Author name cluster

Di Lin

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.

15 papers

1 author row

AAAI Conference 2026 Conference Paper

CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving

Enhui Ma
Lijun Zhou
Tao Tang
Jiahuan Zhang
Junpeng Jiang
Zhan Zhang
Dong Han
Kun Zhan

End-to-end planning methods are the de-facto standard of the current autonomous driving system, while the robustness of the data-driven approaches suffers due to the notorious long-tail problem (i.e., rare but safety-critical failure cases). In this work, we explore whether recent diffusion-based video generation methods (a.k.a. world models), paired with structured 3D layouts, can enable a fully automated pipeline to self-correct such failure cases. We first introduce an agent to simulate the role of product manager, dubbed PM-Agent, which formulates data requirements to collect data similar to the failure cases. Then, we use a generative model that can simulate both data collection and annotation. However, existing generative models struggle to generate high-fidelity data conditioned on 3D layouts. To address this, we propose DriveSora, which can generate spatiotemporally consistent videos aligned with the 3D annotations requested by PM-Agent. We integrate these components into our self-correcting agentic system, CorrectAD. Importantly, our pipeline is end-to-end model agnostic and can be applied to improve any end-to-end planner. Evaluated on both nuScenes and a more challenging in-house dataset across multiple end-to-end planners, CorrectAD corrects 62.5% and 49.8% of failure cases, reducing collision rates by 39% and 27%, respectively.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Exploiting Geometric Structures for Modeling Multi-Agent Behaviors: A New Thinking

Bohao Qu
Xiaofeng Cao
Bing Li
Menglin Zhang
Tuan-Anh Vu
Di Lin
Qing Guo

In this paper, we rethink model agent behaviors from a geometric structure perspective in multi-agent reinforcement learning. Modeling agent behaviors is essential for understanding how agents interact and facilitating effective decisions. The key lies in capturing the dependencies and sequential relationships among agent decisions. Since each decision influences the subsequent choices, this forms a hierarchical and nested tree-like structure of interdependencies. While modeling tree-like data in Euclidean spaces could cause distortion, which results in a loss of agent decision structure information. Motivated by this, we reconsider model agent behaviors in hyperbolic space and propose the Hyperbolic Multi-Agent Representations (HMAR) method, which projects the agent behaviors into a Poincaré ball and leverages hyperbolic neural networks to learn agent policy representations. Additionally, we designed a contrastive loss function to train this network, minimizing the distance in feature space between different representations of the same agent while maximizing the distance between representations of distinct agents. Experimental results provide empirical evidence for the effectiveness of the HMAR method in cooperative and competitive environments, demonstrating the potential of hyperbolic agent representations for effective decision-making in multi-agent environments.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Firing Bits Where It Matters: Spiking-Guided Just Recognizable Distortion Modeling for Machine-Centric Video Coding

Wuyuan Xie
Zhenming Li
Yuwu Lu
Di Lin
Yun Song
Miaohui Wang

Just recognizable distortion (JRD) has emerged as a promising paradigm for machine-centric video coding. However, existing JRD-guided coding methods are limited by coarse annotation granularity and high computational cost, which hinder their deployment. In this paper, we first investigate the impact of different JRD annotation strategies on downstream task performance. By incorporating both instance-level and contextual information, we construct a new JRD dataset with fine-grained annotations compatible with object detection and instance segmentation tasks. To enhance quantization parameter (QP) map prediction while maintaining computational efficiency, we propose a novel spiking neural network (SNN)-based framework that decomposes video frames into spatial structures, channel interactions, and temporal patterns. Furthermore, we introduce a spiking attention mechanism to aggregate task-relevant features and employ adaptive scaling vectors to suppress machine-perceived redundancy, enabling targeted bitrate allocation aligned with task-critical content. Extensive experiments on multiple datasets and backbones demonstrate that our approach consistently outperforms state-of-the-art codec-based and JRD-guided methods in maintaining task performance at ultra-low bitrates, while significantly reducing computational overhead.

