检索结果-内蒙古大学图书馆

GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xuanchang Zhang, Zhuosheng Zhao, Hai College of Zhiyuan Shanghai Jiao Tong University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Despite the rapid progress of large language models (LLMs), their task performance remains sensitive to prompt design. Recent studies have explored leveraging the LLM itself as an optimizer to identify optimal prompts that maximize task accuracy. However, when evaluating prompts, such approaches heavily rely on elusive manually annotated gold labels to calculate task accuracy for each candidate prompt, which hinders its generality. To overcome the limitation, this work proposes GLaPE, a gold label-agnostic prompt evaluation method to alleviate dependence on gold labels. GLaPE is composed of two critical aspects: self-consistency evaluation of a single prompt and mutual-consistency refinement across multiple prompts. Experimental results on 8 widely-recognized reasoning tasks demonstrate that GLaPE can produce more effective prompts, achieving performance comparable to those derived from manually annotated gold labels. Analysis shows that GLaPE provides reliable evaluations aligned with accuracy, even in the absence of gold labels. Code is publicly available at https://***/thunderous77/GLaPE. Copyright © 2024, The Authors. All rights reserved.

关键词： Gold

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Yifeng Wang, Suzhen Hu, Zhipeng Fan, Changjie Lv, Tangjie Ding, Yu Deng, Zhidong Yu, Xin Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China Virtual Human Group Netease Fuxi AI Lab China Zhejiang University China University of Technology Sydney Australia

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://***/FuxiVirtualhuman/styletalk. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

Evaluating the Benefits of the Immersive Space to Think

学校读者我要写书评

暂无评论

Evaluating the Benefits of the Immersive Space to Think

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Lee Lisle Xiaoyu Chen J.K. Edward Gitre Chris North Doug A. Bowman Department of Computer Science Center for Human-Computer Interaction Grado Department of Industrial and Systems Engineering Virginia Tech Department of History Virginia Tech Center for Human-Computer Interaction

ISBN: (数字)9781728165325

ISBN: (纸本)9781728165332

Sensemaking with large multimedia dataset is a cognitively intensive task that requires analysts to understand the underlying stories that the dataset tells. Often, analysts use tools in order to offload cognition as well as convey their new understanding of the dataset; however, existing tools are limited by their underlying technologies. We have proposed a novel virtual reality tool to support sensemaking called the Immersive Space to Think (IST). IST can aid the process of analyzing multimedia data, but it remains unproven whether IST improves sensemaking performance over a traditional desktop setting. In a study performed over six weeks, one participant used both IST and traditional methods of sensemaking with a dataset of 100 text documents of transcribed survey responses from World War 2 soldiers to perform historical analysis. The participant was asked guided questions that produced three essays with their understanding of the data. After conducting a blind evaluation of the participant’s interpretation of the data, a team of three experts in historical analysis concluded that the essays written with IST displayed a better understanding of the dataset. Furthermore, the participant gave positive feedback on IST, and also suggested possible improvements.

关键词： Tools Visualization Task analysis human computer interaction Virtual reality Three-dimensional displays Information analysis

Lite Unified Modeling for Discriminative Reading Comprehension

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Yilin Zhao, Hai Shen, Libin Zhao, Yinggong Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China Leyan Tech Shanghai China

As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally;while extractive MRC focuses on higher local boundary preciseness for answer extraction. Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks. To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously. Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components. The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://***/Yilin1111/poi-net. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Skeleton-Embedded Network for action recognition

学校读者我要写书评

暂无评论

Skeleton-Embedded Network for action recognition

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Li Luo Ziliang Ren Yong Qin Qieshi Zhang Xiangyang Gao Department of Computer Science Dongguan University of Technology Dongguan China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China The Chinese University of Hong Kong China

Multimodality-based human action recognition is becoming an increasingly attractive topic as different modalities can provide complementary information. RGB and skeleton data have their pros and limitations for action recognition because they describe the action from distinctive views. Therefore, the fusion of these two modalities using their complementarity is meaningful to action recognition. However, it is difficult to completely utilize the supplementarity of RGB and skeleton data. In this paper, to take advantage of their complementary at the semantic level, A skeleton-embedded network(SE-Net) is proposed by us. The architecture is based on integrating their feature in the network not only a post-hoc fusion. With a sparse sampling strategy, which is efficient for learning using the whole action video. To examine the performance of our method, we conducted experiments on the wildly used datasets, obtaining an accuracy of 86.4% in C-sub and 88.2% in C-view on NTU-RGB+D 60. For NTU-RGB+D 120, the accuracy of 81.3% in C-sub and 83.4% in C-set is obtained.

