仿生智能 · 全部实体（第 82 / 100 页）

本页收录第 8101–8200 条，共 10000 条 · 返回 仿生智能 首页

• ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding
  Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare ev…
  arxiv Liang Shi, Boyu Jiang, Tong Zeng, Feng Guo 2024-10-01T18:10:23Z 置信度 0.78 cs.CV
• Image Generators are Generalist Vision Learners
  Recent works show that image and video generators exhibit zero-shot visual understanding behaviors, in a way reminiscent of how LLMs develop emergent capabilities of language understanding and reasoning from generative pretraining. While it has long been conje…
  arxiv Valentin Gabeur, Shangbang Long, Songyou Peng, Paul Voigtlaender 等 2026-04-22T08:23:48Z 置信度 0.78 cs.CVcs.AI
• Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object Interaction
  This paper presents a novel approach that integrates vision foundation models with reinforcement learning to enhance object interaction capabilities in simulated environments. By combining the Segment Anything Model (SAM) and YOLOv5 with a Proximal Policy Opti…
  arxiv Ahmad Farooq, Kamran Iqbal 2025-08-07T20:29:01Z 置信度 0.78 cs.ROcs.AIcs.CVcs.LGeess.SY
• A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers
  When it comes to clinical images, automatic segmentation has a wide variety of applications and a considerable diversity of input domains, such as different types of Magnetic Resonance Images (MRIs) and Computerized Tomography (CT) scans. This heterogeneity is…
  arxiv Matteo Bastico, David Ryckelynck, Laurent Corté, Yannick Tillier 等 2023-10-09T09:51:44Z 置信度 0.78 eess.IVcs.CVcs.LG
• TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints
  Reasoning about fine-grained spatial relationships in warehouse-scale environments poses a significant challenge for existing vision-language models (VLMs), which often struggle to comprehend 3D layouts, object arrangements, and multimodal cues in real-world i…
  arxiv Vinh-Thuan Ly, Hoang M. Truong, Xuan-Huong Nguyen 2025-08-25T01:36:22Z 置信度 0.78 cs.CV
• Adversarial Vision Challenge
  The NIPS 2018 Adversarial Vision Challenge is a competition to facilitate measurable progress towards robust machine vision models and more generally applicable adversarial attacks. This document is an updated version of our competition proposal that was accep…
  arxiv Wieland Brendel, Jonas Rauber, Alexey Kurakin, Nicolas Papernot 等 2018-08-06T16:13:43Z 置信度 0.78 cs.LGcs.CVstat.ML
• Vicinity Vision Transformer
  Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory foot…
  arxiv Weixuan Sun, Zhen Qin, Hui Deng, Jianyuan Wang 等 2022-06-21T17:33:53Z 置信度 0.78 cs.CV
• Universal Object Detection with Large Vision Model
  Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system. Such systems have the potential to address a wide range of vision tasks simultaneously, without being limited to specific pro…
  arxiv Feng Lin, Wenze Hu, Yaowei Wang, Yonghong Tian 等 2022-12-19T12:40:13Z 置信度 0.78 cs.CV
• Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism
  Computer vision is a growing field with a lot of new applications in automation and robotics, since it allows the analysis of images and shapes for the generation of numerical or analytical information. One of the most used method of information extraction is …
  arxiv Dominique Beaini, Sofiane Achiche, Yann-Seing Law-Kam Cio, Maxime Raison 2018-06-20T21:31:00Z 置信度 0.78 cs.CV
• Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
  Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the Vision-Language-Vision (VLV) au…
  arxiv Tiezheng Zhang, Yitong Li, Yu-cheng Chou, Jieneng Chen 等 2025-07-09T17:59:04Z 置信度 0.78 cs.CV
• What Does TERRA-REF's High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community?
