arXiv subjects

Wenhao Li

Publications and source records attributed to Wenhao Li.

At least 181 records · Page 10Linked to original sources

arXiv2025

JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images

Existing vision-language understanding benchmarks largely consist of images of objects in their usual contexts. As a consequence, recent multimodal large language models can perform well with only a shallow visual understanding by relying on background language biases. Thus, strong performance on these benchmarks does not necessarily correlate with strong visual understanding. In this paper, we release JourneyBench, a comprehensive human-annotated benchmark of generated images designed to assess the model's fine-grained multimodal reasoning abilities across five tasks: complementary multimodal chain of thought, multi-image VQA, imaginary image captioning, VQA with hallucination triggers, and fine-grained retrieval with sample-specific distractors. Unlike existing benchmarks, JourneyBench explicitly requires fine-grained multimodal reasoning in unusual imaginary scenarios where language bias and holistic image gist are insufficient. We benchmark state-of-the-art models on JourneyBench and analyze performance along a number of fine-grained dimensions. Results across all five tasks show that JourneyBench is exceptionally challenging for even the best models, indicating that models' visual reasoning abilities are not as strong as they first appear. We discuss the implications of our findings and propose avenues for further research.

cs.CV↗

arXiv2025

Interactive 3D Medical Image Segmentation with SAM 2

Interactive medical image segmentation (IMIS) has shown significant potential in enhancing segmentation accuracy by integrating iterative feedback from medical professionals. However, the limited availability of enough 3D medical data restricts the generalization and robustness of most IMIS methods. The Segment Anything Model (SAM), though effective for 2D images, requires expensive semi-auto slice-by-slice annotations for 3D medical images. In this paper, we explore the zero-shot capabilities of SAM 2, the next-generation Meta SAM model trained on videos, for 3D medical image segmentation. By treating sequential 2D slices of 3D images as video frames, SAM 2 can fully automatically propagate annotations from a single frame to the entire 3D volume. We propose a practical pipeline for using SAM 2 in 3D medical image segmentation and present key findings highlighting its efficiency and potential for further optimization. Concretely, numerical experiments on the BraTS2020 and the medical segmentation decathlon datasets demonstrate that SAM 2 still has a gap with supervised methods but can narrow the gap in specific settings and organ types, significantly reducing the annotation burden on medical professionals. Our code will be open-sourced and available at https://github.com/Chuyun-Shen/SAM_2_Medical_3D.

cs.CV↗

arXiv2025

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we propose TCPFormer, which leverages an implicit pose proxy as an intermediate representation. Each proxy within the implicit pose proxy can build one temporal correlation therefore helping us learn more comprehensive temporal correlation of human motion. Specifically, our method consists of three key components: Proxy Update Module (PUM), Proxy Invocation Module (PIM), and Proxy Attention Module (PAM). PUM first uses pose features to update the implicit pose proxy, enabling it to store representative information from the pose sequence. PIM then invocates and integrates the pose proxy with the pose sequence to enhance the motion semantics of each pose. Finally, PAM leverages the above mapping between the pose sequence and pose proxy to enhance the temporal correlation of the whole pose sequence. Experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that our proposed TCPFormer outperforms the previous state-of-the-art methods.

cs.CV↗

arXiv2024

Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models

Diffusion models have demonstrated remarkable efficacy in various generative tasks with the predictive prowess of denoising model. Currently, diffusion models employ a uniform denoising model across all timesteps. However, the inherent variations in data distributions at different timesteps lead to conflicts during training, constraining the potential of diffusion models. To address this challenge, we propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model. Additionally, we introduce Proxy-based Pruning to further customize the denoising models. This method transforms the pruning problem of diffusion models into a multi-round decision-making problem, enabling precise pruning of diffusion models. Our experiments validate the effectiveness of TDC Training, demonstrating improvements in FID of 1.5 on ImageNet64 compared to original IDDPM, while saving about 20\% of computational resources.

cs.LG↗

arXiv2024

Decoupled Video Generation with Chain of Training-free Diffusion Model Experts

Video generation models hold substantial potential in areas such as filmmaking. However, current video diffusion models need high computational costs and produce suboptimal results due to extreme complexity of video generation task. In this paper, we propose \textbf{ConFiner}, an efficient video generation framework that decouples video generation into easier subtasks: structure \textbf{con}trol and spatial-temporal re\textbf{fine}ment. It can generate high-quality videos with chain of off-the-shelf diffusion model experts, each expert responsible for a decoupled subtask. During the refinement, we introduce coordinated denoising, which can merge multiple diffusion experts' capabilities into a single sampling. Furthermore, we design ConFiner-Long framework, which can generate long coherent video with three constraint strategies on ConFiner. Experimental results indicate that with only 10\% of the inference cost, our ConFiner surpasses representative models like Lavie and Modelscope across all objective and subjective metrics. And ConFiner-Long can generate high-quality and coherent videos with up to 600 frames.

