具身智能 · 全部实体（第 9 / 100 页）

本页收录第 801–900 条，共 9964 条 · 返回 具身智能 首页

• Enhancing Glaucoma Diagnosis through Vision-Language Models and Large Language Model Descriptions
  Deep learning approaches have been widely studied for their effectiveness in glaucoma detection using fundus images. For deep learning models to perform well, high-quality labeled data is essential for training the models. However, as annotating medical images…
  crossref Heui Yeon Bae, Morteza Saberi, Sahar Shariflou, Michael Kalloniatis 等 2025-02-13T18:31:50Z 置信度 0.82 cs.lgartificial intelligencecs.aics.cvcs.cl
• Language Models as Black-Box Optimizers for Vision-Language Models
  Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. However, many VLMs rely on proprietary data and are not open-source, which restricts the use of whi…
  crossref Shihong Liu, Samuel Yu, Zhiqiu Lin, Deepak Pathak 等 2024-09-16T17:34:53Z 置信度 0.82 cs.aicomputer sciencecs.lgartificial intelligencecomputer and information sciences
• Exploring the interface between difficult circumstances and action research in English language teaching
  The past few decades have witnessed an increasing awareness about and interest in ‘difficult circumstances’ (DC) as a widespread and global phenomenon in ELT, and a realisation that the ‘mainstream’ frameworks of theory and practice seem inadequate in understa…
  crossref Amol Padwad 2024-12-02T13:08:45Z 置信度 0.82 psychologycognitive scienceperceptionmathematics educationpolitical science
• Vision Language Models in X-ray: A Review
  Vision-language models (VLMs) have demonstrated significant potential in various domains, including natural language processing and computer vision. However, their application in medical imaging, particularly in X-ray diagnosis, remains underexplored. This rev…
  crossref Ali Majali 2024-08-12T16:00:48Z 置信度 0.82 medicinecomputer sciencedata sciencemedical physicshealth care
• Sensory feedback modulates Weber's law of both perception and action
  Weber's law states that estimation noise is proportional to stimulus intensity. Although this holds in perception, it appears absent in visually guided actions where response variability does not scale with object size. This discrepancy is often attributed to …
  crossref Ailin Deng, Evan Cesanek, Fulvio Domini 2024-12-17T16:30:51Z 置信度 0.82 psychologyneuroscienceroboticsbrain-computer interfacecognitive psychology
• Age effects on predictive eye movements for action
  When interacting with the environment, humans typically shift their gaze to where information is to be found that is useful for the upcoming action. With increasing age, people become slower both in processing sensory information and in performing their moveme…
  crossref Leonard Gerharz, Eli Brenner, Jutta Billino, Dimitris Voudouris 2024-06-10T11:30:57Z 置信度 0.78 psychologysocial and behavioral sciencescognitive psychologyastro-ph.epneuroscience
• Vary: Scaling up the Vision Vocabulary for Large Vision-Language Model
  crossref Haoran Wei, Lingyu Kong, Jinyue Chen, Liang Zhao 等 2024-09-29T06:01:53Z 置信度 0.66
• Vision et action pour la Résilience
  crossref Anne-Marie Levraut 2024-07-01T17:08:01Z 置信度 0.66
• [Book Review] Embodying Language in Action: The Artistry of Process Drama in Second Language Education
  This paper reviews EriKa Piazzoli's book Embody Language in Action: The Artistry of Process Drama in Second Language Education, published in 2018. The book explores process drama as a form of performative learning in Second language (L2) education. It provides…
  crossref Jungmi Hur 2025-01-23T05:54:49Z 置信度 0.82 psychologycognitive sciencemathematics educationknowledge managementembodied cognition
• How natural action perception unfolds in the brain
  In a fraction of a second, humans can recognize a wide range of actions performed by others. Yet actions pose a unique complexity challenge, bridging visual domains and varying along multiple perceptual and semantic features. What features are extracted in the…
  crossref Diana Dima, Yalda Mohsenzadeh 2024-09-27T20:31:43Z 置信度 0.82 artificial intelligencepsychologycomputer sciencecognitive sciencecs.lg
• Fast and Lightweight Vision-Language Model for Adversarial Traffic Sign Detection
  Several attacks have been proposed against autonomous vehicles and their subsystems that are powered by machine learning (ML). Road sign recognition models are especially heavily tested under various adversarial ML attack settings, and they have proven to be v…
  crossref Furkan Mumcu, Yasin Yilmaz 2024-06-03T03:51:45Z 置信度 0.82 computer and information sciencescomputer sciencecs.lgcs.aiartificial intelligence
• Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning
  Large Language Models (LLMs) have demonstrated impressive performance across various tasks.However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance.These solutions ar…
  crossref Daniele Rege Cambrin, Giuseppe Gallipoli, Irene Benedetto, Luca Cagliero 等 2024-11-27T22:28:12Z 置信度 0.82 cs.aics.lgcs.clcomputer sciencecomputer and information sciences
• Arriving at a Vision and Mission Statement for SHAJ.
