WACV 2026 论文列表

Multimodal emotion recognition (MER) aims to identify human emotions from inputs such as text, vision, and audio. However, existing methods often assume complete modality availability during training and inference, which is unrealistic in real-world scenarios due to sensor failures or privacy constraints.We propose Dual-Query Fusion (DQF), a framework that enables robust MER using only incomplete modality inputs, without relying on reconstruction or knowledge distillation.DQF introduces two types of learnable queries: Q-UA for extracting informative unimodal features, and Q-CA for adaptive cross-modal integration. These modules are designed to operate effectively even when some modalities are missing.Experiments on two public datasets demonstrate that DQF achieves superior performance and robustness compared to existing methods, even when trained exclusively on incomplete inputs. These results highlight the effectiveness and practicality of DQF for real-world MER tasks.

Image editing using generative models has recently advanced through GAN- and diffusion-based techniques. While the current image manipulation methods shows considerable performance in general image editing, their effectiveness drops when extended to fashion attribute editing. This is due to multiple challenges such as category-specific and overlapping attributes, inherent entanglement in real-world datasets that leads to degraded editing quality and unintended attribute shifts. To address these challenges, we propose FAE-Net (Fashion Attribute Editing Network), a latent diffusion framework that leverages disentangled latent projections for precise and reliable attribute manipulation. Our method first disentangles the latent projections to mitigate the inherent entanglement in the data and then conditions the diffusion model with those projections to improve the manipulation control in the presence of overlapping attributes. The attribute presence detector in FAE-Net handles category-specific attributes and prevents invalid attribute manipulations during inference. Extensive experiments on three large-scale datasets demonstrate that our proposed method achieves more controllable, disentangled, and faithful attribute editing compared to state-of-the-art methods.

Out-of-Distribution (OOD) detection is of paramountimportance in guaranteeing safe and reliable deploymentof a Deep Neural Network (DNN) model in real-world set-tings. However, most OOD detection approaches still lackmotivation rooted in established properties of the DNNs.This disconnect between the proposed approach and theo-retical underpinning to measurable DNN properties makesthese approaches unreliable. To bridge this gap, we takea different perspective to using energy scoring for OODdetection. Specifically, we look at energy score throughthe lens of the properties of neural collapse and observethat simple feature scaling can improve the separation be-tween In-Distribution (ID) and OOD inputs. Based on thisobservation, we propose ENCORE , which scales featuresof each input adaptively and uses them to obtain modi-fied logits based on insights from theory of neural collapse.We show that ENCORE outperforms state-of-the-art ap-proaches across a variety of benchmarks; for example, by1.37% on CIFAR10 and by 1.07% on Imagenet benchmarks.

Class-agnostic counting (CAC) aims to estimate the number of objects in images without being restricted to predefined categories. However, while current exemplar-based CAC methods offer flexibility at inference time, they still heavily rely on labeled data for training, which limits scalability and generalization to many downstream use cases. In this paper, we introduce CountingDINO, the first training-free exemplar-based CAC framework that exploits a fully unsupervised feature extractor. Specifically, our approach employs self-supervised vision-only backbones to extract object-aware features, and it eliminates the need for annotated data throughout the entire proposed pipeline. At inference time, we extract latent object prototypes via ROI-Align from DINO features and use them as convolutional kernels to generate similarity maps. These are then transformed into density maps through a simple yet effective normalization scheme. We evaluate our approach on the FSC-147 and CARPK benchmarks, where we consistently outperform a baseline based on an SOTA unsupervised object detector under the same label- and training-free setting. Additionally, we achieve competitive results -- and in some cases surpass -- training-free methods that rely on supervised backbones, non-training-free unsupervised methods, as well as several fully supervised SOTA approaches. This demonstrates that label- and training-free CAC can be both scalable and effective. Website: https://lorebianchi98.github.io/CountingDINO/.

Gaze estimation remains a fundamental yet challenging task, requiring a careful balance between accuracy and efficiency for real-world deployment. We introduce LightGazeNet, a lightweight Graph Neural Network (GNN) framework designed for appearance-based gaze estimation. LightGazeNet effectively integrates multi-modal inputs--including facial features, eye cues, 3D eye centers, head pose, and calibration data--within a compact graph-based architecture. To enhance feature fusion across heterogeneous inputs, the framework leverages multi-head attention to model complex spatial dependencies. Extensive evaluations on multiple benchmark datasets show that LightGazeNet achieves competitive or superior accuracy with significantly fewer parameters than existing methods. Furthermore, it demonstrates strong cross-dataset generalization, with calibration-based adaptation improving robustness under domain shift. By combining accuracy, efficiency, and adaptability, LightGazeNet offers a practical solution for gaze estimation in real-world settings while advancing graph-based modeling in computer vision.

