Image-to-Point Cloud Registration aims to estimate the camera pose of a given image within a 3D scene point cloud, which is a fundamental task in autonomous driving and large-scale outdoor localization. Recent implicit correspondence learning methods have improved registration performance by learning cross-modal alignment in an end-to-end framework, leading to more accurate camera pose estimation. However, due to the inherent modality discrepancy between images and sparse LiDAR point clouds, reliable cross-modal correspondence learning remains challenging. To address this issue, we propose Depth-Guided Projective Alignment for Image-to-Point-Cloud Registration (DPA-I2P). Unlike naive depth or feature concatenation, Ray-Conditioned Metric Depth Encoding (RMDE) and Projection-Consistent Vision Lifting (PVL) exploit depth and visual cues in a structured, geometry-aware manner. In addition, Cross-Modal Query Pruning (CQP) suppresses unreliable queries during early refinement to improve matching stability. Experiments on KITTI and nuScenes demonstrate the effectiveness of the proposed method. On KITTI, DPA-I2P reduces RTE and RRE by 45.0% and 55.6% over the strongest implicit baseline, respectively. On nuScenes, DPA-I2P also improves registration accuracy over the evaluated baselines, suggesting better transferability to different driving scenes.
Radiology report generation (RRG) has recently benefited from large language models, which substantially improve report fluency. However, clinically faithful generation remains challenging because current supervision is still imposed mostly at the report level. This creates a granularity mismatch: radiology reports are composed of disease-grounded findings, while existing methods are trained mainly with whole-report objectives. To address this problem, we propose Graph-Supervised Hierarchical Clinical Alignment, which reformulates image-report supervision as a hierarchical clinical alignment problem. Our method structures this alignment as a disease-conditioned process, where supervision is decomposed into two levels: Disease-Centric Alignment for fine-grained disease-specific correspondence, and Global Clinical Semantic Alignment for report-level semantic coherence. A clinical knowledge graph is used as a training-time-only structural prior that defines disease-specific supervision units and their clinical relationships, introducing no additional overhead at inference. Because standard contrastive alignment could produce false negatives when studies share overlapping pathologies, we combine instance-conditioned discriminative matching with disease-conditioned soft regularization, enabling fine-grained yet clinically consistent cross-modal representations. Experiments on MIMIC-CXR, IU-Xray, and COV-CTR show that our method consistently improves performance on both conventional and clinical metrics. Notably, our 3B model surpasses several prior systems with larger 7B/13B backbones, suggesting that improving supervision structure, rather than increasing model size, can be more effective for RRG.
Eunsoo Im, Junghun Suh, Gyeonggwan Lee +1cs.CV cs.AI cs.RO
Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics. We propose CVSD-Reg, a robust global LiDAR registration framework that distills visual semantic priors from a vision foundation model into LiDAR representations. In Stage 1, a Point Transformer V3 student learns from a frozen DINOv2 teacher through contrastive distillation and spherical-manifold alignment, which preserves the hyperspherical geometry of the teacher embedding space. Self-supervised InfoNCE consistency and soft $\mathrm{SE}(3)$ invariance further encourage viewpoint-robust descriptors. In Stage 2, the distilled representation is adapted to registration through correspondence learning, density-aware point-dropout augmentation, and end-to-end pose optimization. With a single checkpoint, CVSD-Reg generalizes to both single-sensor and zero-shot cross-sensor scenarios without sensor-specific adaptation and remains entirely camera-free at inference. On KITTI, nuScenes, and HeLiPR, CVSD-Reg achieves strict success rate (SR@0.5\,m/$1^\circ$) of 97.7$\%$, 99.0$\%$, and 99.3$\%$, respectively, including 97.3$\%$ on sparse 16-beam Velodyne scans. It outperforms state-of-the-art geometric registration methods by up to 44.0 percentage points without requiring camera inputs or post-hoc ICP refinement.
Transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) provide complementary information for endometriosis image analysis, yet existing studies mainly focus on single-modality analysis or disease classification, leaving cross-modal ovarian segmentation largely unexplored. In this work, to tackle the increased difficulty of ovary segmentation in MRI due to ovaries' small target size and ambiguous boundaries with surrounding pelvic structures, we propose a dual branch framework for ovary segmentation across TVUS and MRI. More specifically, by adapting MedSAM3 with TVUS-derived prototype bank, we aim to align anatomically consistent feature representations across both modalities. Extensive experiments are conducted on endometriosis-related TVUS and MRI datasets. We observe quantitative and qualitative improvements of over 5 percentage points for the proposed dual-branch approach compared with multiple state-of-the-art methods. Furthermore, our ablation study shows the contribution of individual components such as the prototype bank and the importance of warm-up pretraining in the source TVUS domain.