  crossref Khalif Bile 2024-10-30T14:19:15Z 置信度 0.63
• The Enhanced vision-language model developing for fine-grained difficult sample classification tasks
  In special practical scenarios such as severe weather and dense buildings, intelligent target recognition relying on single modal images faces problems of image occlusion and blurring. Especially for fine-grained targets, the classification accuracy will signi…
  crossref Anning Xia, Bin Zhu, Yi Chen, Runhua Wang 2025-03-04T18:39:08Z 置信度 0.82 computer and information sciencescs.lgcomputer sciencecs.cvcs.ai
• Sniffer: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection
  Misinformation is a prevalent societal issue due to its potential high risks. Out-Of-Context (OOC) misinformation, where authentic images are repurposed with false text, is one of the easiest and most effective ways to mislead audiences. Current methods focus …
  crossref Peng Qi, Zehong Yan, Wynne Hsu, Mong Li Lee 2024-09-16T13:34:53Z 置信度 0.78 cs.aics.clartificial intelligencecs.lgcomputer science
• QViLa: Quantum Infused Vision-Language Model for Enhanced Multimodal Understanding
  crossref K. Mukesh, S. L. Jayaprakash, R. Prasanna Kumar 2024-11-05T10:01:45Z 置信度 0.66
• LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge
  Multimodal Large Language Models (MLLMs) have endowed LLMs with the ability to perceive and understand multimodal signals. However, most of the existing MLLMs mainly adopt vision encoders pretrained on coarsely aligned image-text pairs, leading to insufficient…
  crossref Gongwei Chen, Leyang Shen, Rui Shao, Xiang Deng 等 2024-09-16T17:34:53Z 置信度 0.82 cs.aiartificial intelligencecomputer and information sciencescomputer sciencecs.cl
• TALON: Improving Large Language Model Cognition with Tactility-Vision Fusion
  Current Multimodal Large Language Models (MLLMs) mainly focus on vision and language modalities, often overlooking the integration of other senses, such as tactile perception. In this paper, we present Improving Language Model Cognition with Tactility-Vision F…
  crossref Xinyi Jiang, Guoming Wang, Huanhuan Li, Qinghua Xia 等 2024-09-18T17:51:10Z 置信度 0.82 computer and information sciencesartificial intelligencecs.aics.cvcs.lg
• LISA: Reasoning Segmentation via Large Language Model
  Although perception systems have made remarkable ad-vancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems cannot actively reaso…
  crossref Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li 等 2024-09-16T13:34:53Z 置信度 0.78 cs.aicomputer scienceartificial intelligencecs.lgcomputer and information sciences
• A Novel Pretrained General-purpose Vision Language Model for the Vietnamese Language
  Lying in the cross-section of computer vision and natural language processing, vision language models are capable of processing images and text at once. These models are helpful in various tasks: text generation from image and vice versa, image-text retrieval,…
  crossref Dinh Anh Vu, Quang Nhat Minh Pham, Giang Son Tran 2024-03-30T09:24:01Z 置信度 0.82 computer scienceartificial intelligencecs.aics.lgcs.cv
• A Knowledge Graph and Large Language Model-Based Framework for Depression Detection
  Depression is a common mental health disorder that significantly impacts individuals’ quality of life and places a considerable burden on global healthcare systems. Accurate and timely detection of depression is crucial for effective intervention and treatment…
  crossref Youwei Guo, Yanrong Guo 2025-04-14T17:35:47Z 置信度 0.82 computer and information sciencescs.aics.lgcomputer scienceartificial intelligence
• Exploring Vision Language Pretraining with Knowledge Enhancement via Large Language Model
  crossref Chuenyuet Tung, Yi Lin, Jianing Yin, Qiaoyuchen Ye 等 2024-08-01T19:02:53Z 置信度 0.66
• A learnable motion preserving pooling for action recognition
  crossref Tankun Li, Kwok Leung Chan, Tardi Tjahjadi 2024-09-17T18:59:18Z 置信度 0.63
• Student engagement through action research
  This chapter explores the transformative potential of action research (AR) in enhancing student engagement and fostering their active involvement in language learning through participation in teachers’ AR projects. Engaging students directly in the research pr…
  crossref Kenan Dikilitaş 2024-12-02T13:08:45Z 置信度 0.82 psychologymathematics educationengineering ethicsknowledge managementmedical education
• Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model
  The ability of large language models (LLMs) to process visual inputs has given rise to general-purpose vision systems, unifying various vision-language (VL) tasks by instruction tuning. However, due to the enormous diversity in input-output formats in the visi…
