Author name cluster

Jin Zheng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

EAAI Journal 2026 Journal Article

Collective strength and individual influence: A decision-making method for recommending new products

Jin Zheng
Duo-Ning Yuan
Ping-Ping Cao
Ming-Yang Li

In a market environment characterized by rapid product iteration and intense competition, accurate new product recommendation has become crucial for online retail platforms to gain competitive advantages, enhance user engagement, and improve economic performance. However, during the early launch phase of new products, recommendation performance is often limited by the scarcity of user reviews and individual preference data. To address this challenge, this study proposes a decision-making method for recommending new product. First, a sentiment analysis algorithm combined with an improved grey clustering algorithm is employed to group consumers with similar attribute preferences and individual concerns. Second, considering that key opinion leaders tend to experience new products early within their areas of interest, these leaders and the attribute preferences embedded in their multimodal evaluation information are identified. Furthermore, preference similarity between key opinion leaders and consumer groups is calculated. Recommendation lists for different groups are then generated by integrating new product evaluation information from candidate key opinion leaders. Finally, the feasibility of the proposed method is validated through case studies involving multiple products. Comparative experiments conducted on the Amazon dataset demonstrate that the proposed method outperforms existing recommendation methods in sparse-data scenarios. By leveraging group preferences and professional evaluation information, the proposed method alleviates information scarcity in new product recommendation, provides reliable decision support for platforms to implement precision marketing of new products, and reduces the decision-making barriers faced by potential consumers due to information asymmetry.

Details DOI

AAAI Conference 2026 Conference Paper

FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM

Yuchen Wu
Jiahe Li
Fabio Tosi
Matteo Poggi
Jin Zheng
Xiao Bai

We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches for accurate and robust tracking and mapping. Our core idea is to bridge flow estimation with geometric reasoning by leveraging the guidance from foundation depth models. To this end, we first develop a Hybrid Flow Network that produces geometry-aware correspondences, enabling consistent depth and pose inference across diverse keyframes. To enforce global consistency, we propose a Bi-Consistent Bundle Adjustment Layer that jointly optimizes keyframe pose and depth under multi-view constraints. Furthermore, we introduce a Reliability-Aware Refinement mechanism that dynamically adapts the flow update process by distinguishing between reliable and uncertain regions, forming a closed feedback loop between matching and optimization. Extensive experiments demonstrate that FoundationSLAM achieves superior trajectory accuracy and dense reconstruction quality across multiple challenging datasets, while running in real-time at 18 FPS, demonstrating strong generalization to various scenarios and practical applicability of our method.

PDF Details DOI

AAAI Conference 2026 Conference Paper

How Wide and How Deep? Mitigating Over-squashing of GNNs via Channel Capacity Constrained Estimation

Zinuo You
Jin Zheng
John Cartlidge

Existing graph neural networks typically rely on heuristic choices for hidden dimensions and propagation depths, which often lead to severe information loss during propagation, known as over-squashing. To address this issue, we propose Channel Capacity Constrained Estimation (C³E), a novel framework that formulates the selection of hidden dimensions and depth as a nonlinear programming problem grounded in information theory. Through modeling spectral graph neural networks as communication channels, our approach directly connects channel capacity to hidden dimensions, propagation depth, propagation mechanism, and graph structure. Extensive experiments on nine public datasets demonstrate that hidden dimensions and depths estimated by C³E can mitigate over-squashing and consistently improve representation learning. Experimental results show that over-squashing occurs due to the cumulative compression of information in representation matrices. Furthermore, our findings show that increasing hidden dimensions indeed mitigates information compression, while the role of propagation depth is more nuanced, uncovering a fundamental balance between information compression and representation complexity.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MTAttack: Multi-Target Backdoor Attacks Against Large Vision-Language Models

