首页/论文/1904.08959

arXiv 1904.089592019-04-18cs.CV

RepGN:Object Detection with Relational Proposal Graph Network

Institute for Clarity in Documentation（文档清晰性研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗克库尔分部）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）

Xingjian Du, Xuan Shi, Risheng Huang

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results.

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

关系先验知识图用于检测与实例分割

Relational Prior Knowledge Graphs for Detection and Instance Segmentation

University of Amsterdam（阿姆斯特丹大学）；TomTom（TomTom公司）

本文提出基于关系先验的图变换器RP-FEM，利用场景图增强目标提议特征，在COCO上提升检测与实例分割性能，抑制错误类别并减少重复预测。

2023-10-11cs.CV

Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection

School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；USTB-EEasyTech Joint Lab of Artificial Intelligence, Tencent Technology (Shenzhen) Co. Ltd（北京科技大学-易享科技人工智能联合实验室，腾讯科技（深圳）有限公司）；Institute of Artificial Intelligence, University of Science and Technology Beijing（北京科技大学人工智能研究院）

Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts. In this paper, we propose a novel unified relational reasoning graph network for arbitrary shape text detection. In our method, an innovative local graph bridges a text proposal model via Convolutional Neural Network (CNN) and a deep relational reasoning network via Graph Convolutional Network (GCN), making our network end-to-end trainable. To be concrete, every text instance will be divided into a series of small rectangular components, and the geometry attributes (e.g., height, width,…

2020-08-30cs.CV

CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning

Sun Yat-sen University（中山大学）；JD AI Research（京东人工智能研究院）

Localizing text instances in natural scenes is regarded as a fundamental challenge in computer vision. Nevertheless, owing to the extremely varied aspect ratios and scales of text instances in real scenes, most conventional text detectors suffer from the sub-text problem that only localizes the fragments of text instance (i.e., sub-texts). In this work, we quantitatively analyze the sub-text problem and present a simple yet effective design, COntrastive RElation (CORE) module, to mitigate that issue. CORE first leverages a vanilla relation block to model the relations among all text proposals …

2021-12-14cs.AIcs.CVcs.MM

Dense Relational Image Captioning via Multi-task Triple-Stream Networks

School of Electrical Engineering, KAIST（韩国科学技术院电气工程学院）；Dept. of Electrical Engineering and Graduate School of AI (GSAI), POSTECH（浦项科技大学电气工程系与人工智能研究生院）

We introduce dense relational captioning, a novel image captioning task which aims to generate multiple captions with respect to relational information between objects in a visual scene. Relational captioning provides explicit descriptions for each relationship between object combinations. This framework is advantageous in both diversity and amount of information, leading to a comprehensive image understanding based on relationships, e.g., relational proposal generation. For relational understanding between objects, the part-of-speech (POS; i.e., subject-object-predicate categories) can be a v…

2021-10-11cs.AIcs.CLcs.CV

HyperVis：洛伦兹双曲面上的连续潜在视觉关系图用于组合推理

HyperVis: Continuous Latent Visual Relational Graphs on the Lorentz Hyperboloid for Compositional Reasoning

Data Science and AI, University of Doha for Science and Technology, Qatar（数据科学与人工智能，多哈科学技术大学，卡塔尔）；Pluralis Research, Australia（Pluralis研究，澳大利亚）；Department of Electrical and Computer Engineering, North South University, Bangladesh（电气与计算机工程系，北南大学，孟加拉国）

针对视觉语言模型在组合推理中理解物体间关系的困难，提出HyperVis方法，通过计算密集视觉关系张量并投影到洛伦兹双曲面，利用空间物理（IoA驱动的蕴含锥和外部角排斥）增强层次结构，在训练时作为正则化器提升生成式VQA性能，在推理时作为关系编码器提升判别式组合评分。

2026-06-04cs.CV

Tell Me What They're Holding: Weakly-supervised Object Detection with Transferable Knowledge from Human-object Interaction

Seoul National University（首尔国立大学）；V.DO Inc（V.DO公司）

In this work, we introduce a novel weakly supervised object detection (WSOD) paradigm to detect objects belonging to rare classes that have not many examples using transferable knowledge from human-object interactions (HOI). While WSOD shows lower performance than full supervision, we mainly focus on HOI as the main context which can strongly supervise complex semantics in images. Therefore, we propose a novel module called RRPN (relational region proposal network) which outputs an object-localizing attention map only with human poses and action verbs. In the source domain, we fully train an o…