PDF Details DOI

AAAI Conference 2026 Conference Paper

FreeMem: Enhancing Consistency in Long Video Generation via Tuning-Free Memory

Jibin Peng
Di Lin
Zhecheng Xu
Haoran Lu
Ruonan Liu
Wuyuan Xie
Miaohui Wang
Lingyu Liang

Text-to-Video (T2V) generation has advanced greatly, yet maintaining consistency remains challenging, especially for tuning-free long video generation. We attribute the consistency problem to cumulative deviations for long video generation at three levels: the random noise lacking correlation results initial deviation between frames; discrepancy in semantic feature tokens between denoising network blocks gradually accumulates as the frame count grows, leading to greater deviations; attention mechanisms struggle to capture global relationships across distant frames in long videos. To address these, we propose FreeMem, a tuning-free framework leveraging hierarchical memory update and injection: the noise memory stabilizes consistency by manipulating low and high frequency components in the initial noise space; the token memory combats inconsistency through adaptive fusion of historical and current semantic feature tokens between denoising network blocks; and the attention memory establishes persistent cache to model long-range relationships within self attention layers. Evaluated on VBench, FreeMem improves subject and background consistency matrics across various methods, offering a practical solution for low-cost, high-consistency long video generation.

PDF Details DOI

AAAI Conference 2025 Conference Paper

mmFAS: Multimodal Face Anti-Spoofing Using Multi-Level Alignment and Switch-Attention Fusion

Geng Chen
Wuyuan Xie
Di Lin
Ye Liu
Miaohui Wang

The increasing number of presentation attacks on reliable face matching has raised concerns and garnered attention towards face anti-spoofing (FAS). However, existing methods for FAS modeling commonly fuse multiple visual modalities (e.g., RGB, Depth, and Infrared) in a straightforward manner, disregarding latent feature gaps that can hinder representation learning. To address this challenge, we propose a novel multimodal FAS framework (mmFAS) that focuses on explicit alignment and fusion of latent features across different modalities. Specifically, we develop a multimodal alignment module to alleviate the latent feature gap by using instance-level contrastive learning and class-level matching simultaneously. Further, we explore a new switch-attention based fusion module to automatically aggregate complementary information and control model complexity. To evaluate the anti-spoofing performance more effectively, we adopt a challenging yet meaningful cross-database protocol involving four benchmark multimodal FAS datasets to simulate realworld scenarios. Extensive experimental results demonstrate the effectiveness of mmFAS in improving the accuracy of FAS systems, outperforming 10 representative methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Open-Vocabulary Part Segmentation via Progressive and Boundary-Aware Strategy

Xinlong Li
Di Lin
Shaoyiyi Gao
Jiaxin Li
Ruonan Liu
Qing Guo

Open-vocabulary part segmentation (OVPS) struggles with structurally connected boundaries due to the inherent conflict between continuous image features and discrete classification mechanism. To address this, we propose PBAPS, a novel training-free framework specifically designed for OVPS. PBAPS leverages structural knowledge of object-part relationships to guide a progressive segmentation from objects to fine-grained parts. To further improve accuracy at challenging boundaries, we introduce a Boundary-Aware Refinement (BAR) module that identifies ambiguous boundary regions by quantifying classification uncertainty, enhances the discriminative features of these ambiguous regions using high-confidence context, and adaptively refines part prototypes to better align with the specific image. Experiments on Pascal-Part-116, ADE20K-Part-234, PartImageNet demonstrate that PBAPS significantly outperforms state-of-the-art methods, achieving 46. 35\% mIoU and 34. 46\% bIoU on Pascal-Part-116. Our code is available at https: //github. com/TJU-IDVLab/PBAPS.

PDF Details

AAAI Conference 2024 Conference Paper

msLPCC: A Multimodal-Driven Scalable Framework for Deep LiDAR Point Cloud Compression

Miaohui Wang
Runnan Huang
Hengjin Dong
Di Lin
Yun Song
Wuyuan Xie

LiDAR sensors are widely used in autonomous driving, and the growing storage and transmission demands have made LiDAR point cloud compression (LPCC) a hot research topic. To address the challenges posed by the large-scale and uneven-distribution (spatial and categorical) of LiDAR point data, this paper presents a new multimodal-driven scalable LPCC framework. For the large-scale challenge, we decouple the original LiDAR data into multi-layer point subsets, compress and transmit each layer separately, so as to ensure the reconstruction quality requirement under different scenarios. For the uneven-distribution challenge, we extract, align, and fuse heterologous feature representations, including point modality with position information, depth modality with spatial distance information, and segmentation modality with category information. Extensive experimental results on the benchmark SemanticKITTI database validate that our method outperforms 14 recent representative LPCC methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire

Yanzhi Li
Keqiu Li
Guohui Li
Zumin Wang
Changqing Ji
Lubo Wang
Die Zuo
Qing Guo

The latest research on wildfire forecast and backtracking has adopted AI models, which require a large amount of data from wildfire scenarios to capture fire spread patterns. This paper explores using cost-effective simulated wildfire scenarios to train AI models and apply them to the analysis of real-world wildfire. This solution requires AI models to minimize the Sim2Real gap, a brand-new topic in the fire spread analysis research community. To investigate the possibility of minimizing the Sim2Real gap, we collect the Sim2Real-Fire dataset that contains 1M simulated scenarios with multi-modal environmental information for training AI models. We prepare 1K real-world wildfire scenarios for testing the AI models. We also propose a deep transformer, S2R-FireTr, which excels in considering the multi-modal environmental information for forecasting and backtracking the wildfire. S2R-FireTr surpasses state-of-the-art methods in real-world wildfire scenarios.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion

Lubo Wang
Di Lin
Kairui Yang
Ruonan Liu
Qing Guo
Wuyuan Xie
Miaohui Wang
Lingyu Liang

Semantic scene completion is a difficult task that involves completing the geometry and semantics of a scene from point clouds in a large-scale environment. Many current methods use 3D/2D convolutions or attention mechanisms, but these have limitations in directly constructing geometry and accurately propagating features from related voxels, the completion likely fails while propagating features in a single pass without considering multiple potential pathways. And they are generally only suitable for static scenes and struggle to handle dynamic aspects. This paper introduces Voxel Proposal Network (VPNet) that completes scenes from 3D and Bird's-Eye-View (BEV) perspectives. It includes Confident Voxel Proposal based on voxel-wise coordinates to propose confident voxels with high reliability for completion. This method reconstructs the scene geometry and implicitly models the uncertainty of voxel-wise semantic labels by presenting multiple possibilities for voxels. VPNet employs Multi-Frame Knowledge Distillation based on the point clouds of multiple adjacent frames to accurately predict the voxel-wise labels by condensing various possibilities of voxel relationships. VPNet has shown superior performance and achieved state-of-the-art results on the SemanticKITTI and SemanticPOSS datasets.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Tingliang Feng
Hao Shi
Xueyang Liu
Wei Feng
Liang Wan
Yanlin Zhou
Di Lin

Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations for target domain's images that train segmentation network. The existing methods globally adapt the scene style of the images, whereas the object styles of different categories or instances are adapted improperly. This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features. The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. With this memory, we select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.

PDF Details

NeurIPS Conference 2022 Conference Paper

Cross-Image Context for Single Image Inpainting

Tingliang Feng
Wei Feng
Weiqi Li
Di Lin

Visual context is of crucial importance for image inpainting. The contextual information captures the appearance and semantic correlation between the image regions, helping to propagate the information of the complete regions for reasoning the content of the corrupted regions. Many inpainting methods compute the visual context based on the regions within the single image. In this paper, we propose the Cross-Image Context Memory (CICM) for learning and using the cross-image context to recover the corrupted regions. CICM consists of multiple sets of the cross-image representations learned from the image regions with different visual patterns. The regional representations are learned across different images, thus providing richer context that benefit the inpainting task. The experimental results demonstrate the effectiveness and generalization of CICM, which achieves state-of-the-art performances on various datasets for single image inpainting.