Zihan Wang
Guansong Pang
Wenjun Miao
Jin Zheng
Xiao Bai

Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security vulnerabilities of LVLMs have become increasingly concerning, particularly their susceptibility to backdoor attacks. Existing backdoor attacks focus on single-target attacks, i.e., targeting a single malicious output associated with a specific trigger. In this work, we uncover multi-target backdoor attacks, where multiple independent triggers corresponding to different attack targets are added in a single pass of training, posing a greater threat to LVLMs in real-world applications. Executing such attacks in LVLMs is challenging since there can be many incorrect trigger-target mappings due to severe feature interference among different triggers. To address this challenge, we propose MTAttack, the first multi-target backdoor attack framework for enforcing accurate multiple trigger-target mappings in LVLMs. The core of MTAttack is a novel optimization method with two constraints, namely Proxy Space Partitioning constraint and Trigger Prototype Anchoring constraint. It jointly optimizes multiple triggers in the latent space, with each trigger independently mapping clean images to a unique proxy class while at the same time guaranteeing their separability. Experiments on popular benchmarks demonstrate a high success rate of MTAttack for multi-target attacks, substantially outperforming existing attack methods. Furthermore, our attack exhibits strong generalizability across datasets and robustness against backdoor defense strategies. These findings highlight the vulnerability of LVLMs to multi-target backdoor attacks and underscore the urgent need for mitigating such threats.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SparseSurf: Sparse-View 3D Gaussian Splatting for Surface Reconstruction

Meiying Gu
Jiawei Zhang
Jiahe Li
Xiaohan Yu
Haonan Luo
Jin Zheng
Xiao Bai

Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to suboptimal reconstruction quality. Existing approaches address this challenge by employing flattened Gaussian primitives to better fit surface geometry, combined with depth regularization to alleviate geometric ambiguities under limited viewpoints. Nevertheless, the increased anisotropy inherent in flattened Gaussians exacerbates overfitting in sparse-view scenarios, hindering accurate surface fitting and degrading novel view synthesis performance. In this paper, we propose SparseSurf, a method that reconstructs more accurate and detailed surfaces while preserving high-quality novel view rendering. Our key insight is to introduce Stereo Geometry-Texture Alignment, which bridges rendering quality and geometry estimation, thereby jointly enhancing both surface reconstruction and view synthesis. In addition, we present a Pseudo-Feature Enhanced Geometry Consistency that enforces multi-view geometric consistency by incorporating both training and unseen views, effectively mitigating overfitting caused by sparse supervision. Extensive experiments on the DTU, BlendedMVS, and Mip-NeRF360 datasets demonstrate that our method achieves the state-of-the-art performance.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting

Jiawei Zhang
Youmin Zhang
Fabio Tosi
Meiying Gu
Jiahe Li
Xiaohan Yu
Jin Zheng
Xiao Bai

We present Eve3D, a novel framework for dense 3D reconstruction based on 3D Gaussian Splatting (3DGS). While most existing methods rely on imperfect priors derived from pre-trained vision models, Eve3D fully leverages these priors by jointly optimizing both them and the 3DGS backbone. This joint optimization creates a mutually reinforcing cycle: the priors enhance the quality of 3DGS, which in turn refines the priors, further improving the reconstruction. Additionally, Eve3D introduces a novel optimization step based on bundle adjustment, overcoming the limitations of the highly local supervision in standard 3DGS pipelines. Eve3D achieves state-of-the-art results in surface reconstruction and novel view synthesis on the Tanks & Temples, DTU, and Mip-NeRF360 datasets. while retaining fast convergence, highlighting an unprecedented trade-off between accuracy and speed.

