Long Chen

Chaoyang Zhu, Long Chen

As the most fundamental scene understanding tasks, object detection and segmentation have made tremendous progress in deep learning era. Due to the expensive manual labeling cost, the annotated categories in existing datasets are often small-scale and pre-defined, i.e., state-of-the-art fully-supervised detectors and segmentors fail to generalize beyond the closed vocabulary. To resolve this limitation, in the last few years, the community has witnessed an increasing attention toward Open-Vocabulary Detection (OVD) and Segmentation (OVS). By ``open-vocabulary'', we mean that the models can classify objects beyond pre-defined categories. In this survey, we provide a comprehensive review on recent developments of OVD and OVS. A taxonomy is first developed to organize different tasks and methodologies. We find that the permission and usage of weak supervision signals can well discriminate different methodologies, including: visual-semantic space mapping, novel visual feature synthesis, region-aware training, pseudo-labeling, knowledge distillation, and transfer learning. The proposed taxonomy is universal across different tasks, covering object detection, semantic/instance/panoptic segmentation, 3D and video understanding. The main design principles, key challenges, development routes, methodology strengths, and weaknesses are thoroughly analyzed. In addition, we benchmark each task along with the vital components of each method in appendix and updated online at https://github.com/seanzhuh/awesome-open-vocabulary-detection-and-segmentation. Finally, several promising directions are provided and discussed to stimulate future research.

Long Chen, Yuchen Li, Chao Huang et al.

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks, lack of systematic summary and research directions in the future. Here we propose a Survey of Surveys (SoS) for total technologies of AD and IVs that reviews the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. To our knowledge, this article is the first SoS with milestones in AD and IVs, which constitutes our complete research work together with two other technical surveys. We anticipate that this article will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Long Chen, Siyu Teng, Bai Li et al.

Growing interest in autonomous driving (AD) and intelligent vehicles (IVs) is fueled by their promise for enhanced safety, efficiency, and economic benefits. While previous surveys have captured progress in this field, a comprehensive and forward-looking summary is needed. Our work fills this gap through three distinct articles. The first part, a "Survey of Surveys" (SoS), outlines the history, surveys, ethics, and future directions of AD and IV technologies. The second part, "Milestones in Autonomous Driving and Intelligent Vehicles Part I: Control, Computing System Design, Communication, HD Map, Testing, and Human Behaviors" delves into the development of control, computing system, communication, HD map, testing, and human behaviors in IVs. This part, the third part, reviews perception and planning in the context of IVs. Aiming to provide a comprehensive overview of the latest advancements in AD and IVs, this work caters to both newcomers and seasoned researchers. By integrating the SoS and Part I, we offer unique insights and strive to serve as a bridge between past achievements and future possibilities in this dynamic field.

Siyu Teng, Xuemin Hu, Peng Deng et al.

Intelligent vehicles (IVs) have gained worldwide attention due to their increased convenience, safety advantages, and potential commercial value. Despite predictions of commercial deployment by 2025, implementation remains limited to small-scale validation, with precise tracking controllers and motion planners being essential prerequisites for IVs. This paper reviews state-of-the-art motion planning methods for IVs, including pipeline planning and end-to-end planning methods. The study examines the selection, expansion, and optimization operations in a pipeline method, while it investigates training approaches and validation scenarios for driving tasks in end-to-end methods. Experimental platforms are reviewed to assist readers in choosing suitable training and validation strategies. A side-by-side comparison of the methods is provided to highlight their strengths and limitations, aiding system-level design choices. Current challenges and future perspectives are also discussed in this survey.

Chen Long, Wenxiao Zhang, Zhe Chen et al.

We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifically designed to handle depth maps with poor quality in real usage. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input by explicitly filling the unstable depth features with stable image features. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth. The key of the embedder is an uncertainty-based fusion module called UFFM to balance the local and long-term information extracted by CNNs and ViTs. Extensive indoor and outdoor experiments demonstrate the robustness of our framework when facing sparse and non-uniform input depths. The pre-trained model and code are available at https://github.com/WHU-USI3DV/SparseDC.

Han Li, Long Chen, Hu Han et al.

Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis. Promising ULD results have been reported by multi-slice-input detection approaches which model 3D context from multiple adjacent CT slices, but such methods still experience difficulty in obtaining a global representation among different slices and within each individual slice since they only use convolution-based fusion operations. In this paper, we propose a novel Slice Attention Transformer (SATr) block which can be easily plugged into convolution-based ULD backbones to form hybrid network structures. Such newly formed hybrid backbones can better model long-distance feature dependency via the cascaded self-attention modules in the Transformer block while still holding a strong power of modeling local features with the convolutional operations in the original backbone. Experiments with five state-of-the-art methods show that the proposed SATr block can provide an almost free boost to lesion detection accuracy without extra hyperparameters or special network designs.