Visible-infrared person re-identification (VI-ReID) suffers from cross-modal discrepancies and limited discriminative capabilities, leading to suboptimal recognition performance. Current approaches exhibit limitations in semantic mining, cross-modal fusion and feature constraints. To tackle these challenges, we propose MDCRNet, a Multi-scale Decomposed Convolution Refinement Network that enhances cross-modal feature learning and discriminative metric learning. Specifically, we introduce a Hierarchical Learning Module (HLM) containing four Hierarchical Decomposed Convolution Attention (HDCA) modules, each equipped with lightweight channel attention and multi-scale spatial perception blocks to capture multi-scale spatial dependencies. Moreover, we develop a Joint Discriminative Metric Loss (JDML) incorporating a novel Granularity Discriminative Loss (GDL) that simultaneously optimizes intra-identity compactness and inter-identity separability across modalities. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate that MDCRNet achieves state-of-the-art performance on both benchmarks. Code is available at https://github.com/Kevin-zms/MDCRNet.
Yuhao Huang, Yuanji Zhang, Yuhuan Lu +3eess.IV cs.AI cs.CV cs.LG
Assessment of ventriculomegaly (VM) on fetal brain ultrasound relies primarily on measuring lateral ventricular atrial width on standard planes, which is operator-dependent and may not fully reflect the overall ventricular enlargement. Fetal brain MRI provides more reliable volumetric information but is costly and less accessible for routine use. To address these limitations, we propose VIFBA, an ultrasound video-based framework for fetal brain assessment that predicts MRI-derived lateral ventricular volume, classifies VM severity, and identifies potential non-VM fetal brain abnormalities. Our contribution is three-fold. First, we introduce a joint-embedding predictive architecture (JEPA)-inspired tube latent prediction objective that leverages spatio-temporal coherence in ultrasound videos to enhance representation learning. Second, we develop a contrastive cross-modal alignment strategy that transfers structural information from MRI to ultrasound during training, while requiring ultrasound alone at inference. Third, we augment VIFBA with a training-free vision-language model and retrieval augmentation to verify uncertain predictions and identify potential non-VM fetal brain abnormalities. We validated VIFBA on a large dataset comprising 857 cases (3,196 videos) with paired fetal brain ultrasound and MRI examinations. On held-out test data, VIFBA achieved an MAE of 0.5909 mL and Pearson correlation coefficient of 0.9907 for ventricular volume regression, 0.9400 accuracy for VM severity classification, and an F1 score of 0.7764 for multi-abnormality classification, substantially outperforming single-task baselines, video-based strong competitors, and state-of-the-art foundation models. By enabling MRI-informed volumetric assessment from routine ultrasound alone, VIFBA offers a practical and potentially broadly deployable pathway toward accurate and affordable prenatal brain screening.
Soumen Ghosh, Amit Soni Arya, Tilottama Goswami +3cs.CV
Focal cortical dysplasia (FCD) type II is an important structural cause of drug-resistant focal epilepsy, but its small size, heterogeneous appearance, and subtle MRI characteristics make automated segmentation challenging. Conventional multimodal networks commonly concatenate T1-weighted (T1w) and fluid-attenuated inversion recovery (FLAIR) images, requiring subsequent layers to learn useful cross-modal relationships implicitly. We propose CRIL-U-Net, a 3D U-Net incorporating a Compact Ratio-Interaction Learning module that combines local spatial features, voxel-wise cross-modal mixing, and bidirectional ratio-inspired interactions. CRIL-U-Net was compared with a conventional 3D U-Net and an input self-attention U-Net using five-fold cross-validation on 85 FCD subjects and 25 healthy controls. Each architecture was trained independently using Dice-binary cross-entropy (Dice-BCE) and Focal Tversky-Focal (FTF) losses. With FTF, CRIL-U-Net achieved the highest mean Dice score (0.196 +/- 0.262), compared with 0.136 +/- 0.224 for the U-Net and 0.135 +/- 0.214 for the attention comparator. It produced nonzero lesion overlap in 44 of 85 cases, compared with 36 for the U-Net. Under FTF, CRIL-U-Net significantly outperformed both comparison architectures after false-discovery-rate correction. These findings suggest that compact cross-modal representation learning can improve FCD segmentation within a controlled U-Net setting when combined with an imbalance-aware objective, although the remaining zero-overlap rate of 48.2% highlights the need for further validation and methodological development.
