检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Huang, Chenyu Tan, Weimin Shi, Jiaxing Xing, Zhen Yan, Bo Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9781728163277

Recently, unsupervised image denoising methods learning from paired noisy samples have received increasing attention. These methods build on the idea that the mean of multiple noisy images of the same scene is the ideal clean image. However, these methods ignore the effect of Aleatoric uncertainty in the noisy image (e.g., pixels deviating from the expected distribution). The presence of Aleatoric uncertainty causes degradation of the reconstructed target pixels, resulting in high uncertainty for these pixels (i.e., low confidence), which in turn leads to sub-optimal denoising results. To address this problem, we propose a novel uncertainty-aware unsupervised image denoising method named Uncer2Natural (U2N). It dynamically predicts the Aleatoric uncertainty for each noisy sample and produces satisfactory denoising results by reducing the effect of Aleatoric uncertainty. Extensive experimental results show that U2N outperforms state-of-the- art unsupervised image denoising methods in terms of both quantitative metrics and qualitative visual quality. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection

Motion Matters: Difference-based Multi-scale Learning for In...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： He, Ruian Zhou, Shili Cheng, Ri Sun, Yuqi Tan, Weimin Yan, Bo Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798350302493

Unmanned Aerial Vehicle (UAV) detection in the wild is a challenging task due to the presence of background noise and the varying size of the object. To address these obstacles, we propose a novel learning framework for robust UAV detectors, which we call Difference-based Multi-scale Learning (DML). We argue that motion information matters in UAV detection because of the low recognition in one frame. Our method utilizes the frame difference of multiple previous frames, extracting motion information and blocking background noise. We also fuse multiple spatial-temporal scales for training and inferencing, enabling fusion from different sources. In addition, to better evaluate the performance of UAV detection in different scales, we propose Multi-Scale Average Precision (MSAP) metric to aggregate the detection accuracy over multiple scales. Through extensive experiments, we demonstrate that our proposed approach improves the detection accuracy of baseline models. Notably, we achieve SOTA performance in the 3rd Anti-UAV Challenge, with 2nd place in Track 2 and 4th place in Track 1. © 2023 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Recipe Generation

Retrieval Augmented Recipe Generation

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

ISBN: (纸本)9798331510831

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2025 IEEE.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Blocky Volume Package: a Web-friendly Volume Storage and Compression Solution

Blocky Volume Package: a Web-friendly Volume Storage and Com...

引用

作者： Lesar, Žiga Bohak, Ciril Marolt, Matija University of Ljubljana Faculty of Computer and Information Science Večna pot 113 Ljubljana1000 Slovenia King Abdullah University of Science and Technology Visual Computing Center Thuwal23955 Saudi Arabia

The Blocky Volume Package (BVP) format is a distributed, platform-independent and API-independent format for storing static and temporal volumetric data. It is designed for efficient transfer over a network by supporting sparse volumes, multiple resolutions, random access, and streaming, as well as providing a strict framework for supporting a wide palette of encoding formats. The BVP format achieves this by dividing a volume or a volume sequence into blocks that can be compressed and reused. The metadata for the blocks are stored in separate files so that a client has all the information required for loading and decoding the blocks before the actual transmission, decoding and rendering take place. This design allows for random access and parallel loading and has been specifically designed for efficient use on the web platform by adhering to the current living standards. In the paper, we compare the BVP format with some of the most often implemented volume storage formats, and show that the BVP format supports most major features of these formats while at the same time being easily implementable and extensible. © 2023 The Author(s).

关键词： Volumetric analysis

来源：评论

学校读者我要写书评

暂无评论

Making Large Language Models Better Reasoners with Orchestrated Streaming Experiences

arXiv

引用

arXiv 2025年

作者： Liu, Xiangyang He, Junliang Qiu, Xipeng School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

Large language models (LLMs) can perform complex reasoning by generating intermediate thoughts under zero-shot or few-shot settings. However, zero-shot prompting always encounters low performance, and the superior performance of few-shot prompting hinges on the manual-crafted demonstrations. In this paper, we present RoSE (Reasoning with Orchestrated Streaming Experiences), a general framework for solving reasoning tasks that can self-improve without complex external efforts. To enable RoSE, we describe an architecture that extends an LLM to store all answered questions and their thoughts in a streaming experience pool then orchestrates helpful questions from the pool to assist in answering new questions. To set up a question-aware orchestration mechanism, RoSE first calculates the similarity of each question in the pool with a new test question. Since the solution to each answered question is not always correct, RoSE will sort the questions according to their similarity with the new question, and then uniformly divide them into multiple buckets. It finally extracts one question from each bucket to make these extracted questions more diverse. To make these extracted questions help RoSE answer new questions as much as possible, we introduce two other attributes of uncertainty and complexity for each question. RoSE will preferentially select the questions with low uncertainty and high complexity from each bucket. We evaluate the versatility of RoSE in various reasoning tasks, LLMs, and CoT methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

GenRec: Unifying Video Generation and Recognition with Diffusion Models 38

GenRec: Unifying Video Generation and Recognition with Diffu...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Weng, Zejia Yang, Xitong Xing, Zhen Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Department of Computer Science University of Maryland United States

Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for video recognition, and eventually joint optimization of generation and recognition. Building upon Stable Video Diffusion, we introduce GenRec, the first unified framework trained with a random-frame conditioning process so as to learn generalized spatial-temporal representations. The resulting framework can naturally supports generation and recognition, and more importantly is robust even when visual inputs contain limited information. Extensive experiments demonstrate the efficacy of GenRec for both recognition and generation. In particular, GenRec achieves competitive recognition performance, offering 75.8% and 87.2% accuracy on SSV2 and K400, respectively. GenRec also performs the best on class-conditioned image-to-video generation, achieving 46.5 and 49.3 FVD scores on SSV2 and EK-100 datasets. Furthermore, GenRec demonstrates extraordinary robustness in scenarios that only limited frames can be observed. Code will be available at https://***/wengzejia1/GenRec. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy 38

Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guan, Zhenyu Kong, Xiangyu Zhong, Fangwei Wang, Yizhou Institute for Artificial Intelligence Peking University China College of Computer Science Beijing Information Science and Technology University China School of Artificial Intelligence Beijing Normal University China Center on Frontiers of Computing Studies School of Computer Science Nat'l Eng Research Center of Visual Technology Peking University China State Key Laboratory of General Artificial Intelligence BIGAI China

Diplomacy is one of the most sophisticated activities in human society, involving complex interactions among multiple parties that require skills in social reasoning, negotiation, and long-term strategic planning. Previous AI agents have demonstrated their ability to handle multi-step games and large action spaces in multi-agent tasks. However, diplomacy involves a staggering magnitude of decision spaces, especially considering the negotiation stage required. While recent agents based on large language models (LLMs) have shown potential in various applications, they still struggle with extended planning periods in complex multi-agent settings. Leveraging recent technologies for LLM-based agents, we aim to explore AI's potential to create a human-like agent capable of executing comprehensive multi-agent missions by integrating three fundamental capabilities: 1) strategic planning with memory and reflection;2) goal-oriented negotiation with social reasoning;and 3) augmenting memory through self-play games for self-evolution without human in the loop. Project page: https://***/view/richelieu-diplomacy. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation

arXiv

引用

arXiv 2024年

作者： Zong, Yi Qiu, Xipeng School of Computer Science Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

The Large Vision-Language Models (LVLMs) have demonstrated great abilities in image perception and language understanding. However, existing datasets either focus solely on primary perception abilities and commonsense knowledge, or have a low level of text comprehension difficulty, which are insufficient to reflect the comprehensive capabilities of LVLMs, particularly in terms of Chinese language proficiency. We propose GAOKAO-MM, a multimodal benchmark based on the Chinese College Entrance Examination (GAOKAO), comprising of 8 subjects and 12 types of images, such as diagrams, function graphs, maps and photos. GAOKAO-MM derives from native Chinese context and sets human-level requirements for the model's abilities, including perception, understanding, knowledge and reasoning. We evaluate 10 LVLMs and find that the accuracies of all of them are lower than 50%, with GPT-4-Vision (48.1%), Qwen-VL-Plus (41.2%) and Gemini-Pro-Vision (35.1%) ranking in the top three positions. The results of our multi-dimension analysis indicate that LVLMs have moderate distance towards Artificial General Intelligence (AGI) and provide insights facilitating the development of multilingual LVLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： visual languages

来源：评论

学校读者我要写书评

暂无评论

Real-Time 3D Object Detection, Recognition and Presentation Using a Mobile Device for Assistive Navigation

引用

SN computer science 2023年第5期4卷 1-18页

作者： Chen, Jin Zhu, Zhigang Visual Computing Laboratory Computer Science Department The City College-CUNY New York 10031 NY United States Nearabl Inc. New York 10023 NY United States PhD Program in Computer Science The Graduate Center-CUNY New York 10016 NY United States

This paper presents an integrated solution for 3D object detection, recognition, and presentation to increase accessibility for various user groups in indoor areas through a mobile application. The system has three major components: a 3D object detection module, an object tracking and update module, and a voice and AR-enhanced interface. The 3D object detection module consists of pre-trained 2D object detectors and 3D bounding box estimation methods to detect the 3D poses and sizes of the objects in each camera frame. This module can easily adapt to various 2D object detectors (e.g., YOLO, SSD, mask RCNN) based on the requested task and requirements of the run time and details for the 3D detection result. It can run on a cloud server or mobile application. The object tracking and update module minimizes the computational power for long-term environment scanning by converting 2D tracking results into 3D results. The voice and AR-enhanced interface integrates ARKit and SiriKit to provide voice interaction and AR visualization to improve information delivery for different user groups. The system can be integrated with existing applications, especially assistive navigation, to increase travel safety for people who are blind or have low vision and improve social interaction for individuals with autism spectrum disorder. In addition, it can potentially be used for 3D reconstruction of the environment for other applications. Our preliminary test results for the object detection evaluation and real-time system performance are provided to validate the proposed system. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： 3D object detection ARKit Assistive technology Blind or low vision Voice assistance

来源：评论

学校读者我要写书评

暂无评论

DeepPointMap2: Accurate and Robust LiDAR-visual SLAM with Neural Descriptors 24

DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Xiaze Ding, Ziheng Jing, Qi Cheng, Ying Ding, Wenchao Feng, Rui Fudan University Shanghai China The School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China The Academy for Engineering and Technology Fudan University China The Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)9798400706868

Simultaneous Localization and Mapping (SLAM) plays a pivotal role in autonomous driving and robotics. Existing methods often rely on hand-craft feature extraction and cross-modal fusion techniques, resulting in limited feature representation capability and reduced robustness. To address this challenge, we introduce DeepPointMap2, a novel learning-based LiDAR-visual SLAM architecture that leverages neural descriptors to tackle multiple SLAM sub-tasks in a unified manner. Our approach employs neural networks to extract multi-modal tokens, which are then adaptively fused by the visual-Point Fusion Module to generate sparse 3D neural descriptors, ensuring precise and robust performance. As a pioneering work, our method achieves state-of-the-art localization performance among various visual-, LiDAR-, and visual-LiDAR-based methods in widely-used benchmarks, as shown in the experiment results. Furthermore, the approach proves to be robust in scenarios involving camera failure and LiDAR obstruction. © 2024 ACM.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：