Siyu Teng, Luxi Li, Yuchen Li et al.

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm for unmanned transportation in open-pit mines is proposed in this research. Firstly, we propose a multi-task motion planning algorithm, called FusionPlanner, for autonomous mining trucks by the multi-sensor fusion method to adapt both lateral and longitudinal control tasks for unmanned transportation. Then, we develop a novel benchmark called MiningNav, which offers three validation approaches to evaluate the trustworthiness and robustness of well-trained algorithms in transportation roads of open-pit mines. Finally, we introduce the Parallel Mining Simulator (PMS), a new high-fidelity simulator specifically designed for open-pit mining scenarios. PMS enables the users to manage and control open-pit mine transportation from both the single-truck control and multi-truck scheduling perspectives. The performance of FusionPlanner is tested by MiningNav in PMS, and the empirical results demonstrate a significant reduction in the number of collisions and takeovers of our planner. We anticipate our unmanned transportation paradigm will bring mining trucks one step closer to trustworthiness and robustness in continuous round-the-clock unmanned transportation.

Long Chen, Piyushimita, Thakuriah et al.

As ride-hailing services become increasingly popular, being able to accurately predict demand for such services can help operators efficiently allocate drivers to customers, and reduce idle time, improve congestion, and enhance the passenger experience. This paper proposes UberNet, a deep learning Convolutional Neural Network for short-term prediction of demand for ride-hailing services. UberNet empploys a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services. The proposed model includes two sub-networks that aim to encode the source series of various features and decode the predicting series, respectively. To assess the performance and effectiveness of UberNet, we use 9 months of Uber pickup data in 2014 and 28 spatial and temporal features from New York City. By comparing the performance of UberNet with several other approaches, we show that the prediction quality of the model is highly competitive. Further, Ubernet's prediction performance is better when using economic, social and built environment features. This suggests that Ubernet is more naturally suited to including complex motivators in making real-time passenger demand predictions for ride-hailing services.

Long Chen, Huiwen Wu

Least squares method is one of the simplest and most popular techniques applied in data fitting, imaging processing and high dimension data analysis. The classic methods like QR and SVD decomposition for solving least squares problems has a large computational cost. Iterative methods such as CG and Kaczmarz can reduce the complexity if the matrix is well conditioned but failed for the ill conditioned cases. Preconditioner based on randomized row sampling algorithms have been developed but destroy the sparsity. In this paper, a new preconditioner is constructed by non-uniform row sampling with a probability proportional to the squared norm of rows. Then Gauss Seidel iterations are applied to the normal equation of the sampled matrix which aims to grab the high frequency component of solution. After all, PCG is used to solve the normal equation with this preconditioner. Our preconditioner can keep the sparsity and improve the poor conditioning for highly overdetermined matrix. Experimental studies are presented on several different simulations including dense Gaussian matrix, `semi Gaussian' matrix, sparse random matrix, `UDV' matrix, and random graph Laplacian matrix to show the effectiveness of the proposed least square solver.

Hanrong Shi, Lin Li, Jun Xiao et al.

Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-structure representation based on panoptic segmentation masks. Despite remarkable progress in PSG, almost all existing methods neglect the importance of shape-aware features, which inherently focus on the contours and boundaries of objects. To bridge this gap, we propose a model-agnostic Curricular shApe-aware FEature (CAFE) learning strategy for PSG. Specifically, we incorporate shape-aware features (i.e., mask features and boundary features) into PSG, moving beyond reliance solely on bbox features. Furthermore, drawing inspiration from human cognition, we propose to integrate shape-aware features in an easy-to-hard manner. To achieve this, we categorize the predicates into three groups based on cognition learning difficulty and correspondingly divide the training process into three stages. Each stage utilizes a specialized relation classifier to distinguish specific groups of predicates. As the learning difficulty of predicates increases, these classifiers are equipped with features of ascending complexity. We also incorporate knowledge distillation to retain knowledge acquired in earlier stages. Due to its model-agnostic nature, CAFE can be seamlessly incorporated into any PSG model. Extensive experiments and ablations on two PSG tasks under both robust and zero-shot PSG have attested to the superiority and robustness of our proposed CAFE, which outperforms existing state-of-the-art methods by a large margin.

Xianda Guo, Ruijun Zhang, Yiqun Duan et al.