  crossref Shraman Pramanick, Guangxing Han, Rui Hou, Sayan Nag 等 2024-09-16T17:34:53Z 置信度 0.82 cs.lgcs.aicomputer and information sciencescs.cvcomputer science
• Examining the role of action-driven attention in ensemble processing
  Ensemble processing allows the visual system to condense visual information into useful summary statistics (e.g., average size), thereby overcoming capacity limitations to visual working memory and attention. To examine the role of attention in ensemble proces…
  crossref Kristina Knox, Jay Pratt, Jonathan S. Cant 2024-06-06T11:31:15Z 置信度 0.82 psychologycognitive psychologyneurosciencebrain-computer interfacebiological sciences not elsewhere classified
• Divide and Conquer Boosting for Enhanced Traffic Safety Description and Analysis with Large Vision Language Model
  The increasing complexity of traffic dynamics has underscored the necessity for advanced traffic safety description and analysis, challenging the efficacy of current methodologies in comprehensively understanding and predicting safety conditions from transport…
  crossref Khai Trinh Xuan, Khoi Nguyen Nguyen, Bach Hoang Ngo, Vu Dinh Xuan 等 2024-09-27T18:27:42Z 置信度 0.82 cs.aicomputer and information sciencescs.lgeess.ascs.cv
• Driving Everywhere with Large Language Model Policy Adaptation
  Adapting driving behavior to new environments, customs, and laws is a longstanding problem in autonomous driving, precluding the widespread deployment of autonomous vehicles (AVs). In this paper, we present LLaDA, a simple yet powerful tool that enables human …
  crossref Boyi Li, Yue Wang, Jiageng Mao, Boris Ivanovic 等 2024-09-16T13:34:53Z 置信度 0.82 computer and information sciencescs.aics.roroboticscomputer science
• LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model
  The capacity of existing human keypoint localization models is limited by keypoint priors provided by the training data. To alleviate this restriction and pursue more gen-eral model, this work studies keypoint localization from a different perspective by reaso…
  crossref Dongkai Wang, Shiyu Xuan, Shiliang Zhang 2024-09-16T17:34:53Z 置信度 0.82 cs.cvcs.aics.clcs.lgartificial intelligence
• Lateralized representations of cause and effect in action observation
  Understanding object-directed actions requires the visual analysis of how body parts interact with objects and how these interactions lead to changes in the objects. However, whether, and if so, how interaction (as cause) and object change (as effect) are dist…
  crossref Moritz Wurm, Philipp Flieger 2024-09-27T20:32:45Z 置信度 0.82 psychologyneurosciencehuman-computer interactioncognitioncognitive psychology
• Layerwised multimodal knowledge distillation for vision-language pretrained model
  The transformer-based model can simultaneously learn the representation for both images and text, providing excellent performance for multimodal applications. Practically, the large scale of parameters may hinder its deployment in resource-constrained devices,…
  crossref Jin Wang, Dawei Liao, You Zhang, Dan Xu 等 2024-03-26T17:54:39Z 置信度 0.82 cs.lgcomputer and information sciencescs.aics.cvcs.cl
• Language Model Adaption for Reinforcement Learning with Natural Language Action Space
  Reinforcement learning with natural language action space often suffers from the curse of dimensionality due to the combinatorial nature of the natural language.Previous research leverages pretrained language models to capture action semantics and reduce the s…
  crossref Jiangxing Wang, Jiachen Li, Xiao Han, Deheng Ye 等 2024-09-20T19:33:08Z 置信度 0.82 cs.lgcs.aireinforcement learningcomputer and information sciencescs.cv
• RS5M and GeoRSCLIP: A Large-Scale Vision- Language Dataset and a Large Vision-Language Model for Remote Sensing
  Pretrained vision-language models (VLMs) utilizing extensive image–text paired data have demonstrated unprecedented image–text association capabilities, achieving remarkable results across various downstream tasks. A critical challenge is how to make use of ex…
  crossref Zilun Zhang, Tiancheng Zhao, Yulong Guo, Jianwei Yin 2024-09-12T13:53:29Z 置信度 0.82 cs.lgcs.cvcs.aics.clcomputer science
• Developing professional ethics for action research
  Ethical issues are integral to research, and it is essential that a teacher who conducts research understands the ethical responsibilities before conducting field research. This chapter begins by explaining the difference between macro- and micro-ethics, and t…
  crossref Roger Barnard 2024-12-02T13:08:45Z 置信度 0.82 psychologyengineering ethicstransparencycognitive sciencemars exploration program
• Robot Manipulation Planning with Large Pre-Trained Models of Language, Vision, and Action
