Related papers: Align Your Query: Representation Alignment for Mul…

Medical contrastive vision-language pre-training (VLP) has demonstrated significant potential in improving performance on downstream tasks. Traditional approaches typically employ contrastive learning, treating paired image-report samples…

Visual Question Answering (VQA) attracts much attention from both industry and academia. As a multi-modality task, it is challenging since it requires not only visual and textual understanding, but also the ability to align cross-modality…

In most modern object detection pipelines, the detection proposals are processed independently given the feature map. