose a byte-based multilingual neural machine translation system (BMNMT) to alleviate the representation bottleneck and improve translation performance in endangered languages.
no code implementations • COLING 2022 • Yu Yu, Abdul Rafae Khan, Jia Xu
The quality of Natural Language Processing (NLP) models is typically measured by the accuracy or error rate of a predefined test set.
no code implementations • 18 Feb 2024 • Jia Xu, Mona Diab
Minimizing social bias strengthens societal bonds, promoting shared understanding and better decision-making.
no code implementations • 14 Feb 2024 • Md Kowsher, Jia Xu
In Chaos, a minor divergence between two initial conditions exhibits exponential amplification over time, leading to far-away outcomes, known as the butterfly effect.
no code implementations • 19 Jan 2024 • Yu Yu, Chao-Han Huck Yang, Tuan Dinh, Sungho Ryu, Jari Kolehmainen, Roger Ren, Denis Filimonov, Prashanth G. Shivakumar, Ankur Gandhe, Ariya Rastow, Jia Xu, Ivan Bulyko, Andreas Stolcke
The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware.
1 code implementation • 20 Sep 2023 • Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi
We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.
Ranked #4 on Video Retrieval on MSR-VTT-1kA
1 code implementation • 10 Aug 2023 • Zeyuan Chen, Wei Chen, Jia Xu, Zhongyi Liu, Wei zhang
Drawing inspiration from this, we devise a novel Behavior Augmented Relevance Learning model for Alipay Search (BARL-ASe) that leverages neighbor queries of target item and neighbor items of target query to complement target query-item semantic matching.
no code implementations • 25 Jul 2023 • Shengyue Yao, Jingru Yu, Yi Yu, Jia Xu, Xingyuan Dai, Honghai Li, Fei-Yue Wang, Yilun Lin
Furthermore, an operation algorithm is proposed regarding the issue of structural rigidity in DAO.
no code implementations • 9 May 2023 • Jia Xu, Longbing Cao
Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across multivariate time series by variational long short-term memory networks and regular vine copula.
1 code implementation • 22 Feb 2023 • Deqiang Li, Shicheng Cui, Yun Li, Jia Xu, Fu Xiao, Shouhuai Xu
To promote defense effectiveness, we propose a new mixture of attacks to instantiate PAD to enhance deep neural network-based measurements and malware detectors.
1 code implementation • 22 Feb 2023 • Hongyu Liu, Xintong Han, ChengBin Jin, Lihui Qian, Huawei Wei, Zhe Lin, Faqiang Wang, Haoye Dong, Yibing Song, Jia Xu, Qifeng Chen
In this paper, we propose Human MotionFormer, a hierarchical ViT framework that leverages global and local perceptions to capture large and subtle motion matching, respectively.
1 code implementation • European Journal of Remote Sensing 2023 • Leilei Xu, Peng Yang, Juanjuan Yu, Fei Peng, Jia Xu, Shiran Song &Yongxing Wu
Parcel-level farmland information contains rich spatial distribution and boundary details, which is crucial for digital agriculture and agricultural resource surveys.
no code implementations • 12 Nov 2022 • Firoj Alam, Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Abdul Rafae Khan, Jia Xu
We use an unsupervised method to discover concepts learned in these models and enable a graphical interface for humans to generate explanations for the concepts.
no code implementations • 21 Oct 2022 • Abdul Rafae Khan, Hrishikesh Kanade, Girish Amar Budhrani, Preet Jhanglani, Jia Xu
This paper describes the Stevens Institute of Technology's submission for the WMT 2022 Shared Task: Code-mixed Machine Translation (MixMT).
no code implementations • 4 Aug 2022 • Xuting Tang, Jia Xu, Shusen Wang
To tackle this problem, we propose a special network architecture with a few-shot learning algorithm that allows the number of agents to vary during centralized training.