Accurate spatial reasoning in outdoor environments - covering geometry, object pose, and inter-object relationships - is fundamental to downstream tasks such as mapping, motion forecasting, and high-level planning in autonomous driving. We introduce SURDS, a large-scale benchmark designed to systematically evaluate the spatial reasoning capabilities of vision language models (VLMs). Built on the nuScenes dataset, SURDS comprises 41,080 vision-question-answer training instances and 9,250 evaluation samples, spanning six spatial categories: orientation, depth estimation, pixel-level localization, pairwise distance, lateral ordering, and front-behind relations. We benchmark leading general-purpose VLMs, including GPT, Gemini, and Qwen, revealing persistent limitations in fine-grained spatial understanding. To address these deficiencies, we go beyond static evaluation and explore whether alignment techniques can improve spatial reasoning performance. Specifically, we propose a reinforcement learning-based alignment scheme leveraging spatially grounded reward signals - capturing both perception-level accuracy (location) and reasoning consistency (logic). We further incorporate final-answer correctness and output-format rewards to guide fine-grained policy adaptation. Our GRPO-aligned variant achieves an overall score of 40.80 in the SURDS benchmark. Notably, it outperforms proprietary systems such as GPT-4o (13.30) and Gemini-2.0-flash (35.71). To our best knowledge, this is the first study to demonstrate that reinforcement learning-based alignment can significantly and consistently enhance the spatial reasoning capabilities of VLMs in real-world driving contexts. We release the SURDS benchmark, evaluation toolkit, and GRPO alignment code through: https://github.com/XiandaGuo/Drive-MLLM.

Long Chen, Jinhua Xu

Person Search aims to simultaneously localize and recognize a target person from realistic and uncropped gallery images. One major challenge of person search comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons so as to distinguish persons from the background, while person re-identification (re-ID) focuses on the differences among different persons. In this paper, we propose a novel Sequential Transformer (SeqTR) for end-to-end person search to deal with this challenge. Our SeqTR contains a detection transformer and a novel re-ID transformer that sequentially addresses detection and re-ID tasks. The re-ID transformer comprises the self-attention layer that utilizes contextual information and the cross-attention layer that learns local fine-grained discriminative features of the human body. Moreover, the re-ID transformer is shared and supervised by multi-scale features to improve the robustness of learned person representations. Extensive experiments on two widely-used person search benchmarks, CUHK-SYSU and PRW, show that our proposed SeqTR not only outperforms all existing person search methods with a 59.3% mAP on PRW but also achieves comparable performance to the state-of-the-art results with an mAP of 94.8% on CUHK-SYSU.

Yuxuan Wang, Xuanyu Yi, Qingshan Xu et al.

Personalizing 3D scenes from a single reference image enables intuitive user-guided editing, which requires achieving both multi-view consistency across perspectives and referential consistency with the input image. However, these goals are particularly challenging due to the viewpoint bias caused by the limited perspective provided in a single image. Lacking the mechanisms to effectively expand reference information beyond the original view, existing methods of image-conditioned 3DGS personalization often suffer from this viewpoint bias and struggle to produce consistent results. Therefore, in this paper, we present Consistent Personalization for 3D Gaussian Splatting (CP-GS), a framework that progressively propagates the single-view reference appearance to novel perspectives. In particular, CP-GS integrates pre-trained image-to-3D generation and iterative LoRA fine-tuning to extract and extend the reference appearance, and finally produces faithful multi-view guidance images and the personalized 3DGS outputs through a view-consistent generation process guided by geometric cues. Extensive experiments on real-world scenes show that our CP-GS effectively mitigates the viewpoint bias, achieving high-quality personalization that significantly outperforms existing methods. The code will be released at https://github.com/Yuxuan-W/CP-GS.

Yanghao Wang, Long Chen

Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of various data-scarce tasks. With the powerful image generation ability, diffusion-based DA has shown strong performance gains on different image classification benchmarks. In this paper, we analyze today's diffusion-based DA methods, and argue that they cannot take account of both faithfulness and diversity, which are two critical keys for generating high-quality samples and boosting classification performance. To this end, we propose a novel Diffusion-based DA method: Diff-II. Specifically, it consists of three steps: 1) Category concepts learning: Learning concept embeddings for each category. 2) Inversion interpolation: Calculating the inversion for each image, and conducting circle interpolation for two randomly sampled inversions from the same category. 3) Two-stage denoising: Using different prompts to generate synthesized images in a coarse-to-fine manner. Extensive experiments on various data-scarce image classification tasks (e.g., few-shot, long-tailed, and out-of-distribution classification) have demonstrated its effectiveness over state-of-the-art diffusion-based DA methods.