  This paper explores the integration of large pre-trained models of language, vision, and action to enhance robot manipulation planning. By leveraging advanced language models such as GPT-4 and Gemini, task planning can be articulated in natural language, allow…
  crossref Youngsung Son, Hyonyong Han, Junhee Park 2025-01-14T19:40:10Z 置信度 0.82 cs.roartificial intelligencecomputer and information sciencesroboticsreinforcement learning
• Are Visual-Language Models Effective in Action Recognition? A Comparative Study
  crossref Mahmoud Ali, Di Yang, François Brémond 2025-05-27T15:22:55Z 置信度 0.66
• Cascade Prompt Learning for Vision-Language Model Adaptation
  crossref Ge Wu, Xin Zhang, Zheng Li, Zhaowei Chen 等 2024-10-31T14:03:04Z 置信度 0.66
• Research on Athlete Technical Action Scoring Model Based on Deep Learning
  crossref Tian Long, Xiaodong Li 2025-04-03T00:10:16Z 置信度 0.66
• Vision-language model based handwriting verification
  Handwriting Verification is a critical in document forensics. Deep learning based approaches often face skepticism from forensic document examiners due to their lack of explainability and reliance on extensive training data and handcrafted features. This paper…
  crossref Mihir Chauhan, Abhishek Satbhai, Mohammad Abuzar Hashemi, Mir Basheer Ali 等 2024-12-12T11:00:11Z 置信度 0.82 cs.aics.lgcomputer sciencecomputer and information sciencesartificial intelligence
• Improving Video Representation of Vision-Language Model with Decoupled Explicit Temporal Modeling
  crossref Yuxi Liu, Wenyu Zhang, Sihong Chen, Xinming Zhang 2024-11-02T05:04:50Z 置信度 0.66
• Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model
  Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Aware Emotion Recognition (CAER), and were i…
  crossref XingLin Li, Xinde Li, Chuanfei Hu, Huaping Liu 2024-10-18T17:27:32Z 置信度 0.82 cs.lgeess.ascs.sdcs.clcs.cv
• Parameter-level Mask-based Adapter for 3D Continual Learning with Vision-Language Model
  As 3D object classification becomes increasingly essential in various applications, the need for models to continuously adapt to new scenarios is more crucial than ever. However, existing continual learning methods primarily concentrate on 2D tasks, making the…
  crossref Longyue Qian, Mingxin Zhang, Qian Zhang, Lin Zhang 等 2025-03-07T18:33:40Z 置信度 0.82 computer and information sciencescs.aics.lgcs.cvcomputer science
• Review of Savski (2024): Language Policy in Action
  crossref Hossein Davari, Saeed Nourzadeh 2026-06-25T10:06:26Z 置信度 0.66
• TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning
  Traffic video description and analysis have received much attention recently due to the growing demand for efficient and reliable urban surveillance systems. Most existing methods only focus on locating traffic event segments, which severely lack descriptive d…
  crossref Quang Minh Dinh, Minh Khoi Ho, Anh Quan Dang, Hung Phong Tran 2024-09-27T18:27:42Z 置信度 0.82 computer and information sciencescs.cvcs.lgcs.aics.sd
• A Vision-language Model Based on Prompt Learner for Few-shot Medical Images Diagnosis
  In the real world, it can be challenging to annotate a large-scale dataset for all medical images, making few-shot medical image classification an important task. The latest advancements in pre-trained vision-language models as CLIP have demonstrated excellent…
  crossref Tianyou Chang, Shizhan Chen, Guodong Fan, Zhiyong Feng 2024-07-10T17:21:49Z 置信度 0.82 computer scienceartificial intelligencecs.lgcomputer and information sciencescs.cv
• Modeling Action-Perception Coupling with Reciprocally Connected Neural Fields
  Visual perception is modulated by various contextual factors, including self-motion. The existence of the mirror neuron system highlights a strong connection between action observation and execution. Yet the mechanisms underlying action-perception coupling rem…
  crossref Xinrui Jiang, Martin A. Giese 2025-07-16T00:31:25Z 置信度 0.82 neurosciencepsychologycognitioncs.aicognitive psychology
• Leveraging Large Language and Vision Assistant Model for Multi Camera Appearance Features
  crossref Oliver Zeilerbauer, Mohammad Reza Mohebbi, Mario Doeller 2025-01-07T08:25:22Z 置信度 0.66
• Leveraging Advanced Vision-Language Model in Medical Visual Question Answering
  Visual Question Answering (VQA) in healthcare represents a groundbreaking method that utilizes sophisticated computational tools to interpret intricate details within medical images. These images often involve intricate question variations and high degrees of …
  crossref Abdul Hafidh, Alim Misbullah, Laina Farsiah, Dalila Husna Yunardi 等 2025-01-10T19:59:46Z 置信度 0.82 computer scienceartificial intelligencecs.aics.cvcs.lg