cs.CV↗

arXiv2024

Magnifier: Detecting Network Access via Lightweight Traffic-based Fingerprints

Network access detection plays a crucial role in global network management, enabling efficient network monitoring and topology measurement by identifying unauthorized network access and gathering detailed information about mobile devices. Existing methods for endpoint-based detection primarily rely on deploying monitoring software to recognize network connections. However, the challenges associated with developing and maintaining such systems have limited their universality and coverage in practical deployments, especially given the cost implications of covering a wide array of devices with heterogeneous operating systems. To tackle the issues, we propose Magnifier for mobile device network access detection that, for the first time, passively infers access patterns from backbone traffic at the gateway level. Magnifier's foundation is the creation of device-specific access patterns using the innovative Domain Name Forest (dnForest) fingerprints. We then employ a two-stage distillation algorithm to fine-tune the weights of individual Domain Name Trees (dnTree) within each dnForest, emphasizing the unique device fingerprints. With these meticulously crafted fingerprints, Magnifier efficiently infers network access from backbone traffic using a lightweight fingerprint matching algorithm. Our experimental results, conducted in real-world scenarios, demonstrate that Magnifier exhibits exceptional universality and coverage in both initial and repetitive network access detection in real-time. To facilitate further research, we have thoughtfully curated the NetCess2023 dataset, comprising network access data from 26 different models across 7 brands, covering the majority of mainstream mobile devices. We have also made both the Magnifier prototype and the NetCess2023 dataset publicly available\footnote{https://github.com/SecTeamPolaris/Magnifier}.

cs.NI↗

arXiv2024

Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a \textbf{D}ual-branch \textbf{G}raph \textbf{T}ransformer network for 3D human mesh \textbf{R}econstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to parallelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at \href{https://github.com/TangTao-PKU/DGTR}{\textcolor{myBlue}{https://github.com/TangTao-PKU/DGTR}}.

cs.CV↗

arXiv2024

D$^3$epth: Self-Supervised Depth Estimation with Dynamic Mask in Dynamic Scenes

Depth estimation is a crucial technology in robotics. Recently, self-supervised depth estimation methods have demonstrated great potential as they can efficiently leverage large amounts of unlabelled real-world data. However, most existing methods are designed under the assumption of static scenes, which hinders their adaptability in dynamic environments. To address this issue, we present D$^3$epth, a novel method for self-supervised depth estimation in dynamic scenes. It tackles the challenge of dynamic objects from two key perspectives. First, within the self-supervised framework, we design a reprojection constraint to identify regions likely to contain dynamic objects, allowing the construction of a dynamic mask that mitigates their impact at the loss level. Second, for multi-frame depth estimation, we introduce a cost volume auto-masking strategy that leverages adjacent frames to identify regions associated with dynamic objects and generate corresponding masks. This provides guidance for subsequent processes. Furthermore, we propose a spectral entropy uncertainty module that incorporates spectral entropy to guide uncertainty estimation during depth fusion, effectively addressing issues arising from cost volume computation in dynamic environments. Extensive experiments on KITTI and Cityscapes datasets demonstrate that the proposed method consistently outperforms existing self-supervised monocular depth estimation baselines. Code is available at \url{https://github.com/Csyunling/D3epth}.

cs.CV↗

arXiv2024

ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.

cs.CV↗

arXiv2024

Stochastic diagonal estimation with adaptive parameter selection

In this paper, we investigate diagonal estimation for large or implicit matrices, aiming to develop a novel and efficient stochastic algorithm that incorporates adaptive parameter selection. We explore the influence of different eigenvalue distributions on diagonal estimation and analyze the necessity of introducing the projection method and adaptive parameter optimization into the stochastic diagonal estimator. Based on this analysis, we derive a lower bound on the number of random query vectors needed to satisfy a given probabilistic error bound, which forms the foundation of our adaptive stochastic diagonal estimation algorithm. Finally, numerical experiments demonstrate the effectiveness of the proposed estimator for various matrix types, showcasing its efficiency and stability compared to other existing stochastic diagonal estimation methods.

