arXiv subjects

Qijun Zhao

Publications and source records attributed to Qijun Zhao.

At least 19 recordsLinked to original sources

arXiv2026

Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?

The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this gap primarily to mismatches between MLLMs and annotations over foreground cardinality, granularity, and extent. Motivated by this diagnosis, we recast zero-shot SOD as protocol-aligned Foreground Organization and introduce the first training-free framework that leverages Gestalt-inspired Collaborative attention for Unified SOD (FOCUS). FOCUS couples top-down Bayesian-surprise calibration of protocol-conditioned foreground granularity with bottom-up propagation of MLLMs evidence over entity-centric perceptual manifolds induced by self-supervised features, yielding coherent object extents as prompts for a general segmenter. Across 13 RGB, RGB-D, and RGB-T SOD benchmarks, FOCUS generally surpasses SOTA methods without training, reducing mean absolute error by 11\%, 34\%, and 48\% compared with fully, weakly, and self-supervised methods, respectively. Our findings signal the renaissance of SOD: from task-specific supervision to zero-shot foreground organization. Code is available in the supplementary material.

cs.CV↗

arXiv2026

RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detection

We introduce RDVSv2, a large-scale benchmark for RGB-D video salient object detection (RGB-D VSOD) with dense frame-level annotations. Existing datasets in this emerging field are often limited in scale and annotation quality, while also relying on less geometry-consistent depth cues. To address these limitations, RDVSv2 is built from publicly accessible stereoscopic online videos and contains 249 video sequences with 29,077 annotated frames. It includes depth maps derived from stereoscopic videos, together with frame-wise salient object masks annotated with eye-tracking guidance. Compared with existing datasets, RDVSv2 is much larger in scale and covers more diverse and challenging scenarios. In addition, we establish a strong baseline for RGB-D VSOD based on Segment Anything Model 2 (SAM2). Specifically, we employ a parameter-efficient fine-tuning (PEFT) strategy to adapt the SAM2 encoder to jointly encode RGB, depth, and optical flow cues. Extensive experiments show that RDVSv2 is substantially more challenging for existing RGB-D VSOD methods. Meanwhile, the proposed baseline achieves state-of-the-art results on RDVSv2 and existing RGB-D VSOD benchmarks. We hope that RDVSv2 and the provided baseline will serve as useful resources for future research on RGB-D VSOD and related multi-modal video understanding tasks. Our dataset and code will be available at https://github.com/ltynick/RDVSv2.

cs.CV↗

arXiv2026

Attend to Anything: Foundation Model for Unified Human Attention Modeling

Existing human attention (saliency) modeling methods persist as highly fragmented across modalities, scenes, and task formulations. Consequently, even with increasing model capacity and data scale, current models predominantly remain scene-dependent and task-specific, failing to practically generalize in real-world applications. To address the fundamental limitations, we present the Attend to Anything Model (AAM), a multi-modal foundation model that unifies attention modeling across various image, video, and audio-visual tasks and scenes. AAM reformulates attention as a cognitive entailment relationship organized in a general-to-specific hierarchy, implemented through language prompts with hierarchical embeddings in hyperbolic space. Furthermore, to unify static image and dynamic video attention, we adopt a fluid-dynamics perspective, formulating video-frame attention as a diffusive temporal evolution governed by the Fokker--Planck equation. Extensive experiments on 16 benchmarks demonstrate that AAM consistently outperforms state-of-the-art methods by an average of 6\% across various scenarios, while achieving approximately a 4$\times$ speedup in video inference. Overall, these results demonstrate that AAM provides a principled foundation for future research on attention and saliency-related tasks. The dataset and code will be available at https://github.com/wz-zhao/Attend-to-Anything.