  A core objective of the TERRA-REF project was to generate an open-access reference dataset for the evaluation of sensing technologies to study plants under field conditions. The TERRA-REF program deployed a suite of high-resolution, cutting edge technology sen…
  arxiv David LeBauer, Max Burnette, Noah Fahlgren, Rob Kooper 等 2021-07-29T15:01:29Z 置信度 0.78 cs.CVcs.LG
• The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision Models
  Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation proces…
  arxiv Varun Jampani, Sebastian Nowozin, Matthew Loper, Peter V. Gehler 2014-02-04T20:52:26Z 置信度 0.78 cs.CVcs.LGstat.ML
• Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition
  Automatic dietary assessment based on food images remains a challenge, requiring precise food detection, segmentation, and classification. Vision-Language Models (VLMs) offer new possibilities by integrating visual and textual reasoning. In this study, we eval…
  arxiv Sergio Romero-Tapiador, Ruben Tolosana, Blanca Lacruz-Pleguezuelos, Laura Judith Marcos Zambrano 等 2025-04-09T14:33:59Z 置信度 0.78 cs.CVcs.AI
• Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement
  Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collect…
  arxiv Zijie Yue, Miaojing Shi, Hanli Wang, Shuai Ding 等 2024-07-11T13:45:50Z 置信度 0.78 cs.CV
• Vision-LSTM: xLSTM as Generic Vision Backbone
  Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which over…
  arxiv Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter 等 2024-06-06T17:49:21Z 置信度 0.78 cs.CVcs.AIcs.LG
• Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders
  Large vision--language models (VLMs) often use a frozen vision backbone, whose image features are mapped into a large language model through a lightweight connector. While transformer-based encoders are the standard visual backbone, we ask whether state space …
  arxiv Shang-Jui Ray Kuo, Paola Cascante-Bonilla 2026-03-19T17:56:32Z 置信度 0.78 cs.CVcs.LG
• Second Croatian Computer Vision Workshop (CCVW 2013)
  Proceedings of the Second Croatian Computer Vision Workshop (CCVW 2013, http://www.fer.unizg.hr/crv/ccvw2013) held September 19, 2013, in Zagreb, Croatia. Workshop was organized by the Center of Excellence for Computer Vision of the University of Zagreb.
  arxiv Sven Lončarić, Siniša Šegvić 2013-10-01T14:26:29Z 置信度 0.78 cs.CV
• Steering CLIP's vision transformer with sparse autoencoders
  While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by training SAEs on CLIP'…
  arxiv Sonia Joseph, Praneet Suresh, Ethan Goldfarb, Lorenz Hufe 等 2025-04-11T17:56:09Z 置信度 0.78 cs.CVcs.AIcs.LG
• Vision Generalist Model: A Survey
  Recently, we have witnessed the great success of the generalist model in natural language processing. The generalist model is a general framework trained with massive data and is able to process various downstream tasks simultaneously. Encouraged by their impr…
  arxiv Ziyi Wang, Yongming Rao, Shuofeng Sun, Xinrun Liu 等 2025-06-11T17:23:41Z 置信度 0.78 cs.CVcs.AI
• Multi-Exit Vision Transformer for Dynamic Inference
  Deep neural networks can be converted to multi-exit architectures by inserting early exit branches after some of their intermediate layers. This allows their inference process to become dynamic, which is useful for time critical IoT applications with stringent…
  arxiv Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis 2021-06-29T09:01:13Z 置信度 0.78 cs.CV
• BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation
  The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic data generators offe…
  arxiv Yunhao Ge, Yihe Tang, Jiashu Xu, Cem Gokmen 等 2024-05-15T17:57:56Z 置信度 0.78 cs.CV
• Crowdsourcing in Computer Vision
  Computer vision systems require large amounts of manually annotated data to properly learn challenging visual concepts. Crowdsourcing platforms offer an inexpensive method to capture human knowledge and understanding, for a vast number of visual perception tas…
  arxiv Adriana Kovashka, Olga Russakovsky, Li Fei-Fei, Kristen Grauman 2016-11-07T16:11:19Z 置信度 0.78 cs.CVcs.HC
• Super Vision Transformer
  We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing improved image recognition …
  arxiv Mingbao Lin, Mengzhao Chen, Yuxin Zhang, Chunhua Shen 等 2022-05-23T15:42:12Z 置信度 0.78 cs.CV
• FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
  Federated Learning (FL) is a distributed learning paradigm that can learn a global or personalized model from decentralized datasets on edge devices. However, in the computer vision domain, model performance in FL is far behind centralized training due to the …
  arxiv Chaoyang He, Alay Dilipbhai Shah, Zhenheng Tang, Di Fan1Adarshan Naiynar Sivashunmugam 等 2021-11-22T09:26:08Z 置信度 0.78 cs.CVcs.AIcs.LG
• On the Application of Egocentric Computer Vision to Industrial Scenarios
  Egocentric vision aims to capture and analyse the world from the first-person perspective. We explore the possibilities for egocentric wearable devices to improve and enhance industrial use cases w.r.t. data collection, annotation, labelling and downstream app…