Federated learning (FL) enables collaborative model training across distributed clients while preserving privacy, yet its decentralized nature makes it vulnerable to poisoned updates and performance degradation under highly skewed data. Prior studies typically treat accuracy, robustness, and fairness separately, leaving open the challenge of a unified solution. We propose AFL-PRF, an adaptive federated learning framework that simultaneously enhances accuracy, robustness, and fairness in adversarial and heterogeneous environments. AFL-PRF integrates three key techniques. First, an exponential adaptive weighting mechanism dynamically scales client updates, suppressing poisoned or unreliable contributions while retaining meaningful signals from benign but low-quality clients. Second, a client prioritization strategy guided by the novel Weight Update Divergence (WUD) score promotes reliable updates and their benign neighbors, preventing malicious gradients from dominating aggregation. Third, sensitivity profiling identifies fully connected (FC) layers as highly vulnerable due to large weight variance, motivating a selective clipping strategy that filters extreme updates in these layers while preserving normal learning dynamics. Extensive experiments on benchmark datasets demonstrate that AFL-PRF consistently outperforms state-of-the-art baselines, achieving over 30% improvement in robustness and 20% enhancement in fairness, while maintaining superior predictive accuracy. By unifying adaptive weighting, client prioritization, and targeted clipping, AFL-PRF establishes a new benchmark for federated learning under poisoned and highly non-IID conditions.

In electronics manufacturing, anomaly detection methods face significant challenges due to class distribution imbalance and training instability when handling multiple classes simultaneously under varying imaging conditions. To address these challenges, we propose Reverse Distillation with Core-Exemplar Learning (RDCEL), a unified anomaly detection framework incorporating domain adaptation and novel metric learning strategies. RDCEL integrates unsupervised domain adaptation to align the covariance of the source and target domains and uses soft label-based coreset learning to handle diverse class distributions. It also leverages a coreset repulsion loss to minimize redundancy among coreset representations, fostering a more stable and dispersed embedding space across multiple classes. By aligning spatial statistics across different classes, RDCEL effectively addresses inter-class discrepancies, enabling consistent anomaly scoring under a unified test setting. Extensive experiments show RDCEL significantly outperforms state-of-the-art methods on MVTec AD and VisA datasets, achieving superior accuracy, stable AUROC performance, and faster convergence.

Classical self-calibration techniques either perform computationally expensive bundle adjustment to estimate all camera parameters or initialize the focal lengths alone by globally averaging fundamental matrices, typically ignoring radial distortion. Both strategies can degrade accuracy in large-scale Structure from Motion pipelines.We present a calibration method that overcomes these limitations by averaging focal lengths and radial distortion parameters using radial fundamental matrices. This method avoids costly point-wise optimization. Our algorithm minimizes the geometric distance between an observed fundamental matrix and the essential-matrix manifold. This provides a mathematically consistent and highly scalable framework for calibrating the camera's intrinsic parameters.Experiments on diverse real-world datasets demonstrate that our joint estimator provides more precise focal length and distortion parameter estimates than existing methods. Furthermore, we demonstrate that naive, independent distortion averaging is suboptimal, which reinforces the importance of joint focal-radial estimation. These results underscore the importance of incorporating radial distortion averaging into modern self-calibration methods to improve reconstruction accuracy and stability.

Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments. Consequently, users should retrain models or develop separate AI models for new environments, which requires expertise in machine learning, high-performance hardware, and extensive data collection, limiting the practical usability of VAD. To address these challenges, this study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model. C-VAD considers user-defined text as an abnormal event and detects frames containing a specified event in a video. We effectively implemented AnyAnomaly using a context-aware visual question answering without fine-tuning the large vision language model. To validate the effectiveness of the proposed model, we constructed C-VAD datasets and demonstrated the superiority of AnyAnomaly. Furthermore, our approach showed competitive results on VAD benchmarks, achieving state-of-the-art performance on UBnormal and UCF-Crime and surpassing other methods in generalization across all datasets.