cs.CV↗

arXiv2026

Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction

Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states that violate governing dynamics. We introduce a physics-informed generative solver that separates stable prior learning from inference-time enforcement of conservation laws. Martingale-Regularized Score Matching regularizes score pretraining with a Score Fokker-Planck constraint, yielding a dynamically stable prior. Physics-Informed Implicit Score Sampling then guides denoising trajectories by gradients of physical residuals, projecting samples toward admissible manifolds without retraining. In acoustics, the method co-generates pressure and particle velocity from sparse sensors, enabling dense virtual arrays that suppress spatial aliasing. The same framework generalizes to real-world ERA5 meteorological fields under extreme sparsity. Together, this work establishes a rigorous and generalizable paradigm for solving high-dimensional inverse problems, bridging the gap between generative artificial intelligence and first-principles science.

cs.LG↗

arXiv2026

$\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding

Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on dense spatiotemporal attention suffer from quadratic computational costs for long videos. To circumvent these costs, recent approaches adapt image models for videos via Parameter-Efficient Fine-Tuning (PEFT) methods such as adapters. However, deeply inserting these modules incurs prohibitive activation memory overhead during back-propagation. While recent efficient State Space Models (SSMs) introduce linear complexity, they disrupt 2D spatial relationships and rely on extensive masked pre-training to recover spatial awareness. To overcome these limitations, we propose Parallel Kinematic Selective State Space Scanners (PKS$^4$). We retain a standard 2D vision backbone for spatial semantics and insert a single plug-and-play PKS$^4$ module with linear-complexity temporal scanning, avoiding temporal attention and multi-layer adapters. We first extract kinematic priors via a Kinematic Prior Encoder, which captures local displacements and motion boundaries through inter-frame correlations and differences. These priors drive linear-complexity SSMs to track underlying kinematic states, adaptively modulating update speeds and read-write strategies at each time step. Instead of global scanning, we deploy parallel scanners along the temporal dimension for each spatial location, preserving spatial structures while reducing overhead. Experiments on spatial-heavy and temporal-heavy action recognition benchmarks show that PKS$^4$ achieves state-of-the-art performance. Remarkably, our method converges in merely $20$ epochs, achieving approximately $10\times$ lower training compute than pure video SSMs, establishing a new paradigm for efficient video understanding.

cs.CV↗

arXiv2026

Camouflage-aware Image-Text Retrieval via Expert Collaboration

Camouflaged scene understanding (CSU) has attracted significant attention due to its broad practical implications. However, in this field, robust image-text cross-modal alignment remains under-explored, hindering deeper understanding of camouflaged scenarios and their related applications. To this end, we focus on the typical image-text retrieval task, and formulate a new task dubbed ``camouflage-aware image-text retrieval'' (CA-ITR). We first construct a dedicated camouflage image-text retrieval dataset (CamoIT), comprising $\sim$10.5K samples with multi-granularity textual annotations. Benchmark results conducted on CamoIT reveal the underlying challenges of CA-ITR for existing cutting-edge retrieval techniques, which are mainly caused by objects' camouflage properties as well as those complex image contents. As a solution, we propose a camouflage-expert collaborative network (CECNet), which features a dual-branch visual encoder: one branch captures holistic image representations, while the other incorporates a dedicated model to inject representations of camouflaged objects. A novel confidence-conditioned graph attention (C\textsuperscript{2}GA) mechanism is incorporated to exploit the complementarity across branches. Comparative experiments show that CECNet achieves $\sim$29% overall CA-ITR accuracy boost, surpassing seven representative retrieval models. The dataset and code will be available at https://github.com/jiangyao-scu/CA-ITR.

cs.CV↗

arXiv2026

Dehallu3D: Hallucination-Mitigated 3D Generation from Single Image via Cyclic View Consistency Refinement