PDF Details

NeurIPS Conference 2025 Conference Paper

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

Jiahe Li
Jiawei Zhang
Youmin Zhang
Xiao Bai
Jin Zheng
Xiaohan Yu
Lin Gu

Reconstructing accurate surfaces with radiance fields has achieved remarkable progress in recent years. However, prevailing approaches, primarily based on Gaussian Splatting, are increasingly constrained by representational bottlenecks. In this paper, we introduce GeoSVR, an explicit voxel-based framework that explores and extends the under-investigated potential of sparse voxels for achieving accurate, detailed, and complete surface reconstruction. As strengths, sparse voxels support preserving the coverage completeness and geometric clarity, while corresponding challenges also arise from absent scene constraints and locality in surface refinement. To ensure correct scene convergence, we first propose a Voxel-Uncertainty Depth Constraint that maximizes the effect of monocular depth cues while presenting a voxel-oriented uncertainty to avoid quality degradation, enabling effective and robust scene constraints yet preserving highly accurate geometries. Subsequently, Sparse Voxel Surface Regularization is designed to enhance geometric consistency for tiny voxels and facilitate the voxel-based formation of sharp and accurate surfaces. Extensive experiments demonstrate our superior performance compared to existing methods across diverse challenging scenarios, excelling in geometric accuracy, detail preservation, and reconstruction completeness while maintaining high efficiency. Code is available at https: //github. com/Fictionarry/GeoSVR.

PDF Details

ICRA Conference 2025 Conference Paper

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

Jian Liu 0014
Wei Sun 0028
Hui Yang
Jin Zheng
Zichen Geng
Hossein Rahmani 0001
Ajmal Mian

Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://github.com/CNJianLiu/MonoDiff9D.

Details

AAAI Conference 2025 Conference Paper

Visual Perturbation for Text-Based Person Search

Pengcheng Zhang
Xiaohan Yu
Xiao Bai
Jin Zheng

Text-based person search aims at locating a person described by natural language in uncropped scene images. Recent works for TBPS mainly focus on aligning multi-granularity vision and language representations, neglecting a key discrepancy between training and inference where the former learns to unify vision and language features where the visual side covers all clues described by language, yet the latter matches image-text pairs where the images may capture only part of the described clues due to perturbations such as occlusions, background clutters and misaligned boundaries. To alleviate this issue, we present ViPer: a Visual Perturbation network that learns to match language descriptions with perturbed visual clues. On top of a CLIP-driven baseline, we design three visual perturbation modules: (1) Spatial ViPer that varies person proposals and produces visual features with misaligned boundaries, (2) Attentive ViPer that estimates visual attention on the fly and manipulates attentive visual tokens within a proposal to produce global features under visual perturbations, and (3) Fine-grained ViPer that learns to recover masked visual clues from detailed language descriptions to encourage matching language features with perturbed visual features at the fine granularity. This overall framework thus simulates real-world scenarios at the training stage to minimize the discrepancy and improve the generalization ability of the model. Experimental results demonstrate that the proposed method clearly surpasses previous TBPS methods on the PRW-TBPS and CUHK-SYSU-TBPS datasets.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation

Wenjun Miao
Guansong Pang
Jin Zheng
Xiao Bai

One key challenge in Out-of-Distribution (OOD) detection is the absence of ground-truth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers ($\textit{i. e. }$, pseudo OOD samples) to train OOD detectors. However, we find empirically that the outlier samples often present a distribution shift compared to the true OOD samples, especially in Long-Tailed Recognition (LTR) scenarios, where ID classes are heavily imbalanced, $\textit{i. e. }$, the true OOD samples exhibit very different probability distribution to the head and tailed ID classes from the outliers. In this work, we propose a novel approach, namely $\textit{normalized outlier distribution adaptation}$ (AdaptOD), to tackle this distribution shift problem. One of its key components is $\textit{dynamic outlier distribution adaptation}$ that effectively adapts a vanilla outlier distribution based on the outlier samples to the true OOD distribution by utilizing the OOD knowledge in the predicted OOD samples during inference. Further, to obtain a more reliable set of predicted OOD samples on long-tailed ID data, a novel $\textit{dual-normalized energy loss}$ is introduced in AdaptOD, which leverages class- and sample-wise normalized energy to enforce a more balanced prediction energy on imbalanced ID samples. This helps avoid bias toward the head samples and learn a substantially better vanilla outlier distribution than existing energy losses during training. It also eliminates the need of manually tuning the sensitive margin hyperparameters in energy losses. Empirical results on three popular benchmarks for OOD detection in LTR show the superior performance of AdaptOD over state-of-the-art methods. Code is available at https: //github. com/mala-lab/AdaptOD.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning

Wenjun Miao
Guansong Pang
Xiao Bai
Tianqi Li
Jin Zheng

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to encapsulate the OOD samples. The main challenge is then to tackle the aforementioned confusion between OOD samples and head/tail-class samples when learning the outlier class. To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100-LT, and ImageNet-LT demonstrate that COCL substantially outperforms existing state-of-the-art OOD detection methods in LTR while being able to improve the classification accuracy on ID data. Code is available at https://github.com/mala-lab/COCL.