关键词：

TraSeTR: Track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Zixu Jin, Yueming Heng, Pheng-Ann Department Of Computer Science And Engineering The Chinese University Of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory Of Human-Machine Intelligence-Synergy Systems Shenzhen Institute Of Advanced Technology Chinese Academy Of Sciences China Department Of Computer Science University College London United Kingdom

Surgical instrument segmentation - in general a pixel classification task - is fundamentally crucial for promoting cognitive intelligence in robot-assisted surgery (RAS). However, previous methods are struggling with discriminating instrument types and instances. To address above issues, we explore a mask classification paradigm that produces per-segment predictions. We propose TraSeTR, a novel Track-to-Segment Transformer that wisely exploits tracking cues to assist surgical instrument segmentation. TraSeTR jointly reasons about the instrument type, location, and identity with instance-level predictions i.e., a set of class-bbox-mask pairs, by decoding query embeddings. Specifically, we introduce the prior query that encoded with previous temporal knowledge, to transfer tracking signals to current instances via identity matching. A contrastive query learning strategy is further applied to reshape the query feature space, which greatly alleviates the tracking difficulty caused by large temporal variations. The effectiveness of our method is demonstrated with state-of-the-art instrument type segmentation results on three public datasets, including two RAS benchmarks from EndoVis Challenges and one cataract surgery dataset CaDIS. © 2022, CC BY-NC-SA.

关键词： Surgical equipment

human body odour modulates neural processing of faces: effective connectivity analysis using EEG

学校读者我要写书评

暂无评论

Human body odour modulates neural processing of faces: effec...

Annual IEEE Symposium on computer-Based Medical Systems

作者： Saideh Ferdowsi Dimitri Ognibene Tom Foulsham Alberto Greco Alejandro Luis Callara Sergio Cervera-Torres Mariano Alcañiz Nicola Vanello Luca Citi School of computer science and electrical engineering University of Essex Colchester UK Department of Psychology University of Milan-Bicocca Milan Italy Department of Psychology University of Essex Colchester UK Department of Information Engineering University of Pisa Pisa Italy Laboratory of Immersive Neurotechnologies (LabLENI) Human-Centered Technology Institute (Human-Tech) Polytechnic University of Valencia Spain

Facial emotion processing by the brain plays a decisive role in human social interactions. This signal helps us interpret and predict people's behaviours. However, other social signals such as human voices or human body odours may facilitate or impair the identification of facial expressions. Here we studied the effects of emotional human body odours on face processing by measuring evoked neural responses and brain connectivity using the electroencephalogram (EEG). We used an emotion recognition task in which the participants attributed an emotion (i.e. happy vs fearful) to a presented face image while simultaneously exposed to emotional body odours. First, we measured face related potentials (FRP)s including P100 and N170 components. Statistical analyses revealed significant differences among FRPs recorded in different odour conditions. Second, we used a hierarchical Bayesian approach including a group dynamic causal model (DCM) followed by parametric empirical Bayes (PEB) to characterize the brain network explaining differences between FRPs. Our preliminary results suggested that different brain networks contribute to neutral face processing in the presence of different emotional body odours.

关键词：

Incremental Feature Selection for Dynamic Incomplete Data Using Sub-Tolerance Relations

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhao, Jie Ling, Yun See-To, Wing-Kuen Eric Huang, Faliang Wang, Jiahai School of Management Guangdong University of Technology Guangzhou China Department of Computing and Decision Sciences Faculty of Business Lingnan University Hong Kong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

Feature selection is an important problem in Rough Set and is widely used in data analysis. The extended theory of tolerance relations can effectively deal with the realistic problem of incomplete data. However, the space and time complexity of computing the positive region using TRS increases dramatically. Simultaneously, redundant features are allowed to enter the feature subset, resulting in poor classification accuracy, because the positive region-based significance measure neglects uncertain information. To overcome these drawbacks, this paper introduces a subrelation-based tolerance class (STC) approach. STC transforms the TRS positive region calculation into a two-stage certainty measurement of objects, and thus divides the entire universe into two regions of certainty and uncertainty at each stage, by decomposing the tolerance relation into two subrelations. The computational space is reduced by progressively filtering out of the regions of certainty. Using STC, a new incremental mechanism is proposed. Furthermore, we propose a new significance measure using both certain and uncertain information, which effectively reduces the number of redundant features and subsequently improves computational efficiency and classification accuracy. Experiments on real data sets and comparisons with existing algorithms have been conducted to verify the superiority of the method. © 2023, The Authors. All rights reserved.

关键词： Feature Selection

Static Force-Based Modeling and Parameter Estimation for a Deformable Link Composed of Passive Spherical Joints With Preload Forces

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第11期8卷 1817-1826页

作者： Gaofeng Li Dezhen Song Lei Sun Shan Xu Hongpeng Wang Jingtai Liu Nankai University Tianjin 300350China Humanoids and Human Centered Mechatronics Research Line Italian Institute of Technology16163 GenovaItaly Department of Computer Science and Engineering Texas A&M UniversityCollege StationTexas 77843 USA Institute of Robotics and Automatic Information System Nankai UniversityTianjin 300350China Tianjin Key Laboratory of Intelligent Robotics Nankai UniversityTianjin 300350China

To balance the contradiction between higher flexibility and heavier load bearing capacity,we present a novel deformable manipulator which is composed of active rigid joints and deformable *** deformable link is composed of passive spherical joints with preload forces between socket-ball *** estimate the load bearing capacity of a deformable link,we present a static force-based model of spherical joint with preload force and analyze the static force propagation in the deformable *** yields an important result that the load bearing capacity of a spherical joint only depends on its radius,preload force,and static friction *** further develop a parameter estimation method to estimate the product of preload force and static friction *** experimental results validate our model.80.4%of percentage errors on the maximum payload mass prediction are below 15%.

关键词： Deformable link parameters identification spherical joint with preload force static force-based model