stat.ML↗

arXiv2024

KNN Transformer with Pyramid Prompts for Few-Shot Learning

Few-Shot Learning (FSL) aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features. However, they usually struggle to capture complex semantic relationships between textual and visual features. Moreover, vanilla self-attention is heavily affected by useless information in images, severely constraining the potential of semantic priors in FSL due to the confusion of numerous irrelevant tokens during interaction. To address these aforementioned issues, a K-NN Transformer with Pyramid Prompts (KTPP) is proposed to select discriminative information with K-NN Context Attention (KCA) and adaptively modulate visual features with Pyramid Cross-modal Prompts (PCP). First, for each token, the KCA only selects the K most relevant tokens to compute the self-attention matrix and incorporates the mean of all tokens as the context prompt to provide the global context in three cascaded stages. As a result, irrelevant tokens can be progressively suppressed. Secondly, pyramid prompts are introduced in the PCP to emphasize visual features via interactions between text-based class-aware prompts and multi-scale visual features. This allows the ViT to dynamically adjust the importance weights of visual features based on rich semantic information at different scales, making models robust to spatial variations. Finally, augmented visual features and class-aware prompts are interacted via the KCA to extract class-specific features. Consequently, our model further enhances noise-free visual representations via deep cross-modal interactions, extracting generalized visual representation in scenarios with few labeled samples. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our method.

cs.CV↗

arXiv2024

HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction

Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the Mixture-of-Expert (MoE) architecture. However, the MoE-based method, which aims to project all information in the same feature space, cannot effectively deal with the complex relationships inherent among various scenarios and tasks, resulting in unsatisfactory performance. To tackle the problem, we propose a Hierarchical information extraction Network (HiNet) for multi-scenario and multi-task recommendation, which achieves hierarchical extraction based on coarse-to-fine knowledge transfer scheme. The multiple extraction layers of the hierarchical network enable the model to enhance the capability of transferring valuable information across scenarios while preserving specific features of scenarios and tasks. Furthermore, a novel scenario-aware attentive network module is proposed to model correlations between scenarios explicitly. Comprehensive experiments conducted on real-world industrial datasets from Meituan Meishi platform demonstrate that HiNet achieves a new state-of-the-art performance and significantly outperforms existing solutions. HiNet is currently fully deployed in two scenarios and has achieved 2.87% and 1.75% order quantity gain respectively.

cs.IR↗

arXiv2024

C$^3$P-VoxelMap: Compact, Cumulative and Coalescible Probabilistic Voxel Mapping

This work presents a compact, cumulative and coalescible probabilistic voxel mapping method to enhance performance, accuracy and memory efficiency in LiDAR odometry. Probabilistic voxel mapping requires storing past point clouds and re-iterating on them to update the uncertainty every iteration, which consumes large memory space and CPU cycles. To solve this problem, we propose a two-folded strategy. First, we introduce a compact point-free representation for probabilistic voxels and derive a cumulative update of the planar uncertainty without caching original point clouds. Our voxel structure only keeps track of a predetermined set of statistics for points that lie inside it. This method reduces the runtime complexity from $O(MN)$ to $O(N)$ and the space complexity from $O(N)$ to $O(1)$ where $M$ is the number of iterations and $N$ is the number of points. Second, to further minimize memory usage and enhance mapping accuracy, we provide a strategy to dynamically merge voxels associated with the same physical planes by taking advantage of the geometric features in the real world. Rather than scanning for these coalescible voxels constantly at every iteration, our merging strategy accumulates voxels in a locality-sensitive hash and triggers merging lazily. On-demand merging not only reduces memory footprint with minimal computational overhead but also improves localization accuracy thanks to cross-voxel denoising. Experiments exhibit 20% higher accuracy, 20% faster performance and 70% lower memory consumption than the state-of-the-art.

cs.RO↗

arXiv2024

GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation

Modern multi-layer perceptron (MLP) models have shown competitive results in learning visual representations without self-attention. However, existing MLP models are not good at capturing local details and lack prior knowledge of human body configurations, which limits their modeling power for skeletal representation learning. To address these issues, we propose a simple yet effective graph-reinforced MLP-Like architecture, named GraphMLP, that combines MLPs and graph convolutional networks (GCNs) in a global-local-graphical unified architecture for 3D human pose estimation. GraphMLP incorporates the graph structure of human bodies into an MLP model to meet the domain-specific demand of the 3D human pose, while allowing for both local and global spatial interactions. Furthermore, we propose to flexibly and efficiently extend the GraphMLP to the video domain and show that complex temporal dynamics can be effectively modeled in a simple way with negligible computational cost gains in the sequence length. To the best of our knowledge, this is the first MLP-Like architecture for 3D human pose estimation in a single frame and a video sequence. Extensive experiments show that the proposed GraphMLP achieves state-of-the-art performance on two datasets, i.e., Human3.6M and MPI-INF-3DHP. Code and models are available at https://github.com/Vegetebird/GraphMLP.