• A Large Vision-Language Model based Environment Perception System for Visually Impaired People
  It is a challenging task for visually impaired people to perceive their surrounding environment due to the complexity of the natural scenes. Their personal and social activities are thus highly limited. This paper introduces a Large Vision-Language Model(LVLM)…
  crossref Zezhou Chen, Zhaoxiang Liu, Kai Wang, Kohou Wang 等 2024-12-25T19:17:39Z 置信度 0.82 human-computer interactionembodied cognitionsetrobottask
• Domain Knowledge Enhanced Vision-Language Pretrained Model for Dynamic Facial Expression Recognition
  Dynamic facial expression recognition (DFER) is a rapidly developing field that focuses on recognizing facial expressions in video sequences. However, the complex temporal modeling caused by noisy frames, along with the limited training data significantly hind…
  crossref Liupeng Li, Yuhua Zheng, Shupeng Liu, Xiaoyin Xu 等 2024-10-26T06:59:27Z 置信度 0.82 cs.aicomputer and information sciencescs.lgcomputer sciencecs.cv
• Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval
  crossref Mustafa Shukor, Nicolas Thome, Matthieu Cord 2024-07-09T15:55:41Z 置信度 0.66
• Multiscale Vision Transformers Meet Bipartite Matching for Efficient Single-Stage Action Localization
  In this paper, we observe that a straight bipartite matching loss can be applied to the output tokens of a vision transformer. This results in a backbone + MLP architecture that can do both tasks without the need of an extra encoder-decoder head and learnable …
  crossref Ioanna Ntinoutl, Enrique Sanchez, Georgios Tzimiropoulos 2024-09-16T13:34:53Z 置信度 0.82 cs.lgcomputer and information sciencescomputer sciencecs.aiartificial intelligence
• Efficient Language-Driven Action Localization by Feature Aggregation and Prediction Adjustment
  crossref Zirui Shang, Shuo Yang, Xinxiao Wu 2024-10-19T21:02:10Z 置信度 0.66
• Bridge the Modality and Capability Gaps in Vision-Language Model Selection
  crossref Chao Yi, Yu-Hang He, De-Chuan Zhan, Han-Jia Ye 2025-11-03T11:20:56Z 置信度 0.66
• Scene adaptive mechanism for action recognition
  crossref Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler 2023-10-04T06:26:09Z 置信度 0.61
• Aligning Multimodal Biomedical Images and Language via One Large Vision-Language Model
  Large Vision-Language Models (LVLMs) have garnered substantial attention in the biomedical image analysis domain due to their robust vision understanding capabilities. However, current methods rely heavily on dataset- and modality-specific fine-tuning. This in…
  crossref Haojie Zhang, Min Zeng, Jinfeng Ding, Yixiong Liang 等 2025-01-10T20:12:45Z 置信度 0.82 computer and information sciencescs.cvcs.lgcs.aicomputer science
• How Much Can Vision Language Models Really "See"?
  Introduction The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.
  crossref Amanda Kau 2026-08-30T11:44:42Z 置信度 0.80 cognitive psychologyquantum computercognitive scienceconsciousnessquantum algorithm
• How Much Can Vision Language Models Really "See"?
  Introduction The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.
  crossref Amanda Kau 2026-08-30T11:44:41Z 置信度 0.80 cognitive psychologyquantum computercognitive scienceconsciousnessquantum algorithm
• JOADAA: joint online action detection and action anticipation
  Action anticipation involves forecasting future actions by connecting past events to future ones. However, this reasoning ignores the real-life hierarchy of events which is considered to be composed of three main parts: past, present, and future. We argue that…
  crossref Mohammed Guermal, Abid Ali, Rui Dai, Francois Bremond 2024-04-09T17:36:09Z 置信度 0.82 cs.aicomputer sciencecs.lgcomputer and information sciencesartificial intelligence
• In-service teacher education and action research
  This chapter addresses the issue of the impact of action research (AR) in in-service teacher education. It begins by outlining changes over the last 30 years in theoretical conceptions of what constitutes effective language teacher education and how it should …
  crossref Anne Burns 2024-12-02T13:08:45Z 置信度 0.82 psychologymathematics educationengineering ethicsmedical educationcognitive science
• How Much Can Vision Language Models Really "See"?
  Introduction The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.
  crossref Amanda Kau 2025-12-09T11:02:49Z 置信度 0.80 cognitive psychologyquantum computercognitive scienceconsciousnessquantum algorithm
• Review for "Zero‐shot animal behaviour classification with vision‐language foundation models"
  crossref 2025-05-21T09:05:51Z 置信度 0.66
• How Much Can Vision Language Models Really "See"?