PDF Details

AAAI Conference 2022 Conference Paper

FFNet: Frequency Fusion Network for Semantic Scene Completion

Xuzhi Wang
Di Lin
Liang Wan

Semantic scene completion (SSC) requires the estimation of the 3D geometric occupancies of objects in the scene, along with the object categories. Currently, many methods employ RGB-D images to capture the geometric and semantic information of objects. These methods use simple but popular spatial- and channel-wise operations, which fuse the information of RGB and depth data. Yet, they ignore the large discrepancy of RGB-D data and the uncertainty measurements of depth data. To solve this problem, we propose the Frequency Fusion Network (FFNet), a novel method for boosting semantic scene completion by better utilizing RGB-D data. FFNet explicitly correlates the RGB-D data in the frequency domain, different from the features directly extracted by the convolution operation. Then, the network uses the correlated information to guide the feature learning from the RG- B and depth images, respectively. Moreover, FFNet accounts for the properties of different frequency components of RGB- D features. It has a learnable elliptical mask to decompose the features learned from the RGB and depth images, attending to various frequencies to facilitate the correlation process of RGB-D data. We evaluate FFNet intensively on the public SSC benchmarks, where FFNet surpasses the state-ofthe-art methods. The code package of FFNet is available at https: //github. com/alanWXZ/FFNet.

PDF Details

NeurIPS Conference 2022 Conference Paper

Generative Status Estimation and Information Decoupling for Image Rain Removal

Di Lin
Xin Wang
Jia Shen
Renjie Zhang
Ruonan Liu
Miaohui Wang
Wuyuan Xie
Qing Guo

Image rain removal requires the accurate separation between the pixels of the rain streaks and object textures. But the confusing appearances of rains and objects lead to the misunderstanding of pixels, thus remaining the rain streaks or missing the object details in the result. In this paper, we propose SEIDNet equipped with the generative Status Estimation and Information Decoupling for rain removal. In the status estimation, we embed the pixel-wise statuses into the status space, where each status indicates a pixel of the rain or object. The status space allows sampling multiple statuses for a pixel, thus capturing the confusing rain or object. In the information decoupling, we respect the pixel-wise statuses, decoupling the appearance information of rain and object from the pixel. Based on the decoupled information, we construct the kernel space, where multiple kernels are sampled for the pixel to remove the rain and recover the object appearance. We evaluate SEIDNet on the public datasets, achieving state-of-the-art performances of image rain removal. The experimental results also demonstrate the generalization of SEIDNet, which can be easily extended to achieve state-of-the-art performances on other image restoration tasks (e. g. , snow, haze, and shadow removal).

PDF Details

NeurIPS Conference 2020 Conference Paper

RANet: Region Attention Network for Semantic Segmentation

Dingguo Shen
Yuanfeng Ji
Ping Li
Yi Wang
Di Lin

Recent semantic segmentation methods model the relationship between pixels to construct the contextual representations. In this paper, we introduce the \emph{Region Attention Network} (RANet), a novel attention network for modeling the relationship between object regions. RANet divides the image into object regions, where we select representative information. In contrast to the previous methods, RANet configures the information pathways between the pixels in different regions, enabling the region interaction to exchange the regional context for enhancing all of the pixels in the image. We train the construction of object regions, the selection of the representative regional contents, the configuration of information pathways and the context exchange between pixels, jointly, to improve the segmentation accuracy. We extensively evaluate our method on the challenging segmentation benchmarks, demonstrating that RANet effectively helps to achieve the state-of-the-art results.

PDF Details

JBHI Journal 2016 Journal Article

Admission Control Over Internet of Vehicles Attached With Medical Sensors for Ubiquitous Healthcare Applications

Di Lin
Fabrice Labeau
Yuanzhe Yao
Athanasios V. Vasilakos
Yu Tang

Wireless technologies and vehicle-mounted or wearable medical sensors are pervasive to support ubiquitous healthcare applications. However, a critical issue of using wireless communications under a healthcare scenario rests at the electromagnetic interference (EMI) caused by radio frequency transmission. A high level of EMI may lead to a critical malfunction of medical sensors, and in such a scenario, a few users who are not transmitting emergency data could be required to reduce their transmit power or even temporarily disconnect from the network in order to guarantee the normal operation of medical sensors as well as the transmission of emergency data. In this paper, we propose a joint power and admission control algorithm to schedule the users' transmission of medical data. The objective of this algorithm is to minimize the number of users who are forced to disconnect from the network while keeping the EMI on medical sensors at an acceptable level. We show that a fixed point of proposed algorithm always exists, and at the fixed point, our proposed algorithm can minimize the number of low-priority users who are required to disconnect from the network. Numerical results illustrate that the proposed algorithm can achieve robust performance against the variations of mobile hospital environments.

Details DOI