Large 3D reconstruction models have revolutionized the 3D content generation field, enabling broad applications in virtual reality and gaming. Just like other large models, large 3D reconstruction models suffer from hallucinations as well, introducing structural outliers (e.g., odd holes or protrusions) that deviate from the input data. However, unlike other large models, hallucinations in large 3D reconstruction models remain severely underexplored, leading to malformed 3D-printed objects or insufficient immersion in virtual scenes. Such hallucinations majorly originate from that existing methods reconstruct 3D content from sparsely generated multi-view images which suffer from large viewpoint gaps and discontinuities. To mitigate hallucinations by eliminating the outliers, we propose Dehallu3D for 3D mesh generation. Our key idea is to design a balanced multi-view continuity constraint to enforce smooth transitions across dense intermediate viewpoints, while avoiding over-smoothing that could erase sharp geometric features. Therefore, Dehallu3D employs a plug-and-play optimization module with two key constraints: (i) adjacent consistency to ensure geometric continuity across views, and (ii) adaptive smoothness to retain fine details.We further propose the Outlier Risk Measure (ORM) metric to quantify geometric fidelity in 3D generation from the perspective of outliers. Extensive experiments show that Dehallu3D achieves high-fidelity 3D generation by effectively preserving structural details while removing hallucinated outliers.

cs.CV↗

arXiv2026

Samba+: General and Accurate Salient Object Detection via A More Unified Mamba-based Framework

Existing salient object detection (SOD) models are generally constrained by the limited receptive fields of convolutional neural networks (CNNs) and quadratic computational complexity of Transformers. Recently, the emerging state-space model, namely Mamba, has shown great potential in balancing global receptive fields and computational efficiency. As a solution, we propose Saliency Mamba (Samba), a pure Mamba-based architecture that flexibly handles various distinct SOD tasks, including RGB/RGB-D/RGB-T SOD, video SOD (VSOD), RGB-D VSOD, and visible-depth-thermal SOD. Specifically, we rethink the scanning strategy of Mamba for SOD, and introduce a saliency-guided Mamba block (SGMB) that features a spatial neighborhood scanning (SNS) algorithm to preserve the spatial continuity of salient regions. A context-aware upsampling (CAU) method is also proposed to promote hierarchical feature alignment and aggregation by modeling contextual dependencies. As one step further, to avoid the "task-specific" problem as in previous SOD solutions, we develop Samba+, which is empowered by training Samba in a multi-task joint manner, leading to a more unified and versatile model. Two crucial components that collaboratively tackle challenges encountered in input of arbitrary modalities and continual adaptation are investigated. Specifically, a hub-and-spoke graph attention (HGA) module facilitates adaptive cross-modal interactive fusion, and a modality-anchored continual learning (MACL) strategy alleviates inter-modal conflicts together with catastrophic forgetting. Extensive experiments demonstrate that Samba individually outperforms existing methods across six SOD tasks on 22 datasets with lower computational cost, whereas Samba+ achieves even superior results on these tasks and datasets by using a single trained versatile model. Additional results further demonstrate the potential of our Samba framework.

cs.CV↗

arXiv2025

Angle-Optimized Partial Disentanglement for Multimodal Emotion Recognition in Conversation

Multimodal Emotion Recognition in Conversation (MERC) aims to enhance emotion understanding by integrating complementary cues from text, audio, and visual modalities. Existing MERC approaches predominantly focus on cross-modal shared features, often overlooking modality-specific features that capture subtle yet critical emotional cues such as micro-expressions, prosodic variations, and sarcasm. Although related work in multimodal emotion recognition (MER) has explored disentangling shared and modality-specific features, these methods typically employ rigid orthogonal constraints to achieve full disentanglement, which neglects the inherent complementarity between feature types and may limit recognition performance. To address these challenges, we propose Angle-Optimized Feature Learning (AO-FL), a framework tailored for MERC that achieves partial disentanglement of shared and specific features within each modality through adaptive angular optimization. Specifically, AO-FL aligns shared features across modalities to ensure semantic consistency, and within each modality it adaptively models the angular relationship between its shared and modality-specific features to preserve both distinctiveness and complementarity. An orthogonal projection refinement further removes redundancy in specific features and enriches shared features with contextual information, yielding more discriminative multimodal representations. Extensive experiments confirm the effectiveness of AO-FL for MERC, demonstrating superior performance over state-of-the-art approaches. Moreover, AO-FL can be seamlessly integrated with various unimodal feature extractors and extended to other multimodal fusion tasks, such as MER, thereby highlighting its strong generalization beyond MERC.