  Introduction The human brain is more extraordinary than any machine we could build. From an early age, many of us gain the ability to comprehend what our eyes tell us and articulate it. Furthermore, we combine evidence from all our senses to reason.
  crossref Amanda Kau 2024-03-11T23:42:04Z 置信度 0.80 cognitive psychologyquantum computercognitive scienceconsciousnessquantum algorithm
• Action research for teaching grammar
  The role of grammar in English language teaching has been an area of ongoing interest for teachers and researchers. Action research (AR) can make an important contribution to understanding grammar teaching, as it provides an avenue for the investigation of dif…
  crossref Melissa Reed, Phil Chappell 2024-12-02T13:08:45Z 置信度 0.82 psychologycomputer sciencemathematics educationcognitive scienceneuroscience
• From action research to higher degree research
  One of the key outcomes of undertaking action research (AR) is enhancing practitioner learning through making changes to current teaching practice. The process of cyclical investigation of a specific educational issue, central to AR, is also an opportunity for…
  crossref Bianka Malecka 2024-12-02T13:08:45Z 置信度 0.82 psychologymathematics educationmedical educationsociologyknowledge management
• Leadership
  The topic of Chapter 7 is leadership. This chapter approaches the question of what leadership is by focusing on discourse. It explores how leadership is accomplished in and through communication and provides several examples to illustrate that leadership is of…
  crossref Stephanie Schnurr 2024-06-24T09:08:29Z 置信度 0.82 transformative learningengineering ethicscognitive scienceknowledge managementmathematics education
• The neural dynamics of natural action understanding
  Humans rapidly make sense of an ever-changing visual world, extracting information about people’s actions in a wide range of settings. Yet it remains unclear how the brain processes this complex information, from the extraction of perceptual details to the eme…
  crossref Diana C Dima, Jody C Culham, Yalda Mohsenzadeh 2024-09-27T22:31:21Z 置信度 0.82 psychologyneurosciencecs.cvcognitive psychologycognitive science
• MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
  Human beings possess the capability to multiply a mélange of multisensory cues while actively exploring and interacting with the 3D world. Current multi-modal large language models, however, passively absorb sensory data as inputs, lacking the capacity to acti…
  crossref Yining Hong, Zishuo Zheng, Peihao Chen, Yian Wang 等 2024-09-16T13:34:53Z 置信度 0.82 cs.aiartificial intelligenceembodied cognitioncs.cllarge language models
• A method for stochastic human action prediction based on denoising diffusion probability model
  This paper proposes a stochastic human action prediction method based on denoising diffusion probability model to address the shortcomings of current motion prediction methods, such as insufficient diversity and deviation of prediction results from reasonable …
  crossref Yulin Wang, Gang Mou, Yuewen Zhao, Tao Song 2025-01-17T15:53:32Z 置信度 0.78 cs.lgcomputer and information sciencescs.cvconvolutional neural networkcomputer vision and pattern recognition
• Between bodily action and conventionalized structure: The neural mechanisms of constructed action in sign language comprehension
  Sign languages (SLs) are expressed through different bodily actions, ranging from re-enactment of physical events (constructed action, CA) to sequences of lexical signs with internal structure (plain telling, PT). Despite the prevalence of CA in signed interac…
  crossref Doris Hernández, Anna Puupponen, Jarkko Keränen, Gerardo Ortega 等 2024-04-11T18:30:27Z 置信度 0.82 medicinepsychologyneurosciencegeologybiology
• How Accurate Can Large Vision Language Model Perform for Images with Compression Degradation?
  The rapid evolution of Large Language Models (LLMs) has spurred the development of Large Vision Language Models (LVLMs), which demonstrate remarkable proficiency in various computer vision tasks through corresponding input prompts. These models perform impress…
  crossref Xiaohan Fang, Peilin Chen, Meng Wang, Shiqi Wang 2025-01-27T18:37:05Z 置信度 0.82 artificial intelligencecomputer sciencecs.cvcomputer and information sciencescs.lg
• TQRFormer: Tubelet query recollection transformer for action detection
  crossref Xiangyang Wang, Kun Yang, Qiang Ding, Rui Wang 等 2024-04-28T21:48:04Z 置信度 0.66
• The “Complex Dynamic Model of Autonomy Development” in Action: A Longitudinal Multiple Case Study on Language Learners’ Trajectories
  This paper explores the autonomy development in the language learning trajectories of two English major students within the complexity paradigm (Larsen-Freeman, 1997, 2017; Larsen-Freeman & Cameron, 2008). Autonomy is viewed as a complex, evolving phenomen…
  crossref Larissa Borges 2024-07-14T02:40:50Z 置信度 0.82 mathematics educationpsychologycomputer scienceartificial intelligencecs.ai
• TexCIL: Text-Guided Continual Learning of Disease with Vision-Language Model
  Current intelligent diagnostic systems often catastrophically forget old knowledge when learning new diseases only from the training dataset of the new diseases. Inspired by human learning of visual classes with the effective help of language, we propose a con…