We introduce a unified, end-to-end framework that seamlessly integrates object detection and pose estimation with a versatile onboarding process. Our pipeline begins with an onboarding stage that generates object representations from either traditional 3D CAD models or, in their absence, by rapidly reconstructing a high-fidelity neural representation (NeRF) from multi-view images. Given a test image, our system first employs the CNOS detector to localize target objects. For each detection, our novel pose estimation module, OPFormer, infers the precise 6D pose. The core of OPFormer is a transformer-based architecture that leverages a foundation model for robust feature extraction. It uniquely learns a comprehensive object representation by jointly encoding multiple template views and enriches these features with explicit 3D geometric priors using Normalized Object Coordinate Space (NOCS). A decoder then establishes robust 2D-3D correspondences to determine the final pose. Evaluated on the challenging BOP benchmarks, our integrated system demonstrates a strong balance between accuracy and efficiency, showcasing its practical applicability in both model-based and model-free scenarios.

Unsupervised anomaly detection aims to identify anomalies without pixel-level annotations. Synthetic anomaly-based methods exhibit a unique capacity to introduce controllable irregularities with known masks, enabling explicit supervision during training. However, existing methods often produce synthetic anomalies that are visually distinct from real pathological patterns and ignore anatomical structure. This paper presents a novel Anatomy-aware Realistic Texture-based Anomaly Synthesis framework (ART-ASyn) for chest X-rays that generates realistic and anatomically consistent lung opacity related anomalies using texture-based augmentation guided by our proposed Progressive Binary Thresholding Segmentation method (PBTSeg) for lung segmentation. The generated paired samples of synthetic anomalies and their corresponding precise pixel-level anomaly mask for each normal sample enable explicit segmentation supervision. In contrast to prior work limited to one-class classification, ART-ASyn is further evaluated for zero-shot anomaly segmentation, demonstrating generalizability on an unseen dataset without target-domain annotations. Code availability is available at https://github.com/angelacao-hub/ART-ASyn.

Semi-Supervised Federated Learning (SSFL) is gaining popularity over conventional Federated Learning in many real-world applications. Due to the practical limitation of limited labeled data on the client side, SSFL considers that participating clients train with unlabeled data, and only the central server has the necessary resources to access limited labeled data, making it an ideal fit for real-world applications (e.g., healthcare). However, traditional SSFL assumes that the data distributions in the training phase and testing phase are the same. In practice, however, domain shifts frequently occur, making it essential for SSFL to incorporate generalization capabilities and enhance their practicality. The core challenge is improving model generalization to new, unseen domains while the client participate in SSFL. However, the decentralized setup of SSFL and unsupervised client training necessitates innovation to achieve improved generalization across domains. To achieve this, we propose a novel framework called the Unified Alignment Protocol (UAP), which consists of an alternating two-stage training process. The first stage involves training the server model to learn and align the features with a parametric distribution, which is subsequently communicated to clients without additional communication overhead. The second stage proposes a novel training algorithm that utilizes the server feature distribution to align client features accordingly. Our extensive experiments on standard domain generalization benchmark datasets across multiple model architectures reveal that proposed UAP successfully achieves SOTA generalization performance in SSFL setting.

Generalizing image classification across domains remains challenging in critical tasks such as fundus image-based diabetic retinopathy (DR) grading and resting-state fMRI seizure onset zone (SOZ) detection. When domains differ in unknown causal factors, achieving cross-domain generalization is difficult, and there is no established methodology to objectively assess such differences without direct metadata or protocol-level information from data collectors, which is typically inaccessible. We first introduce domain conformal bounds (DCB), a theoretical framework to evaluate whether domains diverge in unknown causal factors. Building on this, we propose GenEval, a multimodal Vision Language Models (VLM) approach that combines foundational models (e.g., MedGemma-4B) with human knowledge via Low-Rank Adaptation (LoRA) to bridge causal gaps and enhance single-source domain generalization (SDG). Across eight DR and two SOZ datasets, GenEval achieves superior SDG performance, with average accuracy of 69.2% (DR) and 81% (SOZ), outperforming the strongest baselines by 9.4% and 1.8%, respectively.

Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally identical teacher and student networks, relying on Exponential Moving Average (EMA) updates. However, these approaches face substantial performance degradation with lightweight models due to inherent architectural inflexibility leading to low-quality pseudo-labels. To address this, we propose Distilled Unsupervised Domain Adaptation (DUDA), a novel framework that combines EMA-based self-training with knowledge distillation (KD). Our method employs an auxiliary student network to bridge the architectural gap between heavyweight and lightweight models for EMA-based updates, resulting in improved pseudo-label quality. DUDA employs a strategic fusion of UDA and KD, incorporating innovative elements such as gradual distillation from large to small networks, inconsistency loss prioritizing poorly adapted classes, and learning with multiple teachers. Extensive experiments across four UDA benchmarks demonstrate DUDA's superiority in achieving SOTA performance with lightweight models, often surpassing the performance of heavyweight models from other approaches.

