WACV 2026 Papers

Traditional vision-language models struggle with fine-grained taxonomic reasoning, particularly distinguishing between visually similar species within the same genus or family. We propose a reinforcement learning approach using Group Relative Policy Optimization with intermediate rewards that decompose the reasoning process into hierarchical taxonomic predictions. Our method incentivizes models to explicitly reason about species-level, genus-level, and family-level features before making final classifications. This structured approach is designed not only to boost accuracy but also to yield a transparent, verifiable decision-making process. On the challenging Birds-to-Words dataset, our approach achieves 91.7% accuracy on same-species verification, matching human performance (77.3%) while generating interpretable reasoning traces. We demonstrate cross-domain generalization showing substantial gains on primate verification while generating explainable traces. The intermediate reward mechanism shows that structured biological reasoning provides a powerful framework for fine-grained visual discrimination.

Recent advances in Vision-Language Models (VLMs) and Large Language Models (LLMs) have demonstrated remarkable zero-shot capabilities while becoming increasingly accessible. They have enabled zero-shot text-to-video search, yet they still struggle on real-world queries that demand temporally aligned reasoning across vision and speech. We present VRAgent, an agentic retrieval framework that leverages a central LLM as a planner which (i) decomposes a free-form user query into a tool-instruction set spanning visual, dialogue and other modality-specific retrievers, and (ii) iteratively self-refines this plan by scoring the outputs and rewriting the next tool-instruction set. The resulting closed-loop optimization acts at test time and requires no additional training data or gradient updates. VRAgent is modular by design--adding a new modality is as simple as adding a corresponding foundation model into the toolbox. On our newly proposed MM-MSRVTT and TVR-1200 multimodal benchmarks, VRAgent improves average recall by +8.3% and +1.7% over the best zero-shot baselines, while on single-modality MSR-VTT and DiDeMo it obtains consistent gains of +3.7% and +4.1%. An interactive variant that asks the user up to two multiple-choice questions pushes average recall to 79.7% on MSR-VTT, underscoring the value of on-the-fly human feedback.

Rapid player motion, occlusions, substitutions, and jersey changes pose major challenges for identity-consistent tracking in sports. Existing multi-object tracking (MOT) methods struggle in long-term and multi-perspective settings like broadcast footage, where views change frequently. To address this, we first introduce MuPNIT, the first MOT and ReID benchmark to capture these multi-perspective dynamics along with long-term appearance variations across seasons, teams, and jersey changes. Second, we propose Global ID Fusion (GIF), a novel context-aware tracking-with-identification framework that enables robust tracking of both seen and unseen players. Unlike prior approaches, GIF performs single pass global ID association and supports zero-shot identity recognition. Our approach achieves state-of-the-art results, improving HOTA by 25.3% and IDF1 by 79.5% over OC-SORT. Finally, to assess identity consistency, we introduce five Global ID metrics that reveal tradeoffs in tracking stability. By bridging MOT and ReID, our work advances identity-aware player tracking in sports and sets a new benchmark with applications in sports analytics, surveillance, and long-term person search.

Text-to-image inpainting models often exhibit an unpredictable balance among image coherence and prompt adherence. This rigidity limits their adaptability across diverse scenarios, including coarse masks, non-object, and interaction prompts. Recognizing this instability as an indicator of learned generation diversity, we aim to control model behavior for given objective. We propose Empirical Feature Intervention (EFI), a metric-agnostic framework that precomputes how feature interventions influence evaluation metrics--such as CLIP, Human Preference Score (HPS), and Image Reward (IR). Building on EFI, we introduce FreeCond, a free-of-cost framework that applies two simple input interventions (Image Frequency and Mask Value Modulation), these interventions can be further optimized via Surrogate Intervention Optimization (SIO) based on a surrogate model regressed with precomputed EFI data. FreeCond enables real-time, user-interactive control of pre-trained models without retraining or architectural modifications. Also, to benchmark performance on challenging settings, we present FCIBench. Experiments on EditBench, BrushBench, and FCIBench demonstrate that FreeCond substantially improves CLIP, HPS, and IR metrics by up to 22%, 8%, and 54%, respectively.