Ruifei Ding, Zhe Chen, Wen Fan et al.

Street trees are vital to urban livability, providing ecological and social benefits. Establishing a detailed, accurate, and dynamically updated street tree inventory has become essential for optimizing these multifunctional assets within space-constrained urban environments. Given that traditional field surveys are time-consuming and labor-intensive, automated surveys utilizing Mobile Mapping Systems (MMS) offer a more efficient solution. However, existing MMS-acquired tree datasets are limited by small-scale scene, limited annotation, or single modality, restricting their utility for comprehensive analysis. To address these limitations, we introduce WHU-STree, a cross-city, richly annotated, and multi-modal urban street tree dataset. Collected across two distinct cities, WHU-STree integrates synchronized point clouds and high-resolution images, encompassing 21,007 annotated tree instances across 50 species and 2 morphological parameters. Leveraging the unique characteristics, WHU-STree concurrently supports over 10 tasks related to street tree inventory. We benchmark representative baselines for two key tasks--tree species classification and individual tree segmentation. Extensive experiments and in-depth analysis demonstrate the significant potential of multi-modal data fusion and underscore cross-domain applicability as a critical prerequisite for practical algorithm deployment. In particular, we identify key challenges and outline potential future works for fully exploiting WHU-STree, encompassing multi-modal fusion, multi-task collaboration, cross-domain generalization, spatial pattern learning, and Multi-modal Large Language Model for street tree asset management. The WHU-STree dataset is accessible at: https://github.com/WHU-USI3DV/WHU-STree.

Jinpeng Wang, Tianci Luo, Yaohua Zha et al.

Visual In-Context Learning (VICL) enables adaptively solving vision tasks by leveraging pixel demonstrations, mimicking human-like task completion through analogy. Prompt selection is critical in VICL, but current methods assume the existence of a single "ideal" prompt in a pool of candidates, which in practice may not hold true. Multiple suitable prompts may exist, but individually they often fall short, leading to difficulties in selection and the exclusion of useful context. To address this, we propose a new perspective: prompt condensation. Rather than relying on a single prompt, candidate prompts collaborate to efficiently integrate informative contexts without sacrificing resolution. We devise Condenser, a lightweight external plugin that compresses relevant fine-grained context across multiple prompts. Optimized end-to-end with the backbone, Condenser ensures accurate integration of contextual cues. Experiments demonstrate Condenser outperforms state-of-the-arts across benchmark tasks, showing superior context compression, scalability with more prompts, and enhanced computational efficiency compared to ensemble methods, positioning it as a highly competitive solution for VICL. Code is open-sourced at https://github.com/gimpong/CVPR25-Condenser.

Guojun Wang, Jian Wu, Bin Tian et al.

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point--the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d.

Yuxuan Wang, Xuanyu Yi, Zike Wu et al.

The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS models. However, this approach faces a critical issue of multi-view inconsistency, where the guidance images exhibit significant discrepancies across views, leading to mode collapse and visual artifacts of 3DGS. To this end, we introduce View-consistent Editing (VcEdit), a novel framework that seamlessly incorporates 3DGS into image editing processes, ensuring multi-view consistency in edited guidance images and effectively mitigating mode collapse issues. VcEdit employs two innovative consistency modules: the Cross-attention Consistency Module and the Editing Consistency Module, both designed to reduce inconsistencies in edited images. By incorporating these consistency modules into an iterative pattern, VcEdit proficiently resolves the issue of multi-view inconsistency, facilitating high-quality 3DGS editing across a diverse range of scenes. Further video results are shown in http://vcedit.github.io.

Jiehui Huang, Xiao Dong, Wenhui Song et al.

Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily due to insufficient fine-grained control over facial areas and the lack of a comprehensive strategy for ID preservation by fully considering intricate facial details and the overall face. To address these limitations, we introduce ConsistentID, an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts, utilizing only a single reference image. ConsistentID comprises two key components: a multimodal facial prompt generator that combines facial features, corresponding facial descriptions and the overall facial context to enhance precision in facial details, and an ID-preservation network optimized through the facial attention localization strategy, aimed at preserving ID consistency in facial regions. Together, these components significantly enhance the accuracy of ID preservation by introducing fine-grained multimodal ID information from facial regions. To facilitate training of ConsistentID, we present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets. % such as LAION-Face, CelebA, FFHQ, and SFHQ. Experimental results substantiate that our ConsistentID achieves exceptional precision and diversity in personalized facial generation, surpassing existing methods in the MyStyle dataset. Furthermore, while ConsistentID introduces more multimodal ID information, it maintains a fast inference speed during generation.

