arXiv subjects

Wei Bao

Publications and source records attributed to Wei Bao.

At least 19 recordsLinked to original sources

arXiv2026

GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models

Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the large number of visual tokens. Existing video token compression methods typically rely on frame-wise saliency or heuristic token merging, which can over-focus on locally salient regions and produce ambiguous fused features. To address these issues, we propose GeoTrace, a training-free spatiotemporal token compression framework that decomposes video evidence into exact skeleton tokens and traceable residual event tokens. Specifically, Contextual Farthest-Point Anchoring (CFPA) preserves salient, context-consistent, and high-coverage skeleton tokens, while Trajectory-Constrained Residual Condensation (TCRC) compresses residual tokens through one-to-one temporal trajectories and constrained near-manifold condensation, producing traceable event tokens with reduced ambiguity. We evaluate GeoTrace on four Video LLMs across four video understanding benchmarks, and the results demonstrate its effectiveness and generalization across different model architectures and scenarios. On LLaVA-OneVision, with only 10\% visual tokens retained, GeoTrace achieves a $12.99\times$ TFLOPs reduction while preserving 99.1\% of the vanilla performance. Overall, GeoTrace offers a compact and traceable token representation for efficient and robust Video LLM inference. Code is available at \href{https://github.com/guohuan-xie/GeoTrace.git}{\texttt{Code}}.

cs.CV↗

arXiv2026

M^2C-EvDet: Multi-Domain Multi-Order Cross-Modal Knowledge Distillation for Event-based Object Detection

Event-based object Detection (EvDet), as a biologically inspired visual perception paradigm, demonstrates superior performance in scenarios demanding high temporal resolution and a wide dynamic range. Nevertheless, the inherent sparse representations and inadequate visual semantics of event data result in a considerable performance disparity between EvDet and frame-based object detection. Previous works attempt to alleviate this cross-modal discrepancy through knowledge distillation, yet they only focus on spatial visual semantics or pair-wise relational information, thus limiting performance in more complex scenarios. To address this challenge, this paper proposes M^2C-EvDet, a Multi-domain and Multi-order Cross-modal knowledge distillation framework for EvDet. Built upon frequency learning and hypergraph computation, M^2C-EvDet integrates two specialized modules: Adaptive Frequency-Decoupled Feature Distillation (AF^2D^2) and Multi-Order Relational Distillation (MORD).

cs.CV↗

arXiv2026

Count Anything

Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing counting models are often tailored to scenarios such as crowds, vehicles, cells, crops, or remote-sensing objects, and thus struggle to generalize across categories, visual domains, object scales, and density distributions. In this paper, we study text-guided object counting across domains, where a model takes an image and a natural-language query as input and returns an instance-grounded set of target points whose cardinality gives the count. This formulation unifies category-conditioned counting with interpretable spatial localization. To support this setting, we construct CLOC, a Cross-domain Large-scale Object Counting dataset that reorganizes diverse public data sources into a unified benchmark. CLOC covers six visual domains: General Scene, Remote Sensing, Histopathology, Cellular Microscopy, Agriculture, and Microbiology, with about 220K images, 619 categories, and 15M object instances. Based on CLOC, we propose Count Anything, a generalist model for text-guided object counting. Unlike density-map-based methods, which dominate counting models, Count Anything adopts discrete instance points and performs dual-granularity instance enumeration. A Region-level Sparse Counter provides object-level anchors for large and sparse targets, while a Pixel-level Dense Counter handles small, crowded, and weakly bounded targets via dense point prediction. A point-centric supervision strategy enables learning from heterogeneous annotations, and Complementary Count Fusion combines both counters in a parameter-free manner. Extensive experiments show that Count Anything achieves strong accuracy and multi-domain generalization, outperforming existing open-world counting methods. Code is available at: https://github.com/Mengqi-Lei/count-anything.

cs.CV↗

arXiv2026

Rethinking Event-Based Object Detection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning

Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection (EOD) methods face limitations at both the representation and model levels: prior event representations usually encode temporal information indirectly through redundant structures, while detection models struggle to explicitly aggregate fragmented event responses into coherent high-order object features. To address these limitations, we present \textbf{Event Dual Temporal-Relational Aggregation Detector (Ev-DTAD)}, a unified EOD framework that integrates representation-level temporal encoding with model-level temporal-hypergraph reasoning. Specifically, we introduce \textbf{Hierarchical Temporal Aggregation (HTA)}, a compact three-channel pseudo-RGB representation that explicitly embeds temporal information across intra- and inter-window events. To further enhance detection under sparse and fragmented event responses, we propose \textbf{Frequency-aware Hypergraph Temporal Fusion (FHTF)}, which refines multi-scale event features through temporal evolution modeling and high-order relational reasoning. Extensive experiments on Gen1 (\textbf{+0.8 mAP}), 1Mpx/Gen4 (\textbf{+0.5 mAP}), and eTraM (\textbf{+3.0 mAP}) demonstrate that Ev-DTAD achieves a competitive accuracy--efficiency trade-off, validating the complementarity between compact temporal representation and temporal-hypergraph feature reasoning (Fig.~\ref{fig:bubble}). The code is available at: https://github.com/meisenwang/Ev-DTAD.

cs.CV↗

arXiv2026

RACANet: Reliability-Aware Crowd Anchor Network for RGB-T Crowd Counting

RGB-Thermal (T) crowd counting aims to integrate visible-spectrum and thermal infrared information to improve the robustness of crowd density estimation in complex scenes. Although existing studies generally improve counting accuracy through cross-modal feature fusion, most current methods rely on implicit cross-modal fusion strategies and lack explicit modeling of local spatial discrepancies as well as fine-grained characterization of modality reliability at the positional level, thereby limiting the accuracy and interpretability of the fusion process. To address these issues, this paper proposes a two-stage fusion framework, RACANet, a Reliability-Aware Crowd Anchor Network for RGB-T crowd counting. First, we introduce a lightweight cross-modal alignment pretraining stage, which explicitly learns cross-modal semantic correspondences through crowd-prior supervision and local bidirectional soft matching. Then, based on the priors learned during pretraining, a Local Anchor Fusion Module (LAFM) is introduced in the formal training stage. This module generates local semantic anchors by aggregating features from highly reliable regions and further enables adaptive pixel-level feature redistribution with a local attention mechanism. In addition, we propose a discrepancy-aware consistency constraint to dynamically coordinate the reliability of regions where modal representations are consistent. Experiments conducted on two widely used benchmark datasets, RGBT-CC and Drone-RGBT, demonstrate that RACANet outperforms existing methods. The anonymous code is available at https://anonymous.4open.science/r/RACANet-9985.

cs.CV↗

arXiv2026

Hyper-FEOD: Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoE

The integration of frame-based RGB cameras with event streams constitutes a promising paradigm for robust object detection under challenging dynamic conditions. Nevertheless, effectively modeling intricate multi-modal interactions and reconciling the semantic heterogeneity between RGB and event data remain formidable challenges for high-precision detection. In this paper, we present Hyper-FEOD, a novel high-performance detection framework that synergistically strengthens cross-modal representation learning through two core hypergraph-driven components. Specifically, we first design a Sparse Hypergraph-enhanced Cross-Modal Fusion (SHCF) module that exploits event activity cues to identify motion-critical sparse tokens and performs high-order relational reasoning through hypergraph modeling. This design effectively captures intricate high-order dependencies and rich contextual correlations across modalities. Second, we develop a Fine-Grained Mixture-of-Experts (FG-MoE) module tailored to handle the heterogeneous semantic demands arising from distinct visual regions. By deploying specialized hypergraph experts with varying hyperedge connectivity pattern and incorporating a spatial gating mechanism, FG-MoE adaptively routes features to enable precise enhancement at target regions. Coupled with an auxiliary router loss, the proposed framework ensures stable end-to-end training and optimal feature refinement. Comprehensive experiments conducted on widely-adopted RGB-Event benchmarks show that Hyper-FEOD delivers superior detection performance and consistently outperforms existing state-of-the-art approaches by a notable margin.