Jingwei Zhao, Gus Xia, Ziyu Wang +1cs.SD cs.AI cs.MM eess.AS
What is music style? Though often described using text labels such as "swing," "classical," or "emotional," the real style remains implicit and hidden in concrete music examples. In this paper, we introduce a cross-modal framework that learns implicit music styles from raw audio and applies them to symbolic music generation. Inspired by BLIP-2, our model leverages a Querying Transformer (Q-Former) to extract style representations from a large, pre-trained audio language model (LM), and further applies them to condition a symbolic LM for generating piano arrangements. We adopt a two-stage training strategy: contrastive learning to align auditory style with symbolic expression, followed by generative modeling for music arrangement. Our model generates piano performances jointly conditioned on a lead sheet (content) and a reference audio example (style), enabling controllable and stylistically faithful arrangement. Experiments demonstrate the effectiveness of our approach in piano cover generation, style transfer, and audio-to-MIDI retrieval, achieving substantial improvements in style-aware alignment and music quality.
Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transfer poorly to pediatric populations when pediatric labels are scarce. Existing multimodal ECG--text methods typically align waveforms and text at the global sample level, entangling evidence from co-occurring diagnoses and limiting transfer under this gap. We propose Pediatric-Adult ECG Alignment via Cross-modal Enhancement (PEACE), a knowledge-guided framework pretrained on the largely adult MIMIC-IV ECG corpus. PEACE describes each diagnosis along rhythm, morphology, and ST--T axes and, per recording, composes only positive-label descriptors into three axis tokens and a fused embedding. A label query network (LQN) uses diagnostic labels as queries to cross-attend over ECG tokens and axis tokens, while label set aware bidirectional contrastive learning (LSBC) aligns pooled ECG features with the fused embedding when recordings share diagnoses. Curriculum adaptive fusion (CAF) gates alignment strength according to smoothed classification loss and training progress, limiting disruption during early optimization. The knowledge branch is used only for training supervision; inference uses ECG signals alone. On ZZU-pECG, PEACE reaches macro average AUCs of 59.39%, 81.74%, and 91.56% under zero-shot, 50-shot, and full fine-tuning, with the clearest gains over foundation and knowledge-pretraining baselines under limited supervision; versus domain adaptation initializations, zero-shot improves substantially while 50-shot AUC is comparable to DANN. After fine-tuning on PTB-XL, PEACE reaches 96.90% macro average AUC over nine harmonized labels. Ablations confirm that label-conditioned knowledge alignment, rather than global text fusion, is the key driver of pediatric transfer gains.
Kunal Pratap Singh, Ali Garjani, Rishubh Singh +6cs.CV cs.LG
Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications, e.g., deploying a household robot, involve devices that are equipped with a rich set of sensors that enable multimodal sensing in their test environment. This presents an opportunity to apply cross-modal learning to the multimodal data sensed by these devices to learn representations. Findings in developmental psychology also suggest that biological agents leverage it to build an effective representation of their surroundings. To study this, we propose a controlled setup, where we restrict a user device to just a given test environment. It results in a specialization setup where we attempt to develop a performant model for this specific test environment. Under this setup, we develop Test-Space Training (TST), which performs multimodal data collection in the test environment and performs self-supervised pre-training on it. We evaluate these models on various downstream tasks in the same environment. Under this setup, we find various interesting insights, such as collecting rich multimodal data only from the test environment and leveraging cross-modal learning, we can achieve competitive results with generalist models (e.g., DINOv2 and CLIP) pre-trained on large-scale internet datasets. This enables an alternative scenario where the need for external Internet-scale datasets for pre-training models is reduced. We also present a set of analyses and ablations that raise intriguing points on substituting data with (multi)modality, and how varying pre-training data enables a tradeoff between a model's abilities to specialise to a test environment, and generalize to held-out spaces.
Sutharsan Mahendran, Darshana Priyasad, Kaushik Roy +4cs.CV cs.LG cs.RO
Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding. However, existing distillation pipelines typically treat the VFM as a frozen feature source and train a heterogeneous 3D backbone to match fixed image embeddings, forcing the student to bridge both the modality gap and the cross-architecture gap between dense ViT token representations and sparse 3D encoders. We propose TOLiD, a self-supervised pretraining method for LiDAR representation learning that addresses this gap by coupling a LiDAR backbone with a student Vision Transformer (ViT) initialized from a frozen VFM teacher and applying supervision over compatible patch-token representations. TOLiD converts the set of point features within each image patch frustum into a token using Frustum Pooling followed by Frustum Attention, and performs token-level distillation with visibility masking. For LiDAR-only deployment, we lift token features back to per-point representations using masked bilinear sampling to avoid patches that have limited LiDAR points. We extensively evaluate TOLiD on five heterogeneous LiDAR datasets and four cross-sensor adaptation pairs, demonstrating improved transfer with frozen backbones and lightweight heads.
Zhengcen Li, Chenyang Jiang, Liangxu Su +4cs.CV cs.AI
AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under distributional variations. However, we identify a consistent failure mode: SOTA AI-generated image detectors often collapse when applied to frames extracted from videos. Through systematic analysis, we show that this cross-modal gap arises from both entangled synthesis-agnostic video processing shifts, including color conversion, codec compression, resizing, and blur, and model-specific fingerprints introduced by modern video generators. Motivated by these findings, we propose VINA (Video as Natural Augmentation), a unified AIGC detection framework that jointly trains on image and video data. VINA uses video frames as physically grounded natural augmentations and further introduces a cross-modal supervised contrastive objective to align image and video representations under a shared real/fake decision boundary. Extensive experiments on 14 image, video, and in-the-wild benchmarks show that VINA delivers bidirectional gains, improves robustness and transferability, and achieves state-of-the-art performance across nearly all evaluated settings without complex augmentation or dataset-specific tuning.
Deep neural networks enriched with structural information have been widely employed for facial expression recognition tasks. However, these methods often depend on hierarchical information rather than face property to finish expression recognition. In this paper, we propose a cross-modal network with strong biological and structural information for facial expression recognition (CMNet). CMNet can respectively learn expression information via face symmetry on a whole face, left and right half faces to extract complementary facial features. To prevent negative effect of biological and structural information fusion, a salient facial information refinement module can obtain salient facial expression information to improve stability of an obtained facial expression classifier. To reduce reliance on unilateral facial features, a half-face alignment optimization mechanism is designed to align obtained expression information of learned left and right half faces. Our experimental results demonstrate that CMNet outperforms several novel methods, i.e., SCN and LAENet-SA for facial expression recognition. Codes can be obtained at https://github.com/hellloxiaotian/CMNet.
Predicting social media popularity requires understanding both the intrinsic appeal of content and the external context that determines how it is exposed to users. Existing methods focus on content signals but do not separate them from exposure-related patterns, which causes the learned representations to absorb platform-specific visibility effects and weakens both interpretability and cross-platform transfer. This paper introduces OmniTrend, a unified framework that models popularity as the joint outcome of content attractiveness and contextual exposure. The content module learns cross-modal representations from visual, audio, and textual cues to quantify intrinsic appeal, while the context module estimates exposure from exogenous signals such as posting time, author activity, topical trends, and retrieval-based neighborhood statistics. OmniTrend learns separate predictors for content attractiveness and contextual exposure and integrates them in the final popularity estimate, which makes the role of each factor explicit and supports robust transfer across image and video platforms.
Speech-preserving facial expression manipulation (SPFEM) aims to enhance human expressiveness without altering mouth movements tied to the original speech. A primary challenge in this domain is the scarcity of paired data, namely aligned frames of the same individual with identical speech but different expressions, which impedes direct supervision for emotional manipulation. While current Visual-Language Models (VLMs) can extract aligned visual and semantic features, making them a promising source of supervision, their direct application is limited. To this end, we propose a Personalized Cross-Modal Emotional Correlation Learning (PCMECL) algorithm that refines VLM-based supervision through two major improvements. First, standard VLMs rely on a single generic prompt for each emotion, failing to capture expressive variations among individuals. PCMECL addresses this limitation by conditioning on individual visual information to learn personalized prompts, thereby establishing more fine-grained visual-semantic correlations. Second, even with personalization, inherent discrepancies persist between the visual and semantic feature distributions. To bridge this modality gap, PCMECL employs feature differencing to correlate the modalities, providing more precisely aligned supervision by matching the change in visual features to the change in semantic features. As a plug-and-play module, PCMECL can be seamlessly integrated into existing SPFEM models. Extensive experiments across various datasets demonstrate the superior efficacy of our algorithm.