Autonomous vehicles must excel in safety-critical perception tasks, especially in adverse weather conditions. In addition, transitional weather shifts in nature, such as sunny to rainy, rainy to cloudy, etc., pose abrupt illumination changes that can distort object boundaries and degrade segmentation performance. Existing research focuses mainly on segmentation in clear and discrete weather conditions, leaving a gap in addressing the issues of transitional weather scenarios. Hence, we propose a novel method called causal road and rest segmentation (CaRS) that utilizes causal intervention to mitigate the confounding bias due to transitional weather changes. We use dual complementary attention modules, one for causal and another for confounding feature extraction. These modules complement each other and are fine-tuned via an adversarial min-max approach to reduce confounding bias and enhance segmentation performance. Also, our CaRS method concurrently performs road semantic segmentation and instance segmentation of vehicles and pedestrians. Further, we introduce a transitional weather-driving dataset for segmentation (TWDS16) using a spurious correlation generator that leverages data interpolation to produce 16 weather transitions. We evaluate the performance of CaRS on TWDS16, along with three other benchmark datasets, namely, Foggy Cityscapes, RainCityscapes, and BDD100K. The experimental results validate the efficacy of the proposed method in mitigating confounding influences, leading to improved mIoU for semantic segmentation and mAP for instance segmentation across diverse datasets

We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency Spectrum Attention Interpolation technique to facilitate generation and intact key identity characteristics. Second, we achieve Target Structure Guidance via plug-and-play attention injection to better align the structural features from the target frame to the generation. Third, we present a Flow-Guided Attention Temporal Smoothening mechanism that enforces spatiotemporal coherence without modifying the underlying diffusion model to reduce temporal inconsistencies typically encountered in frame-wise generation. Our method requires no additional training or video-specific fine-tuning. Extensive experiments show that our method significantly enhances temporal consistency and visual fidelity, offering a practical and modular solution for video-based face swapping. Our code is available at https://github.com/Sanoojan/VFace.

Controllable image generation is fundamental to the success of modern generative AI, yet it faces a critical trade-off between semantic fidelity and inference speed. The RemEdit diffusion-based framework addresses this trade-off with two synergistic innovations. First, for editing fidelity, we navigate the latent space as a Riemannian manifold. A mamba-based module efficiently learns the manifold's structure, enabling direct and accurate geodesic path computation for smooth semantic edits. This control is further refined by a dual-SLERP blending technique and a goal-aware prompt enrichment pass from a Vision-Language Model. Second, for additional acceleration, we introduce a novel task-specific attention pruning mechanism. A lightweight pruning head learns to retain tokens essential to the edit, enabling effective optimization without the semantic degradation common in content-agnostic approaches. RemEdit surpasses prior state-of-the-art editing frameworks while maintaining real-time performance under 50% pruning. Consequently, RemEdit establishes a new benchmark for practical and powerful image editing. Source code: https://github.com/eashanadhikarla/RemEdit.

Monocular 3D detection relies on just a single camera and is therefore easy to deploy. Yet, achieving reliable 3D understanding from monocular images requires substantial annotation, and 3D labels are especially costly. To maximize performance under constrained labeling budgets, it is essential to prioritize annotating samples expected to deliver the largest performance gains. This prioritization is the focus of active learning. Curiously, we observed two significant limitations in active learning algorithms for 3D monocular object detection. First, previous approaches select entire images, which is inefficient, as non-informative instances contained in the same image also need to be labeled. Secondly, existing methods rely on uncertainty-based selection, which in monocular 3D object detection creates a bias toward depth ambiguity. Consequently, distant objects are selected, while nearby objects are overlooked.To address these limitations, we propose IDEAL-M3D, the first instance-level pipeline for monocular 3D detection.For the first time, we demonstrate that an explicitly diverse, fast-to-train ensemble improves diversity-driven active learning for monocular 3D. We induce diversity with heterogeneous backbones and task-agnostic features, loss weight perturbation, and time-dependent bagging. IDEAL-M3D shows superior performance and significant resource saving: with just 60% of the annotations, we achieve similar or better AP3D on KITTI validation and test set results compared to training the same detector on the whole dataset.