cs.CV↗

arXiv2024

Three-dimensional topological valley photonics

Topological valley photonics, which exploits valley degree of freedom to manipulate electromagnetic waves, offers a practical and effective pathway for various classical and quantum photonic applications across the entire spectrum. Current valley photonics, however, has been limited to two dimensions, which typically suffer from out-of-plane losses and can only manipulate the flow of light in planar geometries. Here, we have theoretically and experimentally developed a framework of three-dimensional (3D) topological valley photonics with a complete photonic bandgap and vectorial valley contrasting physics. Unlike the two-dimensional counterparts with a pair of valleys characterized by scalar valley Chern numbers, the 3D valley systems exhibit triple pairs of valleys characterized by valley Chern vectors, enabling the creation of vectorial bulk valley vortices and canalized chiral valley surface states. Notably, the valley Chern vectors and the circulating propagation direction of the valley surface states are intrinsically governed by the right-hand-thumb rule. Our findings reveal the vectorial nature of the 3D valley states and highlight their potential applications in 3D waveguiding, directional radiation, and imaging.

physics.optics↗

arXiv2024

LLM-enhanced Scene Graph Learning for Household Rearrangement

The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In achieving such task, we propose to mine object functionality with user preference alignment directly from the scene itself, without relying on human intervention. To do so, we work with scene graph representation and propose LLM-enhanced scene graph learning which transforms the input scene graph into an affordance-enhanced graph (AEG) with information-enhanced nodes and newly discovered edges (relations). In AEG, the nodes corresponding to the receptacle objects are augmented with context-induced affordance which encodes what kind of carriable objects can be placed on it. New edges are discovered with newly discovered non-local relations. With AEG, we perform task planning for scene rearrangement by detecting misplaced carriables and determining a proper placement for each of them. We test our method by implementing a tiding robot in simulator and perform evaluation on a new benchmark we build. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on misplacement detection and the following rearrangement planning.

cs.RO↗

arXiv2024

PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection

The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying solely on point features within regions of interest can lead to information loss and limitations in local feature representation. To tackle these challenges, we propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN). PVAFN leverages an attention mechanism to improve multi-modal feature fusion during the feature extraction phase. In the refinement stage, it utilizes a multi-pooling strategy to integrate both multi-scale and region-specific information effectively. The point-voxel attention mechanism adaptively combines point cloud and voxel-based Bird's-Eye-View (BEV) features, resulting in richer object representations that help to reduce false detections. Additionally, a multi-pooling enhancement module is introduced to boost the model's perception capabilities. This module employs cluster pooling and pyramid pooling techniques to efficiently capture key geometric details and fine-grained shape structures, thereby enhancing the integration of local and global features. Extensive experiments on the KITTI and Waymo datasets demonstrate that the proposed PVAFN achieves competitive performance. The code and models will be available.

cs.CV↗

arXiv2024

Scene-wise Adaptive Network for Dynamic Cold-start Scenes Optimization in CTR Prediction

In the realm of modern mobile E-commerce, providing users with nearby commercial service recommendations through location-based online services has become increasingly vital. While machine learning approaches have shown promise in multi-scene recommendation, existing methodologies often struggle to address cold-start problems in unprecedented scenes: the increasing diversity of commercial choices, along with the short online lifespan of scenes, give rise to the complexity of effective recommendations in online and dynamic scenes. In this work, we propose Scene-wise Adaptive Network (SwAN), a novel approach that emphasizes high-performance cold-start online recommendations for new scenes. Our approach introduces several crucial capabilities, including scene similarity learning, user-specific scene transition cognition, scene-specific information construction for the new scene, and enhancing the diverged logical information between scenes. We demonstrate SwAN's potential to optimize dynamic multi-scene recommendation problems by effectively online handling cold-start recommendations for any newly arrived scenes. More encouragingly, SwAN has been successfully deployed in Meituan's online catering recommendation service, which serves millions of customers per day, and SwAN has achieved a 5.64% CTR index improvement relative to the baselines and a 5.19% increase in daily order volume proportion.

cs.IR↗