1 code implementation • NAACL 2022 • Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Firoj Alam, Abdul Rafae Khan, Jia Xu
We propose a novel framework ConceptX, to analyze how latent concepts are encoded in representations learned within pre-trained language models.
no code implementations • ICLR 2022 • Fahim Dalvi, Abdul Rafae Khan, Firoj Alam, Nadir Durrani, Jia Xu, Hassan Sajjad
We address this limitation by discovering and analyzing latent concepts learned in neural network models in an unsupervised fashion and provide interpretations from the model's perspective.
no code implementations • 10 Feb 2022 • Soheil Sadeghi Eshkevari, Xiaocheng Tang, Zhiwei Qin, Jinhan Mei, Cheng Zhang, Qianying Meng, Jia Xu
In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale.
no code implementations • NeurIPS 2021 • Jiangxin Sun, Zihang Lin, Xintong Han, Jian-Fang Hu, Jia Xu, Wei-Shi Zheng
The ability of forecasting future human motion is important for human-machine interaction systems to understand human behaviors and make interaction.
no code implementations • 5 Aug 2021 • Jia Xu, Ziyi Wang, Zulong Chen, Detao Lv, Yao Yu, Chuanfei Xu
All orders in a user itinerary are learned as a whole, based on which the implicit travel intention of each user can be more accurately inferred.
no code implementations • 25 Jun 2021 • Abdul Rafae Khan, Jia Xu, Peter Varsanyi, Rachit Pabreja
Our analysis of the importance of each input feature shows the critical causal impact on decision-making, suggesting that criminal histories are statistically significant factors, while identifiers, such as race and age, are not.
no code implementations • 8 Jun 2021 • Pengpeng Liu, Michael R. Lyu, Irwin King, Jia Xu
Then, a self-supervised learning framework is constructed: confident predictions from teacher models are served as annotations to guide the student model to learn optical flow for those less confident predictions.
1 code implementation • NAACL 2021 • Karine Chubarian, Abdul Rafae Khan, Anastasios Sidiropoulos, Jia Xu
Deep Learning-based NLP systems can be sensitive to unseen tokens and hard to learn with high-dimensional inputs, which critically hinder learning generalization.
1 code implementation • CVPR 2021 • Zhichao Huang, Xintong Han, Jia Xu, Tong Zhang
We present a new method for few-shot human motion transfer that achieves realistic human image generation with only a small number of appearance inputs.
no code implementations • 24 Feb 2021 • Xuejun Li, Tianxiang Chen, Dong Yuan, Jia Xu, Xiao Liu
To achieve better Quality of Service (QoS), for instance, faster response time and lower energy consumption, computation offloading is widely used in the MEC environment.
Edge-computing Distributed, Parallel, and Cluster Computing C.2.4
no code implementations • 9 Oct 2020 • Pengpeng Liu, Xintong Han, Michael Lyu, Irwin King, Jia Xu
We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN).
1 code implementation • CVPR 2020 • Pengpeng Liu, Irwin King, Michael Lyu, Jia Xu
In this paper, we propose a unified method to jointly learn optical flow and stereo matching.
1 code implementation • 31 Mar 2020 • Abdul Rafae Khan, Asim Karim, Hassan Sajjad, Faisal Kamiran, Jia Xu
Roman Urdu is an informal form of the Urdu language written in Roman script, which is widely used in South Asia for online textual content.
no code implementations • 11 Nov 2019 • Abdul Rafae Khan, Jia Xu
We achieve significant and consistent improvements overall language pairs and datasets: French-English, German-English, and Chinese-English in medium task IWSLT'17 and French-English in large task WMT'18 Bio, with up to 4 BLEU points over the state-of-the-art.
no code implementations • 27 Oct 2019 • Jia Xu, Yiming Li, Yong Jiang, Shu-Tao Xia
In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.
1 code implementation • 26 Jul 2019 • Tingguang Li, Weitao Xi, Meng Fang, Jia Xu, Max Qing-Hu Meng
We present a learning-based approach to solving a Rubik's cube with a multi-fingered dexterous hand.