Siyu Teng, Xuan Li, Yucheng Li et al.

In recent years, open-pit mining has seen significant advancement, the cooperative operation of various specialized machinery substantially enhancing the efficiency of mineral extraction. However, the harsh environment and complex conditions in open-pit mines present substantial challenges for the implementation of autonomous transportation systems. This research introduces a novel paradigm that integrates Scenario Engineering (SE) with autonomous transportation systems to significantly improve the trustworthiness, robustness, and efficiency in open-pit mines by incorporating the four key components of SE, including Scenario Feature Extractor, Intelligence and Index (I&I), Calibration and Certification (C&C), and Verification and Validation (V&V). This paradigm has been validated in two famous open-pit mines, the experiment results demonstrate marked improvements in robustness, trustworthiness, and efficiency. By enhancing the capacity, scalability, and diversity of autonomous transportation, this paradigm fosters the integration of SE and parallel driving and finally propels the achievement of the '6S' objectives.

Xuemin Hu, Pan Chen, Yijun Wen et al.

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the short-term state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods.

Siyu Teng, Xuan Li, Yuchen Li et al.

One critical bottleneck that impedes the development and deployment of autonomous transportation in open-pit mines is guaranteed robustness and trustworthiness in prohibitively extreme scenarios. In this research, a novel scenarios engineering (SE) methodology for the autonomous mining truck is proposed for open-pit mines. SE increases the trustworthiness and robustness of autonomous trucks from four key components: Scenario Feature Extractor, Intelligence & Index (I&I), Calibration & Certification (C&C), and Verification & Validation (V&V). Scenario feature extractor is a comprehensive pipeline approach that captures complex interactions and latent dependencies in complex mining scenarios. I&I effectively enhances the quality of the training dataset, thereby establishing a solid foundation for autonomous transportation in mining areas. C&C is grounded in the intrinsic regulation, capabilities, and contributions of the intelligent systems employed in autonomous transportation to align with traffic participants in the real world and ensure their performance through certification. V&V process ensures that the autonomous transportation system can be correctly implemented, while validation focuses on evaluating the ability of the well-trained model to operate efficiently in the complex and dynamic conditions of the open-pit mines. This methodology addresses the unique challenges of autonomous transportation in open-pit mining, promoting productivity, safety, and performance in mining operations.

Zengzhuang Xu, Bingguang Hao, Zechuan Wang et al.

Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems. As this ability becomes increasingly central to advanced AI systems, the need for high-quality, multi-turn training data to develop and refine it cannot be overstated. Existing data synthesis methods, such as random environment sampling or multi-agent role-playing, are not powerful enough to generate high-quality data in real-world environments. Practical challenges come in three folds: targeted data synthesis, hard query construction, and multi-turn logical dependency. To address these structural deficiencies, we present FunReason-MT, a novel data synthesis framework for real-world multi-turn tool use. FunReason-MT resolves the complexity barrier in multi-turn FC data by employing 1) Environment-API Graph Interactions to gather varied high-quality trajectories with targeted tool, 2) Advanced Tool-Query Synthesis to simplify hard query construction, and 3) Guided Iterative Chain for sophisticated CoT generation. Evaluations on Berkeley Function-Calling Leaderboard (BFCLv3) demonstrate the power of our framework: a 4B model built upon FunReason-MT generated data achieves state-of-the-art performance among comparable-sized models. Further performance improvements on BFCLv4 confirm that FunReason-MT provides a reliable and robust source for agentic learning.

Xuemin Hu, Shen Li, Yingfen Xu et al.

Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given state, resulting in the extrapolation error issue. Recent works address this issue by employing generative adversarial networks (GANs). However, these methods often suffer from insufficient constraints on policy exploration and inaccurate representation of behavior policies. Moreover, the generator in GANs fails in fooling the discriminator while maximizing the expected returns of a policy. Inspired by the diffusion, a generative model with powerful feature expressiveness, we propose a new offline RL method named Diffusion Policies with Generative Adversarial Networks (DiffPoGAN). In this approach, the diffusion serves as the policy generator to generate diverse distributions of actions, and a regularization method based on maximum likelihood estimation (MLE) is developed to generate data that approximate the distribution of behavior policies. Besides, we introduce an additional regularization term based on the discriminator output to effectively constrain policy exploration for policy improvement. Comprehensive experiments are conducted on the datasets for deep data-driven reinforcement learning (D4RL), and experimental results show that DiffPoGAN outperforms state-of-the-art methods in offline RL.