cs.CV↗

arXiv2025

FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

Short-form video moderation increasingly needs learning pipelines that protect user privacy without paying the full bandwidth and latency cost of cloud-centralized inference. We present FedVideoMAE, an on-device federated framework for video violence detection that combines self-supervised VideoMAE representations, LoRA-based parameter-efficient adaptation, client-side DP-SGD, and server-side secure aggregation. By updating only 5.5M parameters (about 3.5% of a 156M backbone), FedVideoMAE reduces communication by 28.3x relative to full-model federated updates while keeping raw videos on device throughout training. On RWF-2000 with 40 clients, the method reaches 77.25% accuracy without privacy protection and 65~66% under strong differential privacy. We further show that this privacy gap is consistent with an effective-SNR analysis tailored to the small-data, parameter-efficient federated regime, which indicates roughly 8.5~12x DP-noise amplification in our setting. To situate these results more clearly, we also compare against archived full-model federated baselines and summarize auxiliary transfer behavior on RLVS and binary UCF-Crime. Taken together, these findings position FedVideoMAE as a practical operating point for privacy-preserving video moderation on edge devices. Our code can be found at: https://github.com/zyt-599/FedVideoMAE.

cs.CV↗

arXiv2025

Orthorhombic nitride perovskite CeTaN3-δ with switchable and robust ferroelectric polarization

Perovskite-type ternary nitrides with predicted exciting ferroelectricity and many other outstanding properties hold great promise to be an emerging class of advanced ferroelectrics for manufacturing diverse technologically important devices. However, such nitride ferroelectrics have not yet been experimentally identified, mainly due to the challenging sample synthesis by traditional methods at ambient pressure. Here we report the successful high-pressure synthesis of a high-quality ferroelectric nitride perovskite of CeTaN3-δ with nitrogen deficiency, adopting an orthorhombic Pmn21 polar structure. This material is electrically insulating and exhibits switchable and robust electric polarization for producing ferroelectricity. Furthermore, a number of other extraordinary properties are also revealed in this nitride such as excellent mechanical properties and chemical inertness, which would make it practically useful for many device-relevant applications and fundamentally important for the study of condensed-matter physics.

cond-mat.mtrl-sci↗

arXiv2025

Design and construction of the multiplexing cold neutron spectrometer BOYA with double-column Rowland focusing analyzers

Developing neutron spectrometers with higher counting efficiency has been an essential pursuit in neutron instrumentation. In this work, we present BOYA, a multiplexing cold neutron spectrometers designed and implemented at the China Advanced Research Reactor. Equipped with 34 angular analyzing channels spanning 119°, each containing 5 inelastic channels and 1 diffraction channel, BOYA enhances the measurement efficiency by two orders of magnitude over a traditional triple-axis spectrometer. To optimize both intensity and energy resolution, innovative double-column Rowland focusing analyzers have been developed. By filling the crystal gaps in the traditional Rowland focusing geometry, our design enhances the neutron beam coverage without introducing appreciable double-scattering. Our commissioning results on vanadium and MnWO4 have confirmed the success of the design, establishing BOYA as a successful multiplexing instrument for neutron spectroscopy.

physics.ins-det↗

arXiv2025

Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory

The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concerns about their ability to accurately reflect authentic model capabilities. This paper provides a critical analysis of benchmark effectiveness, examining mainstream prominent LLM benchmarks using results from diverse models. We first propose Pseudo-Siamese Network for Item Response Theory (PSN-IRT), an enhanced Item Response Theory framework that incorporates a rich set of item parameters within an IRT-grounded architecture. PSN-IRT can be utilized for accurate and reliable estimations of item characteristics and model abilities. Based on PSN-IRT, we conduct extensive analysis on 11 LLM benchmarks comprising 41,871 items, revealing significant and varied shortcomings in their measurement quality. Furthermore, we demonstrate that leveraging PSN-IRT is able to construct smaller benchmarks while maintaining stronger alignment with human preference.