Robotics
1 code implementation • SEMEVAL 2019 • Weimin Lyu, Sheng Huang, Abdul Rafae Khan, Shengqiang Zhang, Weiwei Sun, Jia Xu
This paper describes the systems of the CUNY-PKU team in SemEval 2019 Task 1: Cross-lingual Semantic Parsing with UCCA.
1 code implementation • ICLR 2019 • Meng Fang, Cheng Zhou, Bei Shi, Boqing Gong, Jia Xu, Tong Zhang
Dealing with sparse rewards is one of the most important challenges in reinforcement learning (RL), especially when a goal is dynamic (e. g., to grasp a moving object).
1 code implementation • CVPR 2019 • Pengpeng Liu, Michael Lyu, Irwin King, Jia Xu
We present a self-supervised learning approach for optical flow.
Ranked #7 on Optical Flow Estimation on KITTI 2012
1 code implementation • 25 Feb 2019 • Pengpeng Liu, Irwin King, Michael R. Lyu, Jia Xu
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data.
no code implementations • WS 2018 • Abdul Khan, P, Subhadarshi a, Jia Xu, Lampros Flokas
Furthermore, we applied ensemble learning on training models of intermediate epochs and achieved an improvement of 4. 02 BLEU points over the baseline.
no code implementations • COLING 2018 • Hoang Cuong, Jia Xu
This paper provides an evaluation of a wide range of advanced sentence-level Quality Estimation models, including Support Vector Regression, Ride Regression, Neural Networks, Gaussian Processes, Bayesian Neural Networks, Deep Kernel Learning and Deep Gaussian Processes.
19 code implementations • CVPR 2018 • Chen Chen, Qifeng Chen, Jia Xu, Vladlen Koltun
Imaging in low light is challenging due to low photon count and low SNR.
Ranked #4 on Image Denoising on SID x300
2 code implementations • ICCV 2017 • Qifeng Chen, Jia Xu, Vladlen Koltun
Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action.
no code implementations • CVPR 2017 • Jia Xu, René Ranftl, Vladlen Koltun
We present an optical flow estimation approach that operates on the full four-dimensional cost volume.
no code implementations • 1 Oct 2016 • Jia Xu, Zu-Zhen Huang, Zhi-Rui Wang, Li Xiao, Xiang-Gen Xia, Teng Long
Accordingly, the multichannel SAR systems with different parameters are investigated in three different cases with diverse Doppler ambiguity properties, and a multi-frequency SAR is then proposed to obtain the RV estimation by solving the ambiguity problem based on Chinese remainder theorem (CRT).
no code implementations • CVPR 2015 • Jia Xu, Lopamudra Mukherjee, Yin Li, Jamieson Warner, James M. Rehg, Vikas Singh
Motivated by these applications, this paper focuses on the problem of egocentric video summarization.
no code implementations • CVPR 2015 • Jia Xu, Alexander G. Schwing, Raquel Urtasun
Despite the promising performance of conventional fully supervised algorithms, semantic segmentation has remained an important, yet challenging task.
no code implementations • 18 Jan 2015 • Jia Xu, Geliang Chen
We consider phrase based Language Models (LM), which generalize the commonly used word level models.
no code implementations • 24 Dec 2014 • Jia Xu, Patrick Shironoshita, Ubbo Visser, Nigel John, Mansur Kabuka
Efficiently querying Description Logic (DL) ontologies is becoming a vital task in various data-intensive DL applications.
no code implementations • CVPR 2014 • Jia Xu, Alexander G. Schwing, Raquel Urtasun
We tackle the problem of weakly labeled semantic segmentation, where the only source of annotation are image tags encoding which classes are present in the scene.
no code implementations • CVPR 2013 • Jia Xu, Maxwell D. Collins, Vikas Singh
We study the problem of interactive segmentation and contour completion for multiple objects.
no code implementations • 21 May 2013 • Jia Xu, Patrick Shironoshita, Ubbo Visser, Nigel John, Mansur Kabuka
The extraction of logically-independent fragments out of an ontology ABox can be useful for solving the tractability problem of querying ontologies with large ABoxes.