arXiv 1406.39062014-06-16cs.CV

Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding

Stanford University（斯坦福大学）；UCLA（加州大学洛杉矶分校）；TTIC（丰田技术研究所）；Virginia Tech（弗吉尼亚理工学院暨州立大学）

Roozbeh Mottaghi, Sanja Fidler, Alan Yuille, Raquel Urtasun, Devi Parikh

英文摘要：

Recent trends in image understanding have pushed for holistic scene understanding models that jointly reason about various tasks such as object detection, scene recognition, shape analysis, contextual reasoning, and local appearance based classifiers. In this work, we are interested in understanding the roles of these different tasks in improved scene understanding, in particular semantic segmentation, object detection and scene recognition. Towards this goal, we "plug-in" human subjects for each of the various components in a state-of-the-art conditional random field model. Comparisons among various hybrid human-machine CRFs give us indications of how much "head room" there is to improve scene understanding by focusing research efforts on various individual tasks.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

CA^2ST：面向整体视频识别的音频、空间与时间交叉注意力机制

CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition

Kyung Hee University（庆熙大学）

针对现有视频识别模型时空理解不均衡的问题，提出基于Transformer的CA^2ST框架，通过B-CA模块实现空间、时间、音频专家的信息交互，在多类基准上取得均衡优异的整体视频识别效果。

2025-11-14cs.CV

Holistic Interstitial Lung Disease Detection using Deep Convolutional Neural Networks: Multi-label Learning and Unordered Pooling

National Institutes of Health Clinical Center（美国国立卫生研究院临床中心）

Accurately predicting and detecting interstitial lung disease (ILD) patterns given any computed tomography (CT) slice without any pre-processing prerequisites, such as manually delineated regions of interest (ROIs), is a clinically desirable, yet challenging goal. The majority of existing work relies on manually-provided ILD ROIs to extract sampled 2D image patches from CT slices and, from there, performs patch-based ILD categorization. Acquiring manual ROIs is labor intensive and serves as a bottleneck towards fully-automated CT imaging ILD screening over large-scale populations. Furthermore,…

2017-01-19cs.CV

HoloCount：用于多模态大语言模型的整体视觉计数基准

HoloCount: A Holistic Visual Counting Benchmark for MLLMs

Meituan（美团）

研究针对多模态大语言模型定量精度瓶颈及现有计数基准局限，引入HoloCount基准，从语义、分析计数和鲁棒性测试三方面评估模型，经对20多个模型详尽评估，揭示其性能差距，为多模态系统发展提供路线图。

2026-08-07cs.AIcs.CV

高频语义与几何先验在复杂无人机影像端到端检测Transformer中的应用

High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery

College of Mathematics and Informatics（数学与信息学院）；South China Agricultural University（华南农业大学）；Key Laboratory of Smart Agricultural Technology in Tropical South China, Ministry of Agriculture and Rural Affairs（热带南中国智能农业技术重点实验室，农业农村部）；School of Economics and Trade（经济贸易学院）

针对无人机影像中小目标密集、遮挡等问题，提出HEDS-DETR端到端检测Transformer，通过高频语义网络、小目标金字塔及几何感知编码等创新，在VisDrone数据集上提升性能并保持实时性与精度-效率平衡。

2025-11-10cs.CV

基于多粒度置信度对齐均值教师的跨域目标检测

Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher

National University of Defense Technology (NUDT)（国防科技大学）；College of System Engineering, National University of Defense Technology (NUDT)（国防科技大学系统工程学院）；College of Electronic Science and Technology, NUDT（国防科技大学电子科学学院）；College of Meteorology and Oceanography, NUDT（国防科技大学气象海洋学院）

针对跨域目标检测中均值教师方法伪标签置信度错位导致性能不佳的问题，提出多粒度置信度对齐框架，从类别、实例、图像三层优化伪监督质量，提升跨域检测效果。

2024-07-10cs.CV

从空间到频谱：一种用于小目标检测的高效频率引导特征表示学习器

From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection

Southern University of Science and Technology（南方科技大学）；University of Pennsylvania（宾夕法尼亚大学）

提出从空间域转向频谱域的特征处理范式，通过频率引导特征表示框架和轻量级DER算子（WDG、LGE、FDHead），在多个基准上以1/6参数超越YOLOv11。

2026-06-24cs.AIcs.CV

更多相关论文收起更多论文

深入场景：通过焦点计划生成打破视觉-语言决策中的感知瓶颈

Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation

University of Science and Technology of China（中国科学技术大学）；Tsinghua University（清华大学）

提出SceneDiver方法，通过从粗到细的焦点计划生成，逐步构建场景图并分解任务，减少视觉幻觉，提升视觉-语言模型和视觉-语言-动作模型在具身决策任务中的表现。

2026-06-02cs.AIcs.CLcs.CV

Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）

Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder). In this paper, we propose a Representation and Correlation Enhanced Encoder-Decoder Framework(RCEED) to address these deficiencies and break performance bottleneck. In the encoder module, local vi…

2021-11-14cs.CV

通用场景图生成

Universal Scene Graph Generation

National University of Singapore（新加坡国立大学）

针对当前场景图研究局限于单模态、无法利用多模态互补优势的问题，提出通用场景图（USG）及解析器USG-Par，通过模块化架构、目标关联器和文本中心对比学习解决跨模态对齐与域不平衡问题，实现更优的场景语义表达与生成性能。

2025-03-19cs.CV

SIV-Bench：一种用于社会互动理解和推理的视频基准测试

SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning

Peking University（北京大学）；State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI）；Tsinghua University（清华大学）；ShanghaiTech University（上海科技大学）

本文提出SIV-Bench，一个用于评估多模态大语言模型在社会场景理解、社会状态推理和社会动态预测能力的视频基准测试，揭示了现有模型在社会推理方面的不足。

2026-04-28cs.AIcs.CV