cs.CL↗

arXiv2024

Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization

Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data. Despite enhancing privacy and efficiency in information retrieval and knowledge management contexts, training and deploying FL models confront significant challenges such as communication bottlenecks, data heterogeneity, and memory limitations. To comprehensively address these challenges, we introduce FeDEQ, a novel FL framework that incorporates deep equilibrium learning and consensus optimization to harness compact global data representations for efficient personalization. Specifically, we design a unique model structure featuring an equilibrium layer for global representation extraction, followed by explicit layers tailored for local personalization. We then propose a novel FL algorithm rooted in the alternating directions method of multipliers (ADMM), which enables the joint optimization of a shared equilibrium layer and individual personalized layers across distributed datasets. Our theoretical analysis confirms that FeDEQ converges to a stationary point, achieving both compact global representations and optimal personalized parameters for each client. Extensive experiments on various benchmarks demonstrate that FeDEQ matches the performance of state-of-the-art personalized FL methods, while significantly reducing communication size by up to 4 times and memory footprint by 1.5 times during training.

cs.LG↗

arXiv2024

Bridging the Gap: Sketch-Aware Interpolation Network for High-Quality Animation Sketch Inbetweening

Hand-drawn 2D animation workflow is typically initiated with the creation of sketch keyframes. Subsequent manual inbetweens are crafted for smoothness, which is a labor-intensive process and the prospect of automatic animation sketch interpolation has become highly appealing. Yet, common frame interpolation methods are generally hindered by two key issues: 1) limited texture and colour details in sketches, and 2) exaggerated alterations between two sketch keyframes. To overcome these issues, we propose a novel deep learning method - Sketch-Aware Interpolation Network (SAIN). This approach incorporates multi-level guidance that formulates region-level correspondence, stroke-level correspondence and pixel-level dynamics. A multi-stream U-Transformer is then devised to characterize sketch inbetweening patterns using these multi-level guides through the integration of self / cross-attention mechanisms. Additionally, to facilitate future research on animation sketch inbetweening, we constructed a large-scale dataset - STD-12K, comprising 30 sketch animation series in diverse artistic styles. Comprehensive experiments on this dataset convincingly show that our proposed SAIN surpasses the state-of-the-art interpolation methods.

cs.CV↗

arXiv2024

Federated PCA on Grassmann Manifold for IoT Anomaly Detection

With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labeled data and challenges with high dimensionality. Recent unsupervised ML-IDS approaches such as AutoEncoders and Generative Adversarial Networks (GAN) offer alternative solutions but pose challenges in deployment onto resource-constrained IoT devices and in interpretability. To address these concerns, this paper proposes a novel federated unsupervised anomaly detection framework, FedPCA, that leverages Principal Component Analysis (PCA) and the Alternating Directions Method Multipliers (ADMM) to learn common representations of distributed non-i.i.d. datasets. Building on the FedPCA framework, we propose two algorithms, FEDPE in Euclidean space and FEDPG on Grassmann manifolds. Our approach enables real-time threat detection and mitigation at the device level, enhancing network resilience while ensuring privacy. Moreover, the proposed algorithms are accompanied by theoretical convergence rates even under a subsampling scheme, a novel result. Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to nonlinear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks.

cs.LG↗

arXiv2024

Search Intenion Network for Personalized Query Auto-Completion in E-Commerce

Query Auto-Completion(QAC), as an important part of the modern search engine, plays a key role in complementing user queries and helping them refine their search intentions.Today's QAC systems in real-world scenarios face two major challenges:1)intention equivocality(IE): during the user's typing process,the prefix often contains a combination of characters and subwords, which makes the current intention ambiguous and difficult to model.2)intention transfer (IT):previous works make personalized recommendations based on users' historical sequences, but ignore the search intention transfer.However, the current intention extracted from prefix may be contrary to the historical preferences.

cs.IR↗

arXiv2023

Honest Score Client Selection Scheme: Preventing Federated Learning Label Flipping Attacks in Non-IID Scenarios

