IEEE Transactions on Pattern Analysis and Machine Intelligence最新文献_第8页

ATR-UAP: Enhancing the Transferability of Data-Free Universal Adversarial Perturbation via Adaptive Truncated Ratio Maximization ATR-UAP：通过自适应截断比最大化增强无数据通用对抗性扰动的可转移性

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-08-04 DOI: 10.1109/tpami.2026.3720232

Di Ming, Peng Ren, Yuanchengzhi Liu, Yunlong Wang, Xin Feng

引用次数: 0

GBSK: Skeleton Clustering via Granular-ball Computing and Multi-Sampling for Large-Scale Data GBSK：基于颗粒球计算和多采样的大规模数据骨架聚类

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-08-04 DOI: 10.1109/tpami.2026.3719825

Yewang Chen, Junfeng Li, Shuyin Xia, Qinghong Lai, Xinbo Gao, Guoyin Wang, Dongdong Cheng, Yi Liu, Yi Wang

引用次数: 0

OneBEV++: Towards Unifying Bird's-Eye-View Semantic Mapping with Panoramas onebev++：迈向统一鸟瞰语义映射与全景图

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-07-31 DOI: 10.1109/tpami.2026.3719109

Jiale Wei, Zhifeng Teng, Fei Teng, Junwei Zheng, Ruiping Liu, Yufan Chen, Jie Hu, Kailun Yang, Jiaming Zhang, and Rainer Stiefelhagen

引用次数: 0

NExplore: Exploration with Neural Fields for Autonomous Scene Reconstruction. 探索：利用神经场进行自主场景重建的探索。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-04-16 DOI: 10.1109/tpami.2026.3683554

Zike Yan,Zijia Kuang,Yuetao Li,Jinkun Liu,Guyue Zhou,Hongbin Zha

{"title":"NExplore: Exploration with Neural Fields for Autonomous Scene Reconstruction.","authors":"Zike Yan,Zijia Kuang,Yuetao Li,Jinkun Liu,Guyue Zhou,Hongbin Zha","doi":"10.1109/tpami.2026.3683554","DOIUrl":"https://doi.org/10.1109/tpami.2026.3683554","url":null,"abstract":"We present NExplore, an exploration system designed for autonomous reconstruction of indoor environments using implicit neural representations (INRs). The core of the paper is a principled continual learning paradigm that addresses the optimization process of neural fields from sequential observations as an iterative process to achieve a balance between generalization and forgetting. The equilibrium is reached by maximizing the distribution shifts while minimizing the reconstruction error, enabling a mobile agent to actively explore the environment and construct a neural map in real-time, with prediction error gradually reduced through a self-supervised, data-driven fashion. To achieve this, we 1) introduce a plug-and-play method for quantifying the prediction uncertainty of the neural map through random weight perturbation; 2) adopt an experience replay method for incremental map updating; 3) maintain a sparse graph structure that integrates scene geometry, appearance, topology, and uncertainty synergistically for efficient planning and decision-making. With continuous geometric information inherited in the neural map, the agent is guided to navigate traversable paths while progressively enhancing its understanding of the environment. We present for the first time an online active mapping system with coordinate-based implicit neural representations. Experiments conducted in visually realistic Gibson and Matterport3D environments along with real-world scenarios validate the efficacy of the proposed method.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"22 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2026-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147695209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation. 通过方向不可知的EM公式桥接生成和判别噪声标签学习。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-03-11 DOI: 10.1109/tpami.2026.3673244

Fengbei Liu,Chong Wang,Yuanhong Chen,Yuyuan Liu,Gustavo Carneiro

{"title":"Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation.","authors":"Fengbei Liu,Chong Wang,Yuanhong Chen,Yuyuan Liu,Gustavo Carneiro","doi":"10.1109/tpami.2026.3673244","DOIUrl":"https://doi.org/10.1109/tpami.2026.3673244","url":null,"abstract":"Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint mechanism that produces features, clean labels, and corrupted observations. However, prior work typically (i) introduces extra latent variables and heavy image generators that bias training toward reconstruction, (ii) fixes a single data-generating direction (Y →X or X →Y), limiting adaptability, and (iii) assumes a uniform prior over clean labels, ignoring instance-level uncertainty. Here, we propose a single-stage, EM-style framework for generative noisy-label learning that is direction-agnostic and avoids explicit image synthesis. First, we derive a single Expectation Maximization (EM) objective whose E-step specializes to either causal orientation without changing the overall optimization objective. Second, we replace the intractable p(X | Y) with a dataset-normalized discriminative proxy computed using a discriminative classifier on the finite training set, retaining the structural benefits of generative modeling at much lower cost. Third, we introduce Partial-Label Supervision (PLS), an instance specific prior over clean labels that balances coverage and uncertainty, improving data-dependent regularization. Across standard vision and natural language processing (NLP) noisy label benchmarks, our method achieves state-of-the-art accuracy, lower transition-matrix estimation error, and substantially less training computation than current generative and discriminative baselines. Code: https://github.com/lfb-1/GNL.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"28 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2026-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147393776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