cs.MM↗

arXiv2025

Orthogonal Disentanglement with Projected Feature Alignment for Multimodal Emotion Recognition in Conversation

Multimodal Emotion Recognition in Conversation (MERC) significantly enhances emotion recognition performance by integrating complementary emotional cues from text, audio, and visual modalities. While existing methods commonly utilize techniques such as contrastive learning and cross-attention mechanisms to align cross-modal emotional semantics, they typically overlook modality-specific emotional nuances like micro-expressions, tone variations, and sarcastic language. To overcome these limitations, we propose Orthogonal Disentanglement with Projected Feature Alignment (OD-PFA), a novel framework designed explicitly to capture both shared semantics and modality-specific emotional cues. Our approach first decouples unimodal features into shared and modality-specific components. An orthogonal disentanglement strategy (OD) enforces effective separation between these components, aided by a reconstruction loss to maintain critical emotional information from each modality. Additionally, a projected feature alignment strategy (PFA) maps shared features across modalities into a common latent space and applies a cross-modal consistency alignment loss to enhance semantic coherence. Extensive evaluations on widely-used benchmark datasets, IEMOCAP and MELD, demonstrate effectiveness of our proposed OD-PFA multimodal emotion recognition tasks, as compared with the state-of-the-art approaches.

cs.MM↗

arXiv2025

CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimation

Recent research in Category-Agnostic Pose Estimation (CAPE) has adopted fixed textual keypoint description as semantic prior for two-stage pose matching frameworks. While this paradigm enhances robustness and flexibility by disentangling the dependency of support images, our critical analysis reveals two inherent limitations of static joint embedding: (1) polysemy-induced cross-category ambiguity during the matching process(e.g., the concept "leg" exhibiting divergent visual manifestations across humans and furniture), and (2) insufficient discriminability for fine-grained intra-category variations (e.g., posture and fur discrepancies between a sleeping white cat and a standing black cat). To overcome these challenges, we propose a new framework that innovatively integrates hierarchical cross-modal interaction with dual-stream feature refinement, enhancing the joint embedding with both class-level and instance-specific cues from textual description and specific images. Experiments on the MP-100 dataset demonstrate that, regardless of the network backbone, CapeNext consistently outperforms state-of-the-art CAPE methods by a large margin.

cs.CV↗

arXiv2025

Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation

Generating artistic and coherent 3D scene layouts is crucial in digital content creation. Traditional optimization-based methods are often constrained by cumbersome manual rules, while deep generative models face challenges in producing content with richness and diversity. Furthermore, approaches that utilize large language models frequently lack robustness and fail to accurately capture complex spatial relationships. To address these challenges, this paper presents a novel vision-guided 3D layout generation system. We first construct a high-quality asset library containing 2,037 scene assets and 147 3D scene layouts. Subsequently, we employ an image generation model to expand prompt representations into images, fine-tuning it to align with our asset library. We then develop a robust image parsing module to recover the 3D layout of scenes based on visual semantics and geometric information. Finally, we optimize the scene layout using scene graphs and overall visual semantics to ensure logical coherence and alignment with the images. Extensive user testing demonstrates that our algorithm significantly outperforms existing methods in terms of layout richness and quality. The code and dataset will be available at https://github.com/HiHiAllen/Imaginarium.