Long Chen, Yuchen Li, Chao Huang et al.

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, High Definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this paper is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Feifei Shao, Long Chen, Jian Shao et al.

Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), i.e., detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-standing and challenging tasks in the CV community. With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention. Hundreds of WSOD and WSOL methods and numerous techniques have been proposed in the deep learning era. To this end, in this paper, we consider WSOL is a sub-task of WSOD and provide a comprehensive survey of the recent achievements of WSOD. Specifically, we firstly describe the formulation and setting of the WSOD, including the background, challenges, basic framework. Meanwhile, we summarize and analyze all advanced techniques and training tricks for improving detection performance. Then, we introduce the widely-used datasets and evaluation metrics of WSOD. Lastly, we discuss the future directions of WSOD. We believe that these summaries can help pave a way for future research on WSOD and WSOL.

Luca Bergamini, Yawei Ye, Oliver Scheel et al.

In this work, we present a simple end-to-end trainable machine learning system capable of realistically simulating driving experiences. This can be used for the verification of self-driving system performance without relying on expensive and time-consuming road testing. In particular, we frame the simulation problem as a Markov Process, leveraging deep neural networks to model both state distribution and transition function. These are trainable directly from the existing raw observations without the need for any handcrafting in the form of plant or kinematic models. All that is needed is a dataset of historical traffic episodes. Our formulation allows the system to construct never seen scenes that unfold realistically reacting to the self-driving car's behaviour. We train our system directly from 1,000 hours of driving logs and measure both realism, reactivity of the simulation as the two key properties of the simulation. At the same time, we apply the method to evaluate the performance of a recently proposed state-of-the-art ML planning system trained from human driving logs. We discover this planning system is prone to previously unreported causal confusion issues that are difficult to test by non-reactive simulation. To the best of our knowledge, this is the first work that directly merges highly realistic data-driven simulations with a closed-loop evaluation for self-driving vehicles. We make the data, code, and pre-trained models publicly available to further stimulate simulation development.

Han Li, Long Chen, Hu Han et al.

Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis. Promising ULD results have been reported by coarse-to-fine two-stage detection approaches, but such two-stage ULD methods still suffer from issues like imbalance of positive v.s. negative anchors during object proposal and insufficient supervision problem during localization regression and classification of the region of interest (RoI) proposals. While leveraging pseudo segmentation masks such as bounding map (BM) can reduce the above issues to some degree, it is still an open problem to effectively handle the diverse lesion shapes and sizes in ULD. In this paper, we propose a BM-based conditional training for two-stage ULD, which can (i) reduce positive vs. negative anchor imbalance via BM-based conditioning (BMC) mechanism for anchor sampling instead of traditional IoU-based rule; and (ii) adaptively compute size-adaptive BM (ABM) from lesion bounding box, which is used for improving lesion localization accuracy via ABMsupervised segmentation. Experiments with four state-of-the-art methods show that the proposed approach can bring an almost free detection accuracy improvement without requiring expensive lesion mask annotations.

Guojun Wang, Bin Tian, Yachen Zhang et al.

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To solve this issue, we propose a single-stage multi-view fusion framework that takes LiDAR bird's-eye view, LiDAR range view and camera view images as inputs for 3D object detection. To effectively fuse multi-view features, we propose an attentive pointwise fusion (APF) module to estimate the importance of the three sources with attention mechanisms that can achieve adaptive fusion of multi-view features in a pointwise manner. Furthermore, an attentive pointwise weighting (APW) module is designed to help the network learn structure information and point feature importance with two extra tasks, namely, foreground classification and center regression, and the predicted foreground probability is used to reweight the point features. We design an end-to-end learnable network named MVAF-Net to integrate these two components. Our evaluations conducted on the KITTI 3D object detection datasets demonstrate that the proposed APF and APW modules offer significant performance gains. Moreover, the proposed MVAF-Net achieves the best performance among all single-stage fusion methods and outperforms most two-stage fusion methods, achieving the best trade-off between speed and accuracy on the KITTI benchmark.

Teng Liu, Yang Xing, Long Chen et al.

Parallel driving is a novel framework to synthesize vehicle intelligence and transport automation. This article aims to define digital quadruplets in parallel driving. In the cyber-physical-social systems (CPSS), based on the ACP method, the names of the digital quadruplets are first given, which are descriptive, predictive, prescriptive and real vehicles. The objectives of the three virtual digital vehicles are interacting, guiding, simulating and improving with the real vehicles. Then, the three virtual components of the digital quadruplets are introduced in detail and their applications are also illustrated. Finally, the real vehicles in the parallel driving system and the research process of the digital quadruplets are depicted. The presented digital quadruplets in parallel driving are expected to make the future connected automated driving safety, efficiently and synergistically.