  crossref Wentao Zhang, Defeng Zhao, Wei-Shi Zheng, Ruixuan Wang 2025-01-10T20:12:45Z 置信度 0.82 cs.cvcs.lgartificial intelligencecomputer sciencecs.ai
• Researching mobile technologies in language teaching
  The use of mobile technologies in the field of English language teaching has become increasingly ‘normalised’. Since the appearance of smartphones in the early 2000s, and of the first methodology books for teachers focusing specifically on the use of mobile de…
  crossref Nicky Hockly 2024-12-02T13:08:45Z 置信度 0.82 computer sciencepsychologymathematics educationdata sciencecognitive science
• Action entrepreneuriale, incertitude et vision : l’apport de l’école autrichienne
  Face à l’incertitude entourant l’action des autres individus, l’évolution de la conjoncture, ou l’issue de leur propre action, les individus forment des jugements et des plans d’action. Les entrepreneurs, au travers de leurs actions, forment des opportunités. …
  crossref Christel Vivel 2025-02-13T20:40:06Z 置信度 0.82 philosophymechanical engineeringpolitical sciencecell biologygenomics
• Sign Language Detection Using Action Recognition LSTM Deep Learning Model
  This project aims to develop a system that can recognize sign language gestures in real-time using computer vision techniques. The system is designed to bridge the communication gap between individuals with different hearing abilities by enabling accurate and …
  crossref N Snehalatha, S Mohana Kumar, H Kavitha, S Nisha 等 2024-10-04T13:33:25Z 置信度 0.82 computer scienceartificial intelligencecs.lgbrain-computer interfacecs.ai
• VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
  crossref Han Huang, Haitian Zhong, Tao Yu, Qiang Liu 等 2025-11-03T11:20:56Z 置信度 0.66
• SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
  crossref Sri Dumpala, Aman Jaiswal, Chandramouli Sastry, Evangelos Milios 等 2025-11-03T11:20:56Z 置信度 0.66
• VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model
  crossref Jinze Yang, Haoran Wang, Zining Zhu, Chenglong Liu 等 2024-12-07T07:55:49Z 置信度 0.63
• The centrality of reflection in action research
  Informed by complexity theory, this chapter argues for the need to emphasise the centrality of reflection in the action research (AR) process. The chapter challenges the causal relationship between AR and change of practice based on technical rationality with …
  crossref Van Canh Le 2024-12-02T13:08:45Z 置信度 0.78 psychologycognitive sciencemathematics educationengineering ethicsmedical education
• OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
  crossref Zihao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin 等 2025-11-03T11:20:56Z 置信度 0.66
• Online learning/hybrid learning and action research
  Online learning and hybrid learning have become increasingly prevalent in recent years, and the field of second language acquisition and foreign language education has not been immune to this trend. In this chapter, I first provide a concise overview of online…
  crossref John I. Liontas 2024-12-02T08:08:45Z 置信度 0.82 mathematics educationcomputer sciencepsychologycs.lgcs.cl
• Teacher emotional development and action research
  Action research (AR) enables teachers to investigate their own work to develop an area of practice, and ultimately, improve students’ experience. AR is a systematic, cyclical process of formulating a plan, acting, observing, and reflecting on the process . AR …
  crossref Stephanie King, Christina Gkonou 2024-12-02T13:08:45Z 置信度 0.82 psychologyprocessmathematics educationengineering ethicscognitive science
• Omni-V2x: A Vision-Language Model for Actionable Insights in Vehicle-to-Everything Systems
  crossref Nicanor Mayumu, Deng Xiaoheng, Patrick Mukala, Saif Ur Rehman Khan 等 2024-11-29T04:38:36Z 置信度 0.66
• Integrating Expert Knowledge with Vision-Language Model for Medical Image Retrieval
  Content-Based Image Retrieval (CBIR) is an image search technique that can offer diagnostic guidance when facing difficult cases in radiology. State-of-the-art approaches propose to extract image features using vision-language models which learn image represen…
  crossref Xiaoyang Wei, Zografoula Vagena, Camille Kurtz, Florence Cloppet 2024-08-22T17:49:54Z 置信度 0.82 cs.lgcs.cvcs.aicomputer sciencecomputer and information sciences
• DriveGenVLM: Real-world Video Generation for Vision Language Model based Autonomous Driving
  The advancement of autonomous driving technologies necessitates increasingly sophisticated methods for understanding and predicting real-world scenarios. Vision language models (VLMs) are emerging as revolutionary tools with significant potential to influence …
  crossref Yongjie Fu, Anmol Jain, Xu Chen, Zhaobin Mo 等 2024-12-13T18:50:13Z 置信度 0.82 cs.aics.lgcs.cvcomputer and information sciencesartificial intelligence
• Vision-Language Model-based Physical Reasoning for Robot Liquid Perception
  There is a growing interest in applying large language models (LLMs) in robotic tasks, due to their remarkable reasoning ability and extensive knowledge learned from vast training corpora. Grounding LLMs in the physical world remains an open challenge as they …