cs.CV↗

arXiv2025

Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object Detection

Existing video camouflaged object detection (VCOD) methods primarily rely on spatial appearances for motion perception. However, the high foreground-background similarity in VCOD limits the discriminability of such features (e.g. color and texture). Recent studies demonstrate that frequency features can not only compensate for appearance limitations, but also perceive motion through dynamic variations in spectral energy. Meanwhile, the emerging state space model called Mamba enables efficient motion perception in frame sequences with its linear-time long-sequence modeling capability. Motivated by this, we propose Vcamba, a visual camouflage Mamba based on spatio-frequency motion perception that integrates frequency and spatial features for efficient and accurate VCOD. Specifically, by analyzing the spatial representations of frequency components, we reveal a structural evolution pattern that emerges from the ordered superposition of components. Based on this observation, we propose a unique frequency-domain sequential scanning (FSS) strategy to unfold the spectrum. Utilizing FSS, the adaptive frequency enhancement (AFE) module employs Mamba to model the causal dependencies within sequences, enabling effective frequency learning. Furthermore, we propose a space-based long-range motion perception (SLMP) module and a frequency-based long-range motion perception (FLMP) module to model spatio-temporal and frequency-temporal sequences. Finally, the space and frequency motion fusion module (SFMF) integrates dual-domain features into unified motion representation. Experiments show that Vcamba outperforms state-of-the-art methods across 6 evaluation metrics on 2 datasets with lower computation cost, confirming its superiority. Code is available at: https://github.com/BoydeLi/Vcamba.

cs.CV↗

arXiv2025

Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detection

Applying salient object detection (SOD) to RGB-D videos is an emerging task called RGB-D VSOD and has recently gained increasing interest, due to considerable performance gains of incorporating motion and depth and that RGB-D videos can be easily captured now in daily life. Existing RGB-D VSOD models have different attempts to derive motion cues, in which extracting motion information explicitly from optical flow appears to be a more effective and promising alternative. Despite this, there remains a key issue that how to effectively utilize optical flow and depth to assist the RGB modality in SOD. Previous methods always treat optical flow and depth equally with respect to model designs, without explicitly considering their unequal contributions in individual scenarios, limiting the potential of motion and depth. To address this issue and unleash the power of motion and depth, we propose a novel selective cross-modal fusion framework (SMFNet) for RGB-D VSOD, incorporating a pixel-level selective fusion strategy (PSF) that achieves optimal fusion of optical flow and depth based on their actual contributions. Besides, we propose a multi-dimensional selective attention module (MSAM) to integrate the fused features derived from PSF with the remaining RGB modality at multiple dimensions, effectively enhancing feature representation to generate refined features. We conduct comprehensive evaluation of SMFNet against 19 state-of-the-art models on both RDVS and DVisal datasets, making the evaluation the most comprehensive RGB-D VSOD benchmark up to date, and it also demonstrates the superiority of SMFNet over other models. Meanwhile, evaluation on five video benchmark datasets incorporating synthetic depth validates the efficacy of SMFNet as well. Our code and benchmark results are made publicly available at https://github.com/Jia-hao999/SMFNet.

cs.CV↗

arXiv2025

Vision-Based Anti Unmanned Aerial Technology: Opportunities and Challenges

With the rapid advancement of UAV technology and its extensive application in various fields such as military reconnaissance, environmental monitoring, and logistics, achieving efficient and accurate Anti-UAV tracking has become essential. The importance of Anti-UAV tracking is increasingly prominent, especially in scenarios such as public safety, border patrol, search and rescue, and agricultural monitoring, where operations in complex environments can provide enhanced security. Current mainstream Anti-UAV tracking technologies are primarily centered around computer vision techniques, particularly those that integrate multi-sensor data fusion with advanced detection and tracking algorithms. This paper first reviews the characteristics and current challenges of Anti-UAV detection and tracking technologies. Next, it investigates and compiles several publicly available datasets, providing accessible links to support researchers in efficiently addressing related challenges. Furthermore, the paper analyzes the major vision-based and vision-fusion-based Anti-UAV detection and tracking algorithms proposed in recent years. Finally, based on the above research, this paper outlines future research directions, aiming to provide valuable insights for advancing the field.