Federated Learning (FL) is a promising technology that enables multiple actors to build a joint model without sharing their raw data. The distributed nature makes FL vulnerable to various poisoning attacks, including model poisoning attacks and data poisoning attacks. Today, many byzantine-resilient FL methods have been introduced to mitigate the model poisoning attack, while the effectiveness when defending against data poisoning attacks still remains unclear. In this paper, we focus on the most representative data poisoning attack - "label flipping attack" and monitor its effectiveness when attacking the existing FL methods. The results show that the existing FL methods perform similarly in Independent and identically distributed (IID) settings but fail to maintain the model robustness in Non-IID settings. To mitigate the weaknesses of existing FL methods in Non-IID scenarios, we introduce the Honest Score Client Selection (HSCS) scheme and the corresponding HSCSFL framework. In the HSCSFL, The server collects a clean dataset for evaluation. Under each iteration, the server collects the gradients from clients and then perform HSCS to select aggregation candidates. The server first evaluates the performance of each class of the global model and generates the corresponding risk vector to indicate which class could be potentially attacked. Similarly, the server evaluates the client's model and records the performance of each class as the accuracy vector. The dot product of each client's accuracy vector and global risk vector is generated as the client's host score; only the top p\% host score clients are included in the following aggregation. Finally, server aggregates the gradients and uses the outcome to update the global model. The comprehensive experimental results show our HSCSFL effectively enhances the FL robustness and defends against the "label flipping attack."

cs.CR↗

arXiv2023

Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Heads

With the rapid development of deep learning, object detection and tracking play a vital role in today's society. Being able to identify and track all the pedestrians in the dense crowd scene with computer vision approaches is a typical challenge in this field, also known as the Multiple Object Tracking (MOT) challenge. Modern trackers are required to operate on more and more complicated scenes. According to the MOT20 challenge result, the pedestrian is 4 times denser than the MOT17 challenge. Hence, improving the ability to detect and track in extremely crowded scenes is the aim of this work. In light of the occlusion issue with the human body, the heads are usually easier to identify. In this work, we have designed a joint head and body detector in an anchor-free style to boost the detection recall and precision performance of pedestrians in both small and medium sizes. Innovatively, our model does not require information on the statistical head-body ratio for common pedestrians detection for training. Instead, the proposed model learns the ratio dynamically. To verify the effectiveness of the proposed model, we evaluate the model with extensive experiments on different datasets, including MOT20, Crowdhuman, and HT21 datasets. As a result, our proposed method significantly improves both the recall and precision rate on small & medium sized pedestrians and achieves state-of-the-art results in these challenging datasets.

cs.CV↗

arXiv2023

Online Task Assignment with Controllable Processing Time

We study a new online assignment problem, called the Online Task Assignment with Controllable Processing Time. In a bipartite graph, a set of online vertices (tasks) should be assigned to a set of offline vertices (machines) under the known adversarial distribution (KAD) assumption. We are the first to study controllable processing time in this scenario: There are multiple processing levels for each task and higher level brings larger utility but also larger processing delay. A machine can reject an assignment at the cost of a rejection penalty, taken from a pre-determined rejection budget. Different processing levels cause different penalties. We propose the Online Machine and Level Assignment (OMLA) Algorithm to simultaneously assign an offline machine and a processing level to each online task. We prove that OMLA achieves $1/2$-competitive ratio if each machine has unlimited rejection budget and $Δ/(3Δ-1)$-competitive ratio if each machine has an initial rejection budget up to $Δ$. Interestingly, the competitive ratios do not change under different settings on the controllable processing time and we can conclude that OMLA is "insensitive" to the controllable processing time.

cs.DS↗

arXiv2023

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise. However, current Federated Semi-Supervised/Self-Supervised Learning (FSSL) approaches fail to learn large-scale images because of the limited computing resources of local clients. In this paper, we introduce a new framework FedMAE, which stands for Federated Masked AutoEncoder, to address the problem of how to utilize unlabeled large-scale images for FL. Specifically, FedMAE can pre-train one-block Masked AutoEncoder (MAE) using large images in lightweight client devices, and then cascades multiple pre-trained one-block MAEs in the server to build a multi-block ViT backbone for downstream tasks. Theoretical analysis and experimental results on image reconstruction and classification show that our FedMAE achieves superior performance compared to the state-of-the-art FSSL methods.

cs.LG↗