PDF Details DOI

IROS Conference 2024 Conference Paper

Towards the New Generation of Smart Home-Care with Cloud-Based Internet of Humans and Robotic Things

Dandan Zhang 0001
Jin Zheng

The burgeoning demand for home-care services, driven by a rapidly aging global population, necessitates innovative solutions to alleviate the burden on caregivers and enhance care quality. This paper introduces the development of an Inter-net of Human and Robotic Things (IoHRT) framework, which synergizes cloud computing and the Internet of Robotic Things (IoRT) with human-robot collaborative control mechanisms for home-care applications. The IoHRT framework is designed to enable the seamless integration of customizable robotic platforms with modular, scalable, and compatible features, thereby creating a dynamic and adaptable home-care ecosystem. By leveraging the scalability and computational power of cloud computing, the framework facilitates real-time data analysis and remote monitoring, thus enhancing the efficiency and effectiveness of home-care. We present an in-depth analysis of the key characteristics of IoHRT, supported by evidence embedded in our design, and conduct user studies to evaluate the framework from users’ perspectives. We demonstrate the performance and utility of our proposed framework for the future of home-care applications.

Details

ECAI Conference 2023 Conference Paper

MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient

Sen Wang
Jin Zheng

Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image. Existing monocular 3D detection knowledge distillation methods usually project the LiDAR onto the image plane and train the teacher network accordingly. Transferring LiDAR-based model knowledge to RGB-based models is more complex, so a general distillation strategy is needed. To alleviate cross-modal problem, we propose MonoSKD, a novel Knowledge Distillation framework for Monocular 3D detection based on Spearman correlation coefficient, to learn the relative correlation between cross-modal features. Considering the large gap between these features, strict alignment of features may mislead the training, so we propose a looser Spearman loss. Furthermore, by selecting appropriate distillation locations and removing redundant modules, our scheme saves more GPU resources and trains faster than existing methods. Extensive experiments are performed to verify the effectiveness of our framework on the challenging KITTI 3D object detection benchmark. Our method achieves state-of-the-art performance until submission with no additional inference computational cost. Our codes are available at https: //github. com/Senwang98/MonoSKD.

Details

AAAI Conference 2014 Conference Paper

Semantic Data Representation for Improving Tensor Factorization

Makoto Nakatsuji
Yasuhiro Fujiwara
Hiroyuki Toda
Hiroshi Sawada
Jin Zheng
James Hendler

Predicting human activities is important for improving recommender systems or analyzing social relationships among users. Those human activities are usually represented as multi-object relationships (e. g. user’s tagging activities for items or user’s tweeting activities at some locations). Since multi-object relationships are naturally represented as a tensor, tensor factorization is becoming more important for predicting users’ possible activities. However, its prediction accuracy is weak for ambiguous and/or sparsely observed objects. Our solution, Semantic data Representation for Tensor Factorization (SRTF), tackles these problems by incorporating semantics into tensor factorization based on the following ideas: (1) It first links objects to vocabularies/taxonomies and resolves the ambiguity caused by objects that can be used for multiple purposes. (2) It next links objects to composite classes that merge classes in different kinds of vocabularies/taxonomies (e. g. classes in vocabularies for movie genres and those for directors) to avoid low prediction accuracy caused by rough-grained semantics. (3) It then lifts sparsely observed objects into their classes to solve the sparsity problem for rarely observed objects. To the best of our knowledge, this is the first study that leverages semantics to inject expert knowledge into tensor factorization. Experiments show that SRTF achieves up to 10% higher accuracy than state-of-the-art methods.

PDF Details