cs.CV↗

arXiv2025

Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection

Camouflage poses challenges in distinguishing a static target, whereas any movement of the target can break this disguise. Existing video camouflaged object detection (VCOD) approaches take noisy motion estimation as input or model motion implicitly, restricting detection performance in complex dynamic scenes. In this paper, we propose a novel Explicit Motion handling and Interactive Prompting framework for VCOD, dubbed EMIP, which handles motion cues explicitly using a frozen pre-trained optical flow fundamental model. EMIP is characterized by a two-stream architecture for simultaneously conducting camouflaged segmentation and optical flow estimation. Interactions across the dual streams are realized in an interactive prompting way that is inspired by emerging visual prompt learning. Two learnable modules, i.e., the camouflaged feeder and motion collector, are designed to incorporate segmentation-to-motion and motion-to-segmentation prompts, respectively, and enhance outputs of the both streams. The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner. Furthermore, we show that long-term historical information can also be incorporated as a prompt into EMIP and achieve more robust results with temporal consistency. Experimental results demonstrate that our EMIP achieves new state-of-the-art records on popular VCOD benchmarks. Our code is made publicly available at https://github.com/zhangxin06/EMIP.

cs.CV↗

arXiv2025

QEMesh: Employing A Quadric Error Metrics-Based Representation for Mesh Generation

Mesh generation plays a crucial role in 3D content creation, as mesh is widely used in various industrial applications. Recent works have achieved impressive results but still face several issues, such as unrealistic patterns or pits on surfaces, thin parts missing, and incomplete structures. Most of these problems stem from the choice of shape representation or the capabilities of the generative network. To alleviate these, we extend PoNQ, a Quadric Error Metrics (QEM)-based representation, and propose a novel model, QEMesh, for high-quality mesh generation. PoNQ divides the shape surface into tiny patches, each represented by a point with its normal and QEM matrix, which preserves fine local geometry information. In our QEMesh, we regard these elements as generable parameters and design a unique latent diffusion model containing a novel multi-decoder VAE for PoNQ parameters generation. Given the latent code generated by the diffusion model, three parameter decoders produce several PoNQ parameters within each voxel cell, and an occupancy decoder predicts which voxel cells containing parameters to form the final shape. Extensive evaluations demonstrate that our method generates results with watertight surfaces and is comparable to state-of-the-art methods in several main metrics.

cs.CV↗

arXiv2025

CamoSAM2: SAM2-oriented Prompt Auto-Refinement for Video Camouflaged Object Detection

The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camouflaged objects and their surroundings, which makes them difficult to distinguish even by the human eye, the application of SAM2 for automated segmentation in real-world scenarios faces challenges in camouflage perception and reliable prompts generation. To address these issues, we propose CamoSAM2, a motion-appearance prompt inducer (MAPI) and refinement framework to automatically generate and refine prompts for SAM2, enabling high-quality automatic detection and segmentation in VCOD task. Initially, we introduce a prompt inducer that simultaneously integrates motion and appearance cues to detect camouflaged objects, delivering more accurate initial predictions than existing methods. Subsequently, we propose a video-based adaptive multi-prompts refinement (AMPR) strategy tailored for SAM2, aimed at mitigating prompt error in initial coarse masks and further producing good prompts. Specifically, we introduce a novel three-step process to generate reliable prompts by camouflaged object determination, pivotal prompt frame selection, and multi-prompts formation. Extensive experiments conducted on two benchmark datasets demonstrate that our proposed model, CamoSAM2, significantly outperforms existing state-of-the-art methods, achieving increases of 8.0% and 10.1% in mIoU metric. Additionally, our method achieves the fastest inference speed compared to current VCOD models.

cs.CV↗