Video question answering is a non-trivial task that demands joint understanding of visual contents and linguistic questions as well as temporal reasoning across video frames. Recent agent-based approaches address this by conducting multi-step reasoning with large language models (LLMs) across frame-level captions generated by vision-language models, but encounter limited temporal coherence across frames. A possible direction based on video language models (VideoLMs) directly captures temporal dynamics via video-level descriptions, but often lacks fine-grained visual cues due to a restricted number of input frames and a large dependency on input prompts. To tackle these challenges, we propose RefineVQA, a training-free framework that can easily be plugged into existing VideoLMs with iterative, LLM-guided description refinements. Specifically, the VideoLM produces an initial description, followed by LLM feedback determining whether the description suffices for the question and guiding further visual extraction, which in turn enhances the description quality while preserving temporal context. Plugged into state-of-the-art VideoLMs, ReFineVQA yields consistent gains across diverse benchmarks--NExT-QA, EgoSchema, Video-MME, ActivityNet, and StreamingBench--even with a small external LLM of 3.8B parameters.

The single-image super-resolution domain has witnessed a significant performance improvement due to the advancement of deep learning models. However, most of the deep learning models use an integer-scale and scale-specific model for super-resolution. Separate scale-specific networks require huge memory during deployment. Therefore, a single model for any random scale image super-resolution is an old age demand. Unlike existing solutions based on implicit representation functions, we propose a fully convolutional arbitrary scale upscaling module. Our proposed module consists of fewer parameters and consumes less memory and inference time than existing ones. As it is based on a simple convolutional neural network, it has the flexibility to be adapted to any other networks for arbitrary scale transformation. We also show that the proposed upscaling module can be extended to super-resolution under homographic transformation. We perform extensive experiments on widely used benchmark datasets, and experimental findings show the comparative performance of our proposed upscaling module as compared to recently developed approaches, while it provides ad-hoc benefits of being simple and computationally inexpensive.

Visible-infrared person re-identification (VI-ReID) aims to match individuals across different camera modalities, a critical task in modern surveillance systems. While current VI-ReID methods focus on cross-modality matching, real-world applications often involve mixed galleries containing both V and I images, where state-of-the-art methods show significant performance limitations due to large domain shifts and low discrimination across mixed modalities. This is because gallery images from the same modality may have lower domain gaps but correspond to different identities. This paper introduces a novel mixed-modal ReID setting, where galleries contain data from both modalities. To address the domain shift among inter-modal and low discrimination capacity in intra-modal matching, we propose the Mixed Modality-Erased and -Related (MixER) method. The MixER learning approach disentangles modality-specific and modality-shared identity information through orthogonal decomposition, modality-confusion, and ID-modality-related objectives. MixER enhances feature robustness across modalities, improving cross-modal and mixed-modal settings performance. Our extensive experiments on the SYSU-MM01, RegDB and LLMC datasets indicate that our approach can provide state-of-the-art results using a single backbone, and showcase the flexibility of our approach in mixed gallery applications.

As deep neural networks (DNNs) are increasingly deployed in sensitive applications, ensuring their security and robustness has become critical. A major threat to DNNs arises from adversarial attacks, where small input perturbations can lead to incorrect predictions. Recent advances in adversarial training improve robustness by incorporating additional examples from external datasets or generative models. However, these methods often incur high computational costs, limiting their practicality and hindering real-world deployment. In this paper, we propose a cost-efficient alternative based on Lipschitz continuity that achieves robustness comparable to models trained with extensive supplementary data. Unlike conventional adversarial training, our method requires only a single pass over the dataset without gradient estimation, making it highly efficient. Furthermore, our method can integrate seamlessly with existing adversarial training frameworks and enhances the robustness of models without requiring extra generative data. Experimental results show that our approach not only reduces computational overhead but also maintains or improves the defensive capabilities of robust neural networks. This work opens a promising direction for developing practical, scalable defenses against adversarial attacks.

Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference cost remains a major bottleneck, particularly in video. We empirically analyze visual token sampling in MLLMs and observe a strong correlation between subset token coverage and segmentation performance. This motivates our design of a simple and effective token pruning method that selects a compact yet spatially representative subset of tokens to accelerate inference. In this paper, we introduce a novel visual token pruning method for IVS, called EVTP-IV, which builds upon the k-center by integrating spatial information to ensure better coverage. We further provide an information-theoretic analysis to support our design. Experiments on standard IVS benchmarks show that our method achieves up to 5x speed-up on video tasks and 3.5x on image tasks, while maintaining comparable accuracy using only 20% of the tokens. Our method also consistently outperforms state-of-the-art pruning baselines under varying pruning ratios.