  arxiv Vivek Chavan, Oliver Heimann, Jörg Krüger 2024-06-11T21:48:20Z 置信度 0.78 cs.CV
• PatchRot: A Self-Supervised Technique for Training Vision Transformers
  Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised learning techniques alleviate this problem by learning features similar to supe…
  arxiv Sachin Chhabra, Prabal Bijoy Dutta, Hemanth Venkateswara, Baoxin Li 2022-10-27T18:55:12Z 置信度 0.78 cs.CV
• Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
  Large Vision-Language Models (LVLMs) typically follow a two-stage training paradigm-pretraining and supervised fine-tuning. Recently, preference optimization, derived from the language domain, has emerged as an effective post-training reinforcement strategy to…
  arxiv Yufei Zhan, Yousong Zhu, Shurong Zheng, Hongyin Zhao 等 2025-03-23T10:21:14Z 置信度 0.78 cs.CVcs.AI
• EasyARC: Evaluating Vision Language Models on True Visual Reasoning
  Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking true visual reasoning w…
  arxiv Mert Unsal, Aylin Akkus 2025-06-13T09:03:33Z 置信度 0.78 cs.CVcs.LG
• Vision Transformer with Quadrangle Attention
  Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic, constrains the flexibilit…
  arxiv Qiming Zhang, Jing Zhang, Yufei Xu, Dacheng Tao 2023-03-27T11:13:50Z 置信度 0.78 cs.CV
• High Resolution Multi-Scale RAFT (Robust Vision Challenge 2022)
  In this report, we present our optical flow approach, MS-RAFT+, that won the Robust Vision Challenge 2022. It is based on the MS-RAFT method, which successfully integrates several multi-scale concepts into single-scale RAFT. Our approach extends this method by…
  arxiv Azin Jahedi, Maximilian Luz, Lukas Mehl, Marc Rivinius 等 2022-10-30T17:48:11Z 置信度 0.78 cs.CV
• Domain Adaptation with a Single Vision-Language Embedding
  Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in real-world autonomous driving scenarios, especially under rare or adverse conditions. In…
  arxiv Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez 等 2024-10-28T17:59:53Z 置信度 0.78 cs.CVcs.LG
• FALQON-MST: A Fully Quantum Framework for Graph Optimization in Vision Systems
  Finding the minimum spanning tree (MST) of a graph is an important task in computer vision, as it enables a sparse and low-cost representation of connectivity among elements (such as superpixels, points, or regions), which is useful for tasks such as segmentat…
  arxiv Guilherme E. L. Pexe, Lucas A. M. Rattighieri, Leandro A. Passos, Douglas Rodrigues 等 2026-03-21T07:34:07Z 置信度 0.78 quant-ph
• A Survey on Computer Vision based Human Analysis in the COVID-19 Era
  The emergence of COVID-19 has had a global and profound impact, not only on society as a whole, but also on the lives of individuals. Various prevention measures were introduced around the world to limit the transmission of the disease, including face masks, m…
  arxiv Fevziye Irem Eyiokur, Alperen Kantarcı, Mustafa Ekrem Erakın, Naser Damer 等 2022-11-07T17:20:39Z 置信度 0.78 cs.CVeess.IV
• GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs
  Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. To solve this issue, we propose a new method for designing V…
  arxiv Mustafa Munir, William Avery, Md Mostafijur Rahman, Radu Marculescu 2024-05-10T23:21:16Z 置信度 0.78 cs.CVcs.AIcs.LG
• A Comparative Study of Graph Matching Algorithms in Computer Vision
  The graph matching optimization problem is an essential component for many tasks in computer vision, such as bringing two deformable objects in correspondence. Naturally, a wide range of applicable algorithms have been proposed in the last decades. Since a com…
  arxiv Stefan Haller, Lorenz Feineis, Lisa Hutschenreiter, Florian Bernard 等 2022-07-01T09:37:34Z 置信度 0.78 cs.CVmath.OC
• NITEC: Versatile Hand-Annotated Eye Contact Dataset for Ego-Vision Interaction
  Eye contact is a crucial non-verbal interaction modality and plays an important role in our everyday social life. While humans are very sensitive to eye contact, the capabilities of machines to capture a person's gaze are still mediocre. We tackle this challen…
  arxiv Thorsten Hempel, Magnus Jung, Ahmed A. Abdelrahman, Ayoub Al-Hamadi 2023-11-08T07:42:31Z 置信度 0.78 cs.CV
• Predicting the Future from First Person (Egocentric) Vision: A Survey
  Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour. The research in egocentric video analysis is developing rapidly thanks to the i…
  arxiv Ivan Rodin, Antonino Furnari, Dimitrios Mavroedis, Giovanni Maria Farinella 2021-07-28T14:58:13Z 置信度 0.78 cs.CV
• ViR: Towards Efficient Vision Retention Backbones
  Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for large scale training. Although the training parallelism of self-attention mecha…
  arxiv Ali Hatamizadeh, Michael Ranzinger, Shiyi Lan, Jose M. Alvarez 等 2023-10-30T16:55:50Z 置信度 0.78 cs.CVcs.AIcs.LG
• Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