Object detection in biomedical settings is fundamentally constrained by the scarcity of labeled data and the frequent emergence of novel or rare categories. We present FSP-DETR, a unified detection framework that enables robust few-shot detection, open-set recognition, and generalization to unseen biomedical tasks within a single model. Built upon a class-agnostic DETR backbone, our approach constructs class prototypes from original support images and learns an embedding space using augmented views and a lightweight transformer decoder. Training jointly optimizes a prototype matching loss, an alignment-based separation loss, and a KL divergence regularization to improve discriminative feature learning and calibration under scarce supervision. Unlike prior work that tackles these tasks in isolation, FSP-DETR enables inference-time flexibility to support unseen class recognition, background rejection, and cross-task adaptation without retraining. We also introduce a new ova species detection benchmark with 20 parasite classes and establish standardized evaluation protocols. Extensive experiments across ova, blood cell, and malaria detection tasks demonstrate that FSP-DETR significantly outperforms prior few-shot and prototype-based detectors, especially in low-shot and open-set scenarios.

Adversarial contrastive learning aims to learn robust representations from unlabeled data by integrating adversarial training and contrastive learning. Accordingly, existing methods typically generate adversarial perturbations that maximize the contrastive loss during adversarial training. However, these approaches frequently produce ineffective perturbations, as their effectiveness heavily depends on the semantic similarity among samples within each mini-batch, which is not explicitly controlled. As a result, the improvement in robustness remains limited. To address this, we propose a novel approach that leverages the well-structured representation space learned via contrastive learning, where semantically similar samples cluster well while dissimilar ones are positioned farther apart. Exploiting this clustering structure, we construct adversarial perturbations that move samples away from a group of similar samples and toward a group of dissimilar ones, thereby inducing stronger adversarial effects. Compared to existing approaches, our method achieves significant improvements in robust accuracy by up to 4.75% against the PGD attack and 7.59% against Auto-Attack.

We present Ego-EXTRA, a video-language Egocentric Dataset for EXpert-TRAinee assistance. Ego-EXTRA features 50 hours of unscripted egocentric videos of subjects performing procedural activities (the trainees) while guided by real-world experts who provide guidance and answer specific questions using natural language. Following a "Wizard of OZ" data collection paradigm, the expert enacts a wearable intelligent assistant, looking at the activities performed by the trainee exclusively from their egocentric point of view, answering questions when asked by the trainee, or proactively interacting with suggestions during the procedures. This unique data collection protocol enables Ego-EXTRA to capture a high-quality dialogue in which expert-level feedback is provided to the trainee. Two-way dialogues between experts and trainees are recorded, transcribed, and used to create a novel benchmark comprising more than 45k high-quality Visual Question Answer sets, which we use to evaluate Multimodal Large Language Models. The results show that Ego-EXTRA is challenging and highlight the limitations of current models when used to provide expert-level assistance to the user. The Ego-EXTRA dataset is publicly available to support the benchmark of egocentric video-language assistants: https://fpv-iplab.github.io/Ego-EXTRA/.

Indoor localization in GPS-denied environments is crucial for applications like emergency response and assistive navigation. Vision-based methods such as PALMS enable infrastructure-free localization using only a floor plan and a stationary scan, but are limited by the short range of smartphone LiDAR and ambiguity in indoor layouts. We propose PALMS+, a modular, image-based system that addresses these challenges by reconstructing scale-aligned 3D point clouds from posed RGB images using a foundation monocular depth estimation model (Depth Pro), followed by geometric layout matching via convolution with the floor plan. PALMS+ outputs a posterior over the location and orientation, usable for direct or sequential localization. Evaluated on the Structured3D and a custom campus dataset consisting of 80 observations across four large campus buildings, PALMS+ outperforms PALMS and F3Loc in stationary localization accuracy--without requiring any training. Furthermore, when integrated with a particle filter for sequential localization on 33 real-world trajectories, PALMS+ achieved lower localization errors compared to other methods, demonstrating robustness for camera-free tracking and its potential for infrastructure-free applications. Code and data are available at: https://github.com/Head-inthe-Cloud/PALMS-Plane-based-Accessible-Indoor-Localization-Using-Mobile-Smartphones

WiFi-based human activity recognition (HAR) faces significant challenges in cross-domain generalization due to dynamic environmental variations, device heterogeneity, and subtle changes in human behavior. In this paper, we introduce DATTA - Domain-Adversarial Test-Time Adaptation - a novel framework that combines domain-adversarial training (DAT) with test-time adaptation (TTA) and a random weight-resetting mechanism. Unlike previous approaches that apply these techniques in isolation, DATTA is specifically tailored for WiFi-based HAR: it leverages DAT to learn robust, domain-invariant features while TTA continuously refines the model on streaming data. To mitigate catastrophic forgetting during adaptation, we incorporate a weight-resetting mechanism, ensuring sustained performance over prolonged domain shifts. Our extensive experiments on the Widar3.0-G6D dataset demonstrate that DATTA not only outperforms state-of-the-art methods by up to 8.1% in F1-Score but also achieves real-time inference with a lightweight architecture, making it a compelling solution for practical WiFi sensing applications. The PyTorch implementation of DATTA is publicly available at: https://github.com/StrohmayerJ/DATTA.

Thermal imaging is crucial for scene understanding, particularly in low-light and nighttime conditions. However, collecting large thermal datasets is costly and labor-intensive due to the specialized equipment required for infrared image capture. To address this challenge, researchers have explored visible-to-thermal image translation. Most existing methods rely on Generative Adversarial Networks (GANs) or Diffusion Models (DMs), treating the task as a style transfer problem. As a result, these approaches attempt to learn both the modality distribution shift and underlying physical principles from limited training data. In this paper, we propose F-ViTA, a novel approach that leverages the general world knowledge embedded in foundation models to guide the diffusion process for improved translation. Specifically, we condition an InstructPix2Pix Diffusion Model with zero-shot masks and labels from foundation models such as SAM and Grounded DINO. This allows the model to learn meaningful correlations between scene objects and their thermal signatures in infrared imagery. Extensive experiments on five public datasets demonstrate that F-ViTA outperforms state-of-the-art (SOTA) methods. Furthermore, our model generalizes well to out-of-distribution (OOD) scenarios and can generate Long-Wave Infrared (LWIR), Mid-Wave Infrared (MWIR), and Near-Infrared (NIR) translations from the same visible image. Code: Released post-review.

Reference-based line art video colorization colorizes the target line art according to reference images, which is an essential stage for the cartoon production workflow. However, the manual colorization process is time-consuming and repetitive, making automatic video colorization highly desirable. Existing cartoon colorization methods struggle with domain misalignment between the reference and line art images and the loss of details caused by compression into a low-dimensional space in the existing video diffusion models, reducing colorization quality. In this paper, we propose an Offset Prior-based Diffusion Model (OPDM) for cartoon video colorization, which utilizes the powerful generation capability of the diffusion model and cross-domain matching priors to generate high-quality colorization results. Specifically, we design a simple and effective Offset-Adapter that leverages the idea of sampling offsets in deformable convolution to estimate the cross-domain spatial offset features between the target line arts and reference images. We further introduce a new training strategy that combines forward diffusion and reverse denoising in the training stage to ensure content consistency. Experiments on a public cartoon dataset and our newly constructed long cartoon video dataset demonstrate that our proposed method outperforms the existing state-of-the-art line art coloring methods. Code is available at https://github.com/xzh976/OPDM.

This paper addresses the challenge of detecting complex-shaped action tubes in videos. Existing methods assume that actor's position changes slightly in short video clips. Therefore, they either oversimplify the shape of action tubes by representing them as cuboids or learnable positional patterns. However, these solutions may produce an action tube losing the corresponding actor when the actor trajectory becomes complex. This is because they rely solely on position information to determine action tubes, lacking the ability to trace the same actor when their movement patterns are intricate. To address this issue, we propose Actor-related Tubelet (ART), which incorporates actor-specific information when generating action tubes. Regardless of the complexity of an actor's trajectory, ART ensures that an action tube consistently tracks the same actor, relying on actor-specific cues rather than solely on positional information. To assess ART's effectiveness, we introduce a metric for quantifying tube shape complexity and evaluate ART on three mainstream datasets, MultiSports, UCF101-24 and JHMDB51-21, achieving substantial improvements.

3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and an unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by evaluating a 3D point against a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility.

The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.

Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in safety-critical applications. We introduce a training-free, post-hoc uncertainty estimation method for contrastive VLMs that can be used to detect erroneous predictions. Our approach assesses visual feature consistency within a class, using feature projection combined with multivariate Gaussians to create class-specific probabilistic embeddings. At inference, test embeddings are scored using the log-probability under each class distribution, with a softmax-normalized density used as the new confidence score. Our method is VLM-agnostic, requires no fine-tuning, robust to label shift, and works effectively with as few as 300 training images per class. Extensive experiments on ImageNet, Flowers102, and Food101 show state-of-the-art error detection performance, significantly outperforming both deterministic and probabilistic VLM baselines. Code is available at https://github.com/zhenxianglin/ICPE.