VIRGi: View-dependent Instant Recoloring of 3D Gaussians Splats 基于视图的三维高斯曲线的即时重着色

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2026-02-24 DOI: 10.1109/tpami.2026.3665650

Alessio Mazzucchelli, Ivan Ojeda-Martin, Fernando Rivas-Manzaneque, Elena Garces, Adrian Penate-Sanchez, Francesc Moreno-Noguer

引用次数: 0

Weakly and Single-Frame Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning 基于高斯的对比建议学习的弱单框架监督时态句基础

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-12-17 DOI: 10.1109/tpami.2025.3644900

Minghang Zheng, Yanjie Huang, Qingchao Chen, Yuxin Peng, Yang Liu

引用次数: 0

Diffusion Models are Efficient Data Generators for Human Mesh Recovery. 扩散模型是人体网格恢复的有效数据生成器。

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-11-18 DOI: 10.1109/tpami.2025.3621755

Yongtao Ge,Wenjia Wang,Yongfan Chen,Fanzhou Wang,Lei Yang,Hao Chen,Chunhua Shen

{"title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery.","authors":"Yongtao Ge,Wenjia Wang,Yongfan Chen,Fanzhou Wang,Lei Yang,Hao Chen,Chunhua Shen","doi":"10.1109/tpami.2025.3621755","DOIUrl":"https://doi.org/10.1109/tpami.2025.3621755","url":null,"abstract":"Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor mocap datasets or datasets generated by a rendering engine using computer graphics (CG). Both categories of datasets exhibit inadequacies in furnishing adequate human identities and authentic in-the-wild background scenes, which are crucial for accurately simulating real-world distributions. In this work, we show that synthetic data created by generative models is complementary to CG-rendered data for achieving remarkable generalization performance on diverse real-world scenes. We propose an effective data generation pipeline based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. Specifically, we first collect a large-scale human-centric dataset with comprehensive annotations, e.g., text captions, the depth map, and surface normal images. To generate a wide variety of human images with initial labels, we train a customized, multi-condition ControlNet model. The key to this process is using a 3D parametric model, e.g., SMPL-X, to easily create precise 2D keypoints, depth maps, and surface normal images by rendering the 3D mesh [id=PR]with specific camera parameters. As there exists inevitable noise in the initial labels, we apply an off-the-shelf foundation segmentation model to filter negative data samples, and a 2D vertex estimator to rectify the SMPL-X parameters by using SMPLify. Our data generation pipeline is both flexible and customizable, making it adaptable to various real-world tasks, such as human interaction in complex scenes and humans captured by wide-angle lenses. By relying solely on generative models, we can produce large-scale, in-the-wild human images with high-quality annotations, significantly reducing the need for manual image collection and annotation. The generated dataset encompasses a wide range of viewpoints, environments, and human identities, ensuring its versatility across different scenarios. To verify the effectiveness of the generated data, we perform comprehensive data ablation experiments by performing data ablation studies on top of the both generated data and existing datasets, and evaluating on a wide range of HPS benchmarks. We hope our work could pave the way for scaling up 3D human recovery to in-the-wild scenes.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"13 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145545047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TripoSG: High-Fidelity 3D Shape Synthesis Using Large-Scale Rectified Flow Models TripoSG：高保真三维形状合成使用大规模整流模型

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-11-17 DOI: 10.1109/tpami.2025.3633512

Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, Yan-Pei Cao

引用次数: 0

SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting synctalk++：高保真和高效同步说话头合成使用高斯飞溅

IF 23.6 1区计算机科学

IEEE Transactions on Pattern Analysis and Machine Intelligence Pub Date : 2025-11-06 DOI: 10.1109/tpami.2025.3630057

Ziqiao Peng, Wentao Hu, Junyuan Ma, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Hui Tian, Jun He, Hongyan Liu, Zhaoxin Fan

引用次数: 0