  Prompt learning has emerged as an efficient and effective method for fine-tuning vision-language models such as CLIP. While many studies have explored generalisation abilities of these models in few-shot classification tasks and a few studies have addressed fa…
  arxiv Myong Chol Jung, Joanna Dipnall, Belinda Gabbe, He Zhao 2024-05-25T06:46:16Z 置信度 0.78 cs.CV
• Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
  In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets. At the same time, there has been renewed interest in 3D scene represen…
  arxiv Mukund Varma T, Peihao Wang, Zhiwen Fan, Zhangyang Wang 等 2024-03-27T18:13:16Z 置信度 0.78 cs.CV
• PatchDropout: Economizing Vision Transformers Using Patch Dropout
  Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their use in many applications, especially those that depend on high-resolution images, …
  arxiv Yue Liu, Christos Matsoukas, Fredrik Strand, Hossein Azizpour 等 2022-08-10T14:08:55Z 置信度 0.78 cs.CVcs.LG
• Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
  Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hindered by the lack of accessible framewo…
  arxiv Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson 等 2025-04-28T04:31:24Z 置信度 0.78 cs.CVcs.AIcs.LG
• Computer Vision Systems in Road Vehicles: A Review
  The number of road vehicles significantly increased in recent decades. This trend accompanied a build-up of road infrastructure and development of various control systems to increase road traffic safety, road capacity and travel comfort. In traffic safety sign…
  arxiv Kristian Kovačić, Edouard Ivanjko, Hrvoje Gold 2013-10-01T14:19:11Z 置信度 0.78 cs.CV
• PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
  Omnidirectional vision, using 360-degree vision to understand the environment, has become increasingly critical across domains like robotics, industrial inspection, and environmental monitoring. Compared to traditional pinhole vision, omnidirectional vision pr…
  arxiv Xu Zheng, Chenfei Liao, Ziqiao Weng, Kaiyu Lei 等 2025-09-16T11:54:37Z 置信度 0.78 cs.CV
• MuSViT: A Foundation Vision Model for Sheet Music Representation
  Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce …
  arxiv Carlos Penarrubia, Antonio Rios-Vila, Eliseo Fuentes-Martinez, Juan C. Martinez-Sevilla 等 2026-06-30T15:27:12Z 置信度 0.78 cs.CV
• Hand-Priming in Object Localization for Assistive Egocentric Vision
  Egocentric vision holds great promises for increasing access to visual information and improving the quality of life for people with visual impairments, with object recognition being one of the daily challenges for this population. While we strive to improve r…
  arxiv Kyungjun Lee, Abhinav Shrivastava, Hernisa Kacorri 2020-02-28T05:32:36Z 置信度 0.78 cs.CVcs.HC
• SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks
  The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based architecture into Spiking Neural Networks (SNNs). While existing methods propos…
  arxiv Xinyu Shi, Zecheng Hao, Zhaofei Yu 2024-03-21T11:16:42Z 置信度 0.78 cs.NEcs.CVcs.LG
• Masked Vision-Language Transformers for Scene Text Recognition
  Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel Masked Vision-Language Tr…
  arxiv Jie Wu, Ying Peng, Shengming Zhang, Weigang Qi 等 2022-11-09T10:28:23Z 置信度 0.78 cs.CV
• Deep Learning vs. Traditional Computer Vision
  Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL h…
  arxiv Niall O' Mahony, Sean Campbell, Anderson Carvalho, Suman Harapanahalli 等 2019-10-30T12:25:10Z 置信度 0.78 cs.CVcs.LG
• FairViT: Fair Vision Transformer via Adaptive Masking
  Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential in various computer vision tasks. The wide deployment of ViT in real-world tasks requires a thorough understanding of the societal impact of the model. However…
  arxiv Bowei Tian, Ruijie Du, Yanning Shen 2024-07-20T08:10:37Z 置信度 0.78 cs.CVcs.CY
• AdaptViG: Adaptive Vision GNN with Exponential Decay Gating
  Vision Graph Neural Networks (ViGs) offer a new direction for advancements in vision architectures. While powerful, ViGs often face substantial computational challenges stemming from their graph construction phase, which can hinder their efficiency. To address…
  arxiv Mustafa Munir, Md Mostafijur Rahman, Radu Marculescu 2025-11-13T04:16:20Z 置信度 0.78 cs.CVcs.AIcs.LG
• Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
  Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency, many publications rely on MACs (Multiply Accumulate operations) as a predictor …
  arxiv Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni 2026-03-27T16:05:20Z 置信度 0.78 cs.CVcs.AI
• VLP: A Survey on Vision-Language Pre-training
  In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid …
  arxiv Feilong Chen, Duzhen Zhang, Minglun Han, Xiuyi Chen 等 2022-02-18T07:54:02Z 置信度 0.78 cs.CVcs.CL
• Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
  The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision models encode the I…
  arxiv Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff, Changbai Li 等 2025-05-21T19:38:48Z 置信度 0.78 cs.CVcs.LG
• Is Tracking really more challenging in First Person Egocentric Vision?