Teng Liu, Bin Tian, Yunfeng Ai et al.

As a combination of various kinds of technologies, autonomous vehicles could complete a series of driving tasks by itself, such as perception, decision-making, planning, and control. Since there is no human driver to handle the emergency situation, future transportation information is significant for automated vehicles. This paper proposes different methods to forecast the time series for autonomous vehicles, which are the nearest neighborhood (NN), fuzzy coding (FC), and long short term memory (LSTM). First, the formulation and operational process for these three approaches are introduced. Then, the vehicle velocity is regarded as a case study and the real-world dataset is utilized to predict future information via these techniques. Finally, the performance, merits, and drawbacks of the presented methods are analyzed and discussed.

Yuli Wu, Long Chen, Dorit Merhof

As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab.

Yaodong Cui, Ren Chen, Wenbo Chu et al.

Autonomous vehicles were experiencing rapid development in the past few years. However, achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic driving environment. Therefore, autonomous vehicles are equipped with a suite of different sensors to ensure robust, accurate environmental perception. In particular, the camera-LiDAR fusion is becoming an emerging research theme. However, so far there has been no critical review that focuses on deep-learning-based camera-LiDAR fusion methods. To bridge this gap and motivate future research, this paper devotes to review recent deep-learning-based data fusion approaches that leverage both image and point cloud. This review gives a brief overview of deep learning on image and point cloud data processing. Followed by in-depth reviews of camera-LiDAR fusion methods in depth completion, object detection, semantic segmentation, tracking and online cross-sensor calibration, which are organized based on their respective fusion levels. Furthermore, we compare these methods on publicly available datasets. Finally, we identified gaps and over-looked challenges between current academic researches and real-world applications. Based on these observations, we provide our insights and point out promising research directions.

Qin Zou, Zheng Zhang, Ling Cao et al.

Hash coding has been widely used in approximate nearest neighbor search for large-scale image retrieval. Given semantic annotations such as class labels and pairwise similarities of the training data, hashing methods can learn and generate effective and compact binary codes. While some newly introduced images may contain undefined semantic labels, which we call unseen images, zeor-shot hashing techniques have been studied. However, existing zeor-shot hashing methods focus on the retrieval of single-label images, and cannot handle multi-label images. In this paper, for the first time, a novel transductive zero-shot hashing method is proposed for multi-label unseen image retrieval. In order to predict the labels of the unseen/target data, a visual-semantic bridge is built via instance-concept coherence ranking on the seen/source data. Then, pairwise similarity loss and focal quantization loss are constructed for training a hashing model using both the seen/source and unseen/target data. Extensive evaluations on three popular multi-label datasets demonstrate that, the proposed hashing method achieves significantly better results than the competing methods.

Yucai Bai, Lei Fan, Ziyu Pan et al.

In many robotic applications, especially for the autonomous driving, understanding the semantic information and the geometric structure of surroundings are both essential. Semantic 3D maps, as a carrier of the environmental knowledge, are then intensively studied for their abilities and applications. However, it is still challenging to produce a dense outdoor semantic map from a monocular image stream. Motivated by this target, in this paper, we propose a method for large-scale 3D reconstruction from consecutive monocular images. First, with the correlation of underlying information between depth and semantic prediction, a novel multi-task Convolutional Neural Network (CNN) is designed for joint prediction. Given a single image, the network learns low-level information with a shared encoder and separately predicts with decoders containing additional Atrous Spatial Pyramid Pooling (ASPP) layers and the residual connection which merits disparities and semantic mutually. To overcome the inconsistency of monocular depth prediction for reconstruction, post-processing steps with the superpixelization and the effective 3D representation approach are obtained to give the final semantic map. Experiments are compared with other methods on both semantic labeling and depth prediction. We also qualitatively demonstrate the map reconstructed from large-scale, difficult monocular image sequences to prove the effectiveness and superiority.

Qing Wang, Long Chen, Wei Tian

Imitation learning for end-to-end autonomous driving has drawn attention from academic communities. Current methods either only use images as the input which is ambiguous when a car approaches an intersection, or use additional command information to navigate the vehicle but not automated enough. Focusing on making the vehicle drive along the given path, we propose a new navigation command that does not require human's participation and a novel model architecture called angle branched network. Both the new navigation command and the angle branched network are easy to understand and effective. Besides, we find that not only segmentation information but also depth information can boost the performance of the driving model. We conduct experiments in a 3D urban simulator and both qualitative and quantitative evaluation results show the effectiveness of our model.