  crossref Wenqiang Lai, Tianwei Zhang, Tin Lun Lam, Yuan Gao 2024-12-25T14:17:39Z 置信度 0.82 computer scienceartificial intelligencecomputer and information sciencescs.airobotics
• Exploring Professional Communication
  Routledge Introductions to Applied Linguistics is a series of introductory level textbooks covering the core topics in applied linguistics, primarily designed for those beginning postgraduate studies, or taking an introductory MA course, as well as for advance…
  crossref Stephanie Schnurr 2024-06-24T09:08:29Z 置信度 0.82 psychologyastrobiologycomputer sciencegeologyperception
• Creativity in language teacher action research
  Language teacher action research (AR) may be understood as a product of necessity, as teachers need to grapple with issues stemming from the complex and uncertain ecology of a language curriculum. Necessity leads them to engage with processes and products that…
  crossref Darío Luis Banegas, Luis S. Villacañas de Castro 2024-12-02T13:08:45Z 置信度 0.82 psychologymathematics educationecosystemcs.aicomputer science
• Vision-Language Models for Biomedical Applications
  Vision-language models (VLMs) are transforming the landscape of biomedical research and healthcare by enabling the seamless integration and interpretation of complex multimodal data, including medical images and clinical texts. Recognizing the growing impact o…
  crossref Surendrabikram Thapa, Usman Naseem, Luping Zhou, Jinman Kim 2024-10-02T18:18:42Z 置信度 0.82 health carecomputer scienceartificial intelligencedata scienceworkflow
• Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
  crossref Yanan Zhang, Jiangmeng Li, Lixiang Liu, Wenwen Qiang 2025-11-03T11:20:56Z 置信度 0.66
• Action Classification from Motion Flow
  How do we classify other people's actions, and what information do we use to do it? Ever since Johansson's introduction of Point Light Displays (PLDs) it has been known that human observers can integrate a few moving points into a human form and, in many cases…
  crossref Uriel Gonzalez, Nathan Destler, Jacob Feldman 2024-09-27T21:33:09Z 置信度 0.82 artificial intelligencepsychologycomputer sciencecs.airobotics
• Vision-Language Model for Generating Textual Descriptions From Clinical Images: Model Development and Validation Study
  Background The automatic generation of radiology reports, which seeks to create a free-text description from a clinical radiograph, is emerging as a pivotal intersection between clinical medicine and artificial intelligence. Leveraging natural language process…
  crossref Jia Ji, Yongshuai Hou, Xinyu Chen, Youcheng Pan 等 2024-02-08T09:00:28Z 置信度 0.82 medicinecomputer sciencecs.lgartificial intelligencecs.ai
• ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
  Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored.In this study, we present a pioneering measurement framework, ModSCAN, to SCAN the ste…
  crossref Yukun Jiang, Zheng Li, Xinyue Shen, Yugeng Liu 等 2024-11-27T22:28:12Z 置信度 0.82 cs.aipsychologycs.clcs.lgcs.cv
• SSAT-Adapter: Enhancing Vision-Language Model Few-shot Learning with Auxiliary Tasks
  Traditional deep learning models often struggle in few-shot learning scenarios, where limited labeled data is available. While the Contrastive Language-Image Pre-training (CLIP) model demonstrates impressive zero-shot capabilities, its performance in few-shot …
  crossref Bowen Chen, Yun Sing Koh, Gillian Dobbie 2024-10-26T06:59:49Z 置信度 0.82 cs.lgartificial intelligencecs.aics.cvcomputer and information sciences
• Employing Glyphic Information for Chinese Event Extraction with Vision-Language Model
  As a complex task that requires rich information input, features from various aspects have been utilized in event extraction.However, most of the previous works ignored the value of glyph, which could contain enriched semantic information and can not be fully …
  crossref Xiaoyi Bao, Jinghang Gu, Zhongqing Wang, Minjie Qiang 等 2024-11-27T22:28:12Z 置信度 0.82 cs.lgcs.cvcomputer sciencecomputer and information sciencescs.ai
• Pix2Planning: End-to-End Planning by Vision-language Model for Autonomous Driving on Carla Simulator
  The end-to-end neural network has become a hot topic in recent years. Compared with traditional module-based solutions, the end-to-end paradigm is able to reduce the accumulated error and avoid information loss, so that it earns great attention in autonomous d…
  crossref Xiangru Mu, Tong Qin, Songan Zhang, Chunjing Xu 等 2024-07-15T17:19:28Z 置信度 0.82 cs.cvcs.lgcs.aicomputer and information sciencescomputer science
• Visuo-Tactile Zero-Shot Object Recognition with Vision-Language Model
  Tactile perception is vital, especially when distinguishing visually similar objects. We propose an approach to incorporate tactile data into a Vision-Language Model (VLM) for visuo-tactile zero-shot object recognition. Our approach leverages the zero-shot cap…
  crossref Shiori Ueda, Atsushi Hashimoto, Masashi Hamaya, Kazutoshi Tanaka 等 2024-12-25T14:17:39Z 置信度 0.82 computer and information sciencescs.cvcomputer vision and pattern recognitionroboticscs.lg
• Reinforcement Learning Friendly Vision-Language Model for Minecraft
  crossref Haobin Jiang, Junpeng Yue, Hao Luo, Ziluo Ding 等 2024-11-20T08:45:18Z 置信度 0.66