  Visual object tracking and segmentation are becoming fundamental tasks for understanding human activities in egocentric vision. Recent research has benchmarked state-of-the-art methods and concluded that first person egocentric vision presents challenges compa…
  arxiv Matteo Dunnhofer, Zaira Manigrasso, Christian Micheloni 2025-07-21T19:25:50Z 置信度 0.78 cs.CV
• Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
  Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In…
  arxiv Yongchao Feng, Yajie Liu, Shuai Yang, Wenrui Cai 等 2025-04-13T08:28:13Z 置信度 0.78 cs.CVcs.AI
• Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
  Transformers have revolutionized computer vision and natural language processing, but their high computational complexity limits their application in high-resolution image processing and long-context analysis. This paper introduces Vision-RWKV (VRWKV), a model…
  arxiv Yuchen Duan, Weiyun Wang, Zhe Chen, Xizhou Zhu 等 2024-03-04T18:46:20Z 置信度 0.78 cs.CV
• Evaluating Vision-Language Models as Evaluators in Path Planning
  Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the …
  arxiv Mohamed Aghzal, Xiang Yue, Erion Plaku, Ziyu Yao 2024-11-27T19:32:03Z 置信度 0.78 cs.CVcs.CL
• Searching for Task-Specific Vision Paths: Evolutionary Block Pruning Across Vision-Language Models
  Vision-language models normally execute the same complete vision encoder for every question, even when OCR, counting, object, attribute, and spatial queries may not require identical computation. We study whether fixed-budget combinations of vision blocks can …
  arxiv Tarun Tomar 2026-07-19T03:43:26Z 置信度 0.78 cs.CV
• ObjectTransforms for Uncertainty Quantification and Reduction in Vision-Based Perception for Autonomous Vehicles
  Reliable perception is fundamental for safety critical decision making in autonomous driving. Yet, vision based object detector neural networks remain vulnerable to uncertainty arising from issues such as data bias and distributional shifts. In this paper, we …
  arxiv Nishad Sahu, Shounak Sural, Aditya Satish Patil, Ragunathan 等 2025-10-17T18:04:31Z 置信度 0.78 cs.CV
• Inference via Sparse Coding in a Hierarchical Vision Model
  Sparse coding has been incorporated in models of the visual cortex for its computational advantages and connection to biology. But how the level of sparsity contributes to performance on visual tasks is not well understood. In this work, sparse coding has been…
  arxiv Joshua Bowren, Luis Sanchez-Giraldo, Odelia Schwartz 2021-08-03T14:55:33Z 置信度 0.78 cs.CVcs.LG
• Surface Analysis with Vision Transformers
  The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds. Many of those methods have shown design limitations resulting in poor modelling of long-range associations, as the generali…
  arxiv Simon Dahan, Logan Z. J. Williams, Abdulah Fawaz, Daniel Rueckert 等 2022-05-31T14:41:01Z 置信度 0.78 cs.CVcs.LGq-bio.NC
• Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
  Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We observe a regional-to-global perception gap: the same MLLM answers fine-grained ques…
  arxiv Qianhao Yuan, Jie Lou, Xing Yu, Hongyu Lin 等 2026-05-18T17:57:04Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• Vision-Language Memory for Spatial Reasoning
  Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a semantic-geometric misalignm…
  arxiv Zuntao Liu, Yi Du, Taimeng Fu, Shaoshu Su 等 2025-11-25T18:59:02Z 置信度 0.78 cs.CV
• Tactile Modality Fusion for Vision-Language-Action Models
  We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While advances in VLAs have introduced robot policies that are both generalizable and semantically grounded, these model…
  arxiv Charlotte Morissette, Amin Abyaneh, Wei-Di Chang, Anas Houssaini 等 2026-03-15T20:57:51Z 置信度 0.78 cs.ROcs.CVcs.LG
• Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
  This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years. We group these approaches into three categories: ($i$) VLP for image-text tasks, such as image captioning, image-text retr…
  arxiv Zhe Gan, Linjie Li, Chunyuan Li, Lijuan Wang 等 2022-10-17T17:11:36Z 置信度 0.78 cs.CVcs.CL
• A Comprehensive Study of Vision Transformers on Dense Prediction Tasks
  Convolutional Neural Networks (CNNs), architectures consisting of convolutional layers, have been the standard choice in vision tasks. Recent studies have shown that Vision Transformers (VTs), architectures based on self-attention modules, achieve comparable p…
  arxiv Kishaan Jeeveswaran, Senthilkumar Kathiresan, Arnav Varma, Omar Magdy 等 2022-01-21T13:18:16Z 置信度 0.78 cs.CV
• Vision-Centric BEV Perception: A Survey
  In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion. Th…
  arxiv Yuexin Ma, Tai Wang, Xuyang Bai, Huitong Yang 等 2022-08-04T17:53:17Z 置信度 0.78 cs.CV
• Evaluation of Vision-LLMs in Surveillance Video
  The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of anomalous or criminal …
  arxiv Pascal Benschop, Cristian Meo, Justin Dauwels, Jelte P. Mense 2025-10-27T10:27:02Z 置信度 0.78 cs.CV
• Sparse Modeling for Image and Vision Processing
  In recent years, a large amount of multi-disciplinary research has been conducted on sparse models and their applications. In statistics and machine learning, the sparsity principle is used to perform model selection---that is, automatically selecting a simple…
  arxiv Julien Mairal, Francis Bach, Jean Ponce 2014-11-12T16:33:37Z 置信度 0.78 cs.CV
• Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing
  Face Anti-Spoofing (FAS) remains challenging due to the requirement for robust domain generalization across unseen environments. While recent trends leverage Vision-Language Models (VLMs) for semantic supervision, these multimodal approaches often demand prohi…
  arxiv Mika Feng, Pierre Gallin-Martel, Koichi Ito, Takafumi Aoki 2026-04-21T08:05:21Z 置信度 0.78 cs.CV
• PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers
  Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery driven by a fine-grained classification task make very restrictive assumptions on…
  arxiv Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos 2024-07-05T14:24:37Z 置信度 0.78 cs.CVcs.AIcs.LG
• KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition
  The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold neural networks (KANs), based on the Kolmogorov-Arnold representation theorem, have shown potential to replace…
  arxiv Zhaoxiang Liu, Zhicheng Ma, Kaikai Zhao, Kai Wang 等 2026-04-25T14:14:41Z 置信度 0.78 cs.CV
• Domain Generalisation with Bidirectional Encoder Representations from Vision Transformers
  Domain generalisation involves pooling knowledge from source domain(s) into a single model that can generalise to unseen target domain(s). Recent research in domain generalisation has faced challenges when using deep learning models as they interact with data …
  arxiv Hamza Riaz, Alan F. Smeaton 2023-07-16T17:50:37Z 置信度 0.78 cs.CVcs.LG
• How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks
  Multimodal foundation models (MFMs), such as GPT-4o, have recently made remarkable progress. However, their detailed visual understanding beyond question answering remains unclear. In this paper, we benchmark popular MFMs (GPT-4o, o4-mini, Gemini 1.5 Pro and G…
  arxiv Rahul Ramachandran, Ali Garjani, Roman Bachmann, Andrei Atanov 等 2025-07-02T17:59:07Z 置信度 0.78 cs.CVcs.AIcs.LG
• Artificial vision: what people with bionic eyes see
  crossref Matthew Petoe, Lauren Ayton, Mohit Shivdasani 2025-08-26T06:19:03Z 置信度 0.70
• Machine Vision Based Measurement of Dynamic Contact Angles in Microchannel Flows
  crossref Valtteri Heiskanen, Kalle Marjanen, Pasi Kallio 2009-01-03T09:13:01Z 置信度 0.70
• BIONIC EYE AND CREATE ARTIFICIAL VISION
  Introduction: There are nearly 40 million cases of blindness in the worldwide, and 124 million people have been affected by low vision. For this reason, researchers are intent on developing new ways to restore vision. One of these efforts was the offer of an i…
  crossref Khadijeh moulaei 2017-06-19T09:31:02Z 置信度 0.70
• A REVIEW ON BIONIC VISION TECHNOLOGY
  Bionic vision technology is a quickly expanding topic that includes creating tools to help people with visual impairments see again.The technology replaces damaged cells and stimulates the visual system using a variety of methods, including retinal implants, c…
  crossref 2023-05-15T18:41:06Z 置信度 0.70
• A Novel Vision Localization Method of Automated Micro-Polishing Robot
  crossref Zhao-jun Yang, Fei Chen, Ji Zhao, Xiao-jie Wu 2009-04-13T04:10:42Z 置信度 0.70
• Biomimetic Autopilot Based on Minimalistic Motion Vision for Navigating along Corridors Comprising U-shaped and S-shaped Turns
  crossref Julien R. Serres, Franck Ruffier 2015-01-15T23:30:13Z 置信度 0.70
• An active stereo vision system based on neural pathways of human binocular motor system
  crossref Yu-zhang Gu, Makoto Sato, Xiao-lin Zhang 2008-01-02T22:36:46Z 置信度 0.70
• Bionic vision technology and implications for sport management
  One’s vision impacts sport performance through an ability to perceive, track, hit or shoot more proficiently. Achieving improvements in sight can tend to lead to greater sporting success. Methods or strategies for improving one’s eyesight are legal in sport. T…
  crossref Cheryl Mallen 2019-02-18T17:16:33Z 置信度 0.70
• Ultrabroadband Detection and Self-Powered Functionality in Quasi-One-Dimensional Nb3Se12I Nanowire Photodetectors for Bionic Vision Applications
  The burgeoning fields of the Internet of things (IoT) and artificial intelligence (AI) have escalated the demands for image sensing technologies, necessitating advancements in sensor efficiency and functionality. Traditional image sensors, structured on von Ne…
  crossref 2025-03-27T23:10:13Z 置信度 0.70
• Towards a Smart Bionic Eye: AI-Powered Artificial Vision for the Treatment of Incurable Blindness
  How can we return a functional form of sight to people who are living with incurable blindness? Despite recent advances in the development of visual neuroprostheses, the quality of current prosthetic vision is still rudimentary and does not differ much across …
  crossref Michael Beyeler, Melani Sanchez Garcia 2022-06-17T15:12:06Z 置信度 0.70
• Experiment research on binocular perceptual characteristics around peripheral vision for development of head mounted display with wide view
  crossref Xiao-guang Li, Jing-long Wu, Sadao Kawamura 2018-02-08T09:32:47Z 置信度 0.70
• Vision-based batting training system
  Among all of the skills required in sports, batting a ball is one of the most difficult. In this paper, we propose a vision-based batting training system for batting practice. Our goal is to predict the flying trajectory of a batted ball by using a high-speed …
  crossref Hsiu-Min Chuang, Yang Liu, Akio Namiki 2018-01-22T17:39:22Z 置信度 0.70
• 1-DOF Beam-Driven Bionic Robotic Fish
  Currently, the prevailing methods to design and manufacture fish-like robots focused on articulated way with multi-degree-of-freedom structure. For increasing the reliability and reducing the cost of manufacturing and controlling, a 1-DOF beam-driven bionic ro…
  crossref Jialin Xu, Xingsong Wang 2009-01-16T11:43:02Z 置信度 0.70
• Modeling the Bionic Compound Eye Vision System Based on Graph Neural Networks_supp1-3575172.pdf
  crossref Yuan Li 2025-06-06T13:43:49Z 置信度 0.70
• Method of gaze extraction in bionic vision
  Aiming at the low efficiency of information processing in a robot vision system, our work studies how to extract fixed points during tasks so that significant and interesting target areas in the scene can be located. First, the architecture of a gaze extractio…
  crossref Yingni Duan, Guozhu Li, Yanzi Deng 2023-01-04T18:55:16Z 置信度 0.70
• Channel Flow Field Recognition Method and Application Based on Eagle-Eye Bionic Vision
  The International Association for Hydro-Environment Engineering and Research (IAHR), founded in 1935, is a worldwide independent organisation of engineers and water specialists working in fields related to the hydro-environmental sciences and their practical a…
  crossref Hairong Gao, Zihan Liu, Yu Han 2024-06-18T12:00:55Z 置信度 0.70
• The effect of photoreceptor degeneration on ganglion cell morphology
  ABSTRACT Retinitis pigmentosa refers to a family of inherited photoreceptor degenerations resulting in blindness. During and after photoreceptor loss, neurons of the inner retina are known to undergo plastic changes. Here, we have investigated in detail whethe…
  crossref E.E. O'Brien, U. Greferath, E.L. Fletcher 2013-10-31T11:03:57Z 置信度 0.70
• Pseudo Color Fusion of Infrared and Visible Images Based on the Rattlesnake Vision Imaging System
  crossref Yong Wang, Hongqi Liu, Xiaoguang Wang 2021-12-10T06:48:00Z 置信度 0.70
• Spike-triggered average electrical stimuli as input filters for bionic vision – a perspective.
  Bionic retinal implants are gaining acceptance in the treatment of blindness from degenerative diseases including retinitis pigmentosa and macular degeneration. A current obstacle to the improved performance of such implants is the difficulty of comparing the …
  crossref Daniel Rathbun, Nima Ghorbani, Hamed Shabani, Eberhart Zrenner 等 2018-07-02T07:42:37Z 置信度 0.70
• Monolithic Encapsulation of Implantable Neuroprosthetic Devices Using Liquid Crystal Polymers
  Flexible polymers have gained much attention in the development of low cost, magnetic resonance compatible, and nonfragile implantable medical devices. However, efficacy of the conventional polymer encapsulations containing hybrid interfaces is limited due to …
  openalex Seung Woo Lee, Kyou Sik Min, Joonsoo Jeong, Jung‐Hoon Kim 等 2011-04-06 置信度 0.72 Materials scienceEncapsulation (networking)PolymerPolyimideParylene
• Fascicular Topography of the Human Median Nerve for Neuroprosthetic Surgery
  One of the most sought-after applications of neuroengineering is the communication between the arm and an artificial prosthetic device for the replacement of an amputated hand or the treatment of peripheral nerve injuries. For that, an electrode is placed arou…
  openalex Ignacio Delgado, Jordi Badía, Arán Pascual‐Font, Alfonso Rodríguez‐Baeza 等 2016-07-01 置信度 0.72 NeuroprostheticsFascicleMedicineNeural ProsthesisForearm
• Neuroprosthetic-enabled control of graded arm muscle contraction in a paralyzed human
  Neuroprosthetics that combine a brain computer interface (BCI) with functional electrical stimulation (FES) can restore voluntary control of a patients' own paralyzed limbs. To date, human studies have demonstrated an "all-or-none" type of control for a fixed …
  openalex David A. Friedenberg, Michael A. Schwemmer, Andrew J. Landgraf, Nicholas V. Annetta 等 2017-08-10 置信度 0.72 NeuroprostheticsFunctional electrical stimulationBrain–computer interfacePhysical medicine and rehabilitationWrist
• Emergence of Coordinated Neural Dynamics Underlies Neuroprosthetic Learning and Skillful Control
  openalex Vivek R. Athalye, Karunesh Ganguly, Rui M. Costa, Jose M. Carmena 2017-02-01 置信度 0.72 NeuroscienceMotor learningMotor cortexMotor controlPopulation
• Single‐Walled Carbon Nanotube Polyelectrolyte Multilayers and Freestanding Films as a Biocompatible Platform for Neuroprosthetic Implants
  Layer-by-layer (LBL) assembly has been used to prepare single-walled carbon nanotube (SWNT) freestanding structures that can be used for implantable devices with unique mechanical and electrical properties (see Figure). The thin LBL membranes prepared are bioc…
  openalex Muhammed K. Gheith, Vladimir A. Sinani, James P. Wicksted, Robert L. Matts 等 2005-10-11 置信度 0.72 Materials scienceCarbon nanotubeBiocompatible materialNanotechnologyPolyelectrolyte
• Development and Characterization of PEDOT:PSS/Alginate Soft Microelectrodes for Application in Neuroprosthetics
  Reducing the mechanical mismatch between the stiffness of a neural implant and the softness of the neural tissue is still an open challenge in neuroprosthetics. The emergence of conductive hydrogels in the last few years has considerably widened the spectrum o…
  openalex Laura Ferlauto, Antonio Nunzio D’Angelo, Paola Vagni, Marta Jole Ildelfonsa Airaghi Leccardi 等 2018-09-19 置信度 0.72 NeuroprostheticsMicroelectrodePEDOT:PSSCharacterization (materials science)Materials science