Long Chen, Wen Tang, Nigel John et al.

Mixed Reality (MR) is a powerful interactive technology that yields new types of user experience. We present a semantic based interactive MR framework that exceeds the current geometry level approaches, a step change in generating high-level context-aware interactions. Our key insight is to build semantic understanding in MR that not only can greatly enhance user experience through object-specific behaviours, but also pave the way for solving complex interaction design challenges. The framework generates semantic properties of the real world environment through dense scene reconstruction and deep image understanding. We demonstrate our approach with a material-aware prototype system for generating context-aware physical interactions between the real and the virtual objects. Quantitative and qualitative evaluations are carried out and the results show that the framework delivers accurate and fast semantic information in interactive MR environment, providing effective semantic level interactions.

Zheng Zhang, Qin Zou, Yuewei Lin et al.

Hash coding has been widely used in the approximate nearest neighbor search for large-scale image retrieval. Recently, many deep hashing methods have been proposed and shown largely improved performance over traditional feature-learning-based methods. Most of these methods examine the pairwise similarity on the semantic-level labels, where the pairwise similarity is generally defined in a hard-assignment way. That is, the pairwise similarity is '1' if they share no less than one class label and '0' if they do not share any. However, such similarity definition cannot reflect the similarity ranking for pairwise images that hold multiple labels. In this paper, a new deep hashing method is proposed for multi-label image retrieval by re-defining the pairwise similarity into an instance similarity, where the instance similarity is quantified into a percentage based on the normalized semantic labels. Based on the instance similarity, a weighted cross-entropy loss and a minimum mean square error loss are tailored for loss-function construction, and are efficiently used for simultaneous feature learning and hash coding. Experiments on three popular datasets demonstrate that, the proposed method outperforms the competing methods and achieves the state-of-the-art performance in multi-label image retrieval.

Long Chen, Wen Tang, Nigel W. John

The potential of Augmented Reality (AR) technology to assist minimally invasive surgeries (MIS) lies in its computational performance and accuracy in dealing with challenging MIS scenes. Even with the latest hardware and software technologies, achieving both real-time and accurate augmented information overlay in MIS is still a formidable task. In this paper, we present a novel real-time AR framework for MIS that achieves interactive geometric aware augmented reality in endoscopic surgery with stereo views. Our framework tracks the movement of the endoscopic camera and simultaneously reconstructs a dense geometric mesh of the MIS scene. The movement of the camera is predicted by minimising the re-projection error to achieve a fast tracking performance, while the 3D mesh is incrementally built by a dense zero mean normalised cross correlation stereo matching method to improve the accuracy of the surface reconstruction. Our proposed system does not require any prior template or pre-operative scan and can infer the geometric information intra-operatively in real-time. With the geometric information available, our proposed AR framework is able to interactively add annotations, localisation of tumours and vessels, and measurement labelling with greater precision and accuracy compared with the state of the art approaches.

Lei Fan, Ziyu Pan, Long Chen et al.

Reconstruction based on the stereo camera has received considerable attention recently, but two particular challenges still remain. The first concerns the need to aggregate similar pixels in an effective approach, and the second is to maintain as much of the available information as possible while ensuring sufficient accuracy. To overcome these issues, we propose a new 3D representation method, namely, planecell, that extracts planarity from the depth-assisted image segmentation and then projects these depth planes into the 3D world. An energy function formulated from Conditional Random Field that generalizes the planar relationships is maximized to merge coplanar segments. We evaluate our method with a variety of reconstruction baselines on both KITTI and Middlebury datasets, and the results indicate the superiorities compared to other 3D space representation methods in accuracy, memory requirements and further applications.

Long Chen, Junyu Dong, ShengKe Wang et al.

Fine-grained recognition is a challenging task due to the small intra-category variances. Most of top-performing fine-grained recognition methods leverage parts of objects for better performance. Therefore, part annotations which are extremely computationally expensive are required. In this paper, we propose a novel cascaded deep CNN detection framework for fine-grained recognition which is trained to detect the whole object without considering parts. Nevertheless, most of current top-performing detection networks use the N+1 class (N object categories plus background) softmax loss, and the background category with much more training samples dominates the feature learning progress so that the features are not good for object categories with fewer samples. To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories. Experiments show that our proposed recognition framework achieves comparable performance with state-of-the-art, part-free, fine-grained recognition methods on the CUB-200-2011 Bird dataset. Moreover, our method even outperforms most of part-based methods while does not need part annotations at the training stage and is free from any annotations at test stage.