检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yang, Chen Wang, Kailing Wang, Yuehao Yang, Xiaokang Shen, Wei MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Dept. of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Reconstructing deformable tissues from endoscopic stereo videos in robotic surgery is crucial for various clinical applications. However, existing methods relying only on implicit representations are computationally expensive and require dozens of hours, which limits further practical applications. To address this challenge, we introduce LerPlane, a novel method for fast and accurate reconstruction of surgical scenes under a single-viewpoint setting. LerPlane treats surgical procedures as 4D volumes and factorizes them into explicit 2D planes of static and dynamic fields, leading to a compact memory footprint and significantly accelerated optimization. The efficient factorization is accomplished by fusing features obtained through linear interpolation of each plane and enables using lightweight neural networks to model surgical scenes. Besides, LerPlane shares static fields, significantly reducing the workload of dynamic tissue modeling. We also propose a novel sample scheme to boost optimization and improve performance in regions with tool occlusion and large motions. Experiments on DaVinci robotic surgery videos demonstrate that LerPlane accelerates optimization by over 100× while maintaining high quality across various non-rigid deformations, showing significant promise for future intraoperative surgery applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

ATTENTION-CONSTRaiNED INFERENCE FOR ROBUST DECODER-ONLY TEXT-TO-SPEECH

arXiv

引用

arXiv 2024年

作者： Wang, Hankun Du, Chenpeng Guo, Yiwei Wang, Shuai Chen, Xie Yu, Kai MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and repeating due to the lack of explicit monotonic alignment constraints. In this paper, we notice from the attention maps that some particular attention heads of the decoder-only model indicate the alignments between speech and text. We call the attention maps of those heads Alignment-Emerged Attention Maps (AEAMs). Based on this discovery, we propose a novel inference method without altering the training process, named Attention-Constrained Inference (ACI), to facilitate monotonic synthesis. It first identifies AEAMs using the Attention Sweeping algorithm and then applies constraining masks on AEAMs. Our experimental results on decoder-only TTS model VALL-E show that the WER of synthesized speech is reduced by up to 20.5% relatively with ACI while the naturalness and speaker similarity are comparable. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

D4: a Chinese Dialogue Dataset for dep.ession-Diagnosis-Oriented Chat

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Orie...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Yao, Binwei Shi, Chao Zou, Likai Dai, Lingfeng Wu, Mengyue Chen, Lu Wang, Zhen Yu, Kai SJTU X-LANCE Lab Department of Computer Science and Engineering China MoE Key Lab of Artificial Intelligence SJTU AI Institute China Shanghai Jiao Tong University Shanghai China Shanghai Mental Health Center China Shanghai Jiao Tong University School of Medicine Shanghai China

In a dep.ession-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria. Such a dialogue system is distinguished from existing single-purpose human-machine dialog systems, as it combines task-oriented and chit-chats with uniqueness in dialogue topics and procedures. However, due to the social stigma associated with mental illness, the dialogue data related to dep.ession consultation and diagnosis are rarely disclosed. Based on clinical dep.ession diagnostic criteria ICD-11 and DSM-5, we designed a 3-phase procedure to construct D4: a Chinese Dialogue Dataset for dep.ession-Diagnosis-Oriented Chat, which simulates the dialogue between doctors and patients during the diagnosis of dep.ession, including diagnosis results and symptom summary given by professional psychiatrists for each conversation. Upon the newly-constructed dataset, four tasks mirroring the dep.ession diagnosis process are established: response generation, topic prediction, dialog summary, and severity classification of dep.essive episode and suicide risk. Multiscale evaluation results demonstrate that a more empathy-driven and diagnostic-accurate consultation dialogue system trained on our dataset can be achieved compared to rule-based bots. © 2022 Association for Computational Linguistics.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Attention-Constrained Inference For Robust Decoder-Only Text-to-Speech

Attention-Constrained Inference For Robust Decoder-Only Text...

引用

IEEE Spoken Language Technology Workshop

作者： Hankun Wang Chenpeng Du Yiwei Guo Shuai Wang Xie Chen Kai Yu Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Recent popular decoder-only text-to-speech models are known for their ability of generating natural-sounding speech. However, such models sometimes suffer from word skipping and repeating due to the lack of explicit monotonic alignment constraints. In this paper, we notice from the attention maps that some particular attention heads of the decoder-only model indicate the alignments between speech and text. We call the attention maps of those heads Alignment-Emerged Attention Maps (AEAMs). Based on this discovery, we propose a novel inference method without altering the training process, named Attention-Constrained Inference (ACI), to facilitate monotonic synthesis. It first identifies AEAMs using the Attention Sweeping algorithm and then applies constraining masks on AEAMs. Our experimental results on decoderonly TTS model VALL-E show that the WER of synthesized speech is reduced by up to 20.5% relatively with ACI while the naturalness and speaker similarity are comparable.

关键词： Training Conferences Robustness Inference algorithms Text to speech Optimization

来源：评论

学校读者我要写书评

暂无评论

BézierPalm: A Free Lunch for Palmprint Recognition 1

引用

17th European Conference on computer Vision, ECCV 2022

作者： Zhao, Kai Shen, Lei Zhang, Yingyi Zhou, Chuhan Wang, Tao Zhang, Ruixin Ding, Shouhong Jia, Wei Shen, Wei Tencent Youtu Lab Shanghai China University of California Los Angeles Los Angeles United States School of Computer Science and Information Engineering Hefei University of Technology Hefei United States MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031197789

ISBN: (纸本)9783031197772

Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases. Concretely, we introduce an intuitive geometric model which represents palmar creases with parameterized Bézier curves. By randomly sampling Bézier parameters, we can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability: they can be efficiently transferred to real datasets, leading to significant performance improvements on palmprint recognition. For example, under the open-set protocol, our method improves the strong ArcFace baseline by more than 10% in terms of TAR@1e–6. And under the closed-set protocol, our method reduces the equal error rate (EER) by an order of magnitude. Code is available at http://***/palmprint. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Text-Informed Knowledge Distillation for Robust Speech Enhancement and Recognition

Text-Informed Knowledge Distillation for Robust Speech Enhan...

引用

International Symposium on Chinese Spoken Language Processing

作者： Wei Wang Wangyou Zhang Shaoxiong Lin Yanmin Qian Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Shanghai Jiao Tong University

ISBN: (纸本)9798350397970

Most existing speech enhancement (SE) approaches heavily dep.nd on simulated data for training, leading to performance degradation on realistic data and subsequent speech recognition task. One of the main reasons is that SE models cannot be trained on real data due to the absence of reference signals. In this paper, we aim to tackle this problem by exploiting transcribed real data to mitigate the mismatch between training and evaluation. A text-informed SE teacher is first trained to provide “reference” signals for the transcribed real data. Then a SE student is trained on both simulated and real data, where the supervision comes from the simulated ground truth and the teacher, respectively. Finally, a speech recognition model is trained on enhanced signals from the SE student. Our experimental results show that the proposed method can not only improve the speech enhancement performance, but also reduce the word error rate on the downstream speech recognition task.

关键词： Training Degradation Error analysis Speech recognition Speech enhancement Performance gain Data models

来源：评论

学校读者我要写书评

暂无评论

Prototype and Instance Contrastive Learning for Unsupervised Domain Adaptation in Speaker Verification

Prototype and Instance Contrastive Learning for Unsupervised...

引用

International Symposium on Chinese Spoken Language Processing

作者： Wen Huang Bing Han Zhengyang Chen Shuai Wang Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Speaker verification system trained on one domain usually suffers performance degradation when applied to another domain. To address this challenge, researchers commonly use feature distribution matching-based methods in unsupervised domain adaptation scenarios where some unlabeled target domain data is available. However, these methods often have limited performance improvement and lack generalization in various mismatch situations. In this paper, we propose Prototype and Instance Contrastive Learning (PICL), a novel method for unsupervised domain adaptation in speaker verification through dual-level contrastive learning. For prototype contrastive learning, we generate pseudo labels via clustering to create dynamically updated prototype representations, aligning instances with their corresponding class or cluster prototypes. For instance contrastive learning, we minimize the distance between different views or augmentations of the same instance, ensuring robust and invariant representations resilient to variations like noise. This dual-level approach provides both high-level and low-level supervision, leading to improved generalization and robustness of the speaker verification model. Unlike previous studies that only evaluated mismatches in one situation, we have conducted relevant explorations on various datasets and achieved state-of-the-art performance currently, which also proves the generalization of our method.

关键词： Degradation Adaptation models Noise Prototypes Contrastive learning Robustness

来源：评论

学校读者我要写书评

暂无评论

Structure-Aware Policy to Improve Generalization among Various Robots and Environments

Structure-Aware Policy to Improve Generalization among Vario...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Xu, Wei Gao, Yue Nie, Buqing Shanghai Jiao Tong University Department of Automation Shanghai200240 China Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence and AI Institute Shanghai200240 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

ISBN: (纸本)9781665481090

Recently, Deep Reinforcement Learning (DRL) has been used to solve complex robot control tasks with outstanding success. However, previous DRL methods still exist some shortcomings, such as poor generalization performance, which makes policy performance quite sensitive to small vari-ations of the task settings. Besides, it is quite time-consuming and computationally expensive to retrain a new policy from scratch for new tasks, hence restricts the applications of DRL-based methods in the real world. In this work, we propose a novel DRL generalization method called GNN-embedding, which incorporates the robot hardware and the environment simultaneously with GNN-based policy network and learnable embedding vectors of tasks. Thus, it can learn a unified policy for different robots under different environment conditions, which improves the generalization performance of existing DRL robot policies. Multiple experiments on the Hopper-v2 robot are conducted. The experimental results demonstrate the effectiveness and efficiency of GNN-embedding on generalization, including multi-task learning and transfer learning problems. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor

arXiv

引用

arXiv 2023年

作者： Chen, Zhengyang Han, Bing Wang, Shuai Qian, Yanmin MoE Key Lab of Artificial Intelligence AI Institute X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University China Shenzhen Research Institute of Big Data Shenzhen China

This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity detection (TS-VAD) to calculate the attractor, which can mitigate the speaker permutation problem and facilitate easier model convergence. In the training process, we propose a teacher-forcing strategy to obtain the enrollment information using the ground-truth label. Furthermore, we propose three heuristic decoding methods to identify the enrollment area for each speaker during the evaluation process. Additionally, we enhance the attractor calculation network LSTM used in the end-to-end encoder-decoder based attractor calculation (EEND-EDA) system by incorporating an attention-based model. By utilizing such an attention-based attractor decoder, our proposed AED-EEND system outperforms both the EEND-EDA and TS-VAD systems with only 0.5s of enrollment data. © 2023, CC BY-NC-SA.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation

arXiv

引用

arXiv 2023年

作者： Li, Jiefeng Bian, Siyuan Liu, Qi Tang, Jiasheng Wang, Fan Lu, Cewu Department of Computer Science and Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Alibaba Group China

With the progress of 3D human pose and shape estimation, state-of-the-art methods can either be robust to occlusions or obtain pixel-aligned accuracy in non-occlusion cases. However, they cannot obtain robustness and mesh-image alignment at the same time. In this work, we present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors to improve the robustness to occlusions and obtain pixel-aligned accuracy. NIKI can learn from both the forward and inverse processes with invertible networks. In the inverse process, the model separates the error from the plausible 3D pose manifold for a robust 3D human pose estimation. In the forward process, we enforce the zero-error boundary conditions to improve the sensitivity to reliable joint positions for better mesh-image alignment. Furthermore, NIKI emulates the analytical inverse kinematics algorithms with the twist- and-swing decomposition for better interpretability. Experiments on standard and occlusion-specific benchmarks demonstrate the effectiveness of NIKI, where we exhibit robust and well-aligned results simultaneously. Code is available at https://***/Jeff-sjtu/NIKI. Copyright © 2023, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：