2019-11-19cs.CVcs.LG

更多相关论文收起更多论文

FutureLift：将轨迹提案提升为用于运动预测的双向未来图

FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting

FZI Research Center for Information Technology（FZI信息技术研究中心）

FutureLift是一种与主干无关的运动预测修正器，通过异构未来图实现双向修正，在Argoverse2、Waymo Open Motion Dataset上提升性能，在WOMD排行榜标准输入方法中minADE、minFDE居首。

2026-10-16cs.CVcs.LG

Object Relational Graph with Teacher-Recommended Learning for Video Captioning

National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）；PeopleAI, Inc.（人民人工智能有限公司）；State Key Laboratory of Communication Content Cognition, People’s Daily Online（人民网传播内容认知国家重点实验室）；Aerospace Information Research Institute, CAS（中国科学院空天信息创新研究院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）

Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a …

2020-02-26cs.CLcs.CV

Relation Network for Multi-label Aerial Image Classification

German Aerospace Center（德国航空航天中心）；Technical University of Munich（慕尼黑工业大学）

Multi-label classification plays a momentous role in perceiving intricate contents of an aerial image and triggers several related studies over the last years. However, most of them deploy few efforts in exploiting label relations, while such dependencies are crucial for making accurate predictions. Although an LSTM layer can be introduced to modeling such label dependencies in a chain propagation manner, the efficiency might be questioned when certain labels are improperly inferred. To address this, we propose a novel aerial image multi-label classification network, attention-aware label rela…

2020-02-10cs.CV

ThinkAfford：面向杂乱场景中细粒度3D grounding的以可供性为中心的推理

ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes

该研究提出ThinkAfford模型，通过解耦可供性提议生成与指令推理，结合GRPO优化，在SceneFun3D验证集上的3D grounding指标优于基线方法。

2026-08-12cs.CV

重新审视通过配对亲和学习的弱监督视频场景图生成

Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning

Yonsei University（延世大学）；LG Electronics（LG电子）

本文通过引入可学习的配对亲和力，改进弱监督视频场景图生成，利用配对亲和学习和调节，提升关系模型的准确性，实验表明在Action Genome上取得最优性能。

2026-03-23cs.CV

SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation

Beijing Institute of Technology（北京理工大学）；Huawei（华为）；The University of Hong Kong（香港大学）

Objects in a scene are not always related. The execution efficiency of the one-stage scene graph generation approaches are quite high, which infer the effective relation between entity pairs using sparse proposal sets and a few queries. However, they only focus on the relation between subject and object in triplet set subject entity, predicate entity, object entity, ignoring the relation between subject and predicate or predicate and object, and the model lacks self-reasoning ability. In addition, linguistic modality has been neglected in the one-stage method. It is necessary to mine linguisti…

2022-12-19cs.CV

GATA2Floor: 图注意力用于街道视图立面的楼层计数

GATA2Floor: Graph attention for floor counting in street-view facades

ETRO Department, Vrije Universiteit Brussel (VUB)（比利时布鲁塞尔自由大学ETRO部门）；imec

本文提出GATA2Floor模型，通过图注意力机制实现对街道视图立面楼层的自动计数，结合可学习的交叉注意力查询实现元素到潜在楼层槽的软分配，提升解释性和鲁棒性。

2026-05-12cs.CVeess.IV

TBSG-Net：用于细粒度视频时刻检索的时间二分场景图网络

TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval

Queen’s University Belfast（贝尔法斯特女王大学）；School of Electronics, Electrical Engineering and Computer Science（电子、电气工程与计算机科学学院）

针对无提案视频时刻检索中静态场景图的时间动态性缺失与时间跨度编码不足问题，提出首个基于动态场景图的TBSG-Net，通过TBSG构造器与混合编码器实现显著性能提升。

2026-08-04cs.AIcs.CV

MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes

Fudan University（复旦大学）；Meituan Inc.（美团）

3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation …

2022-07-20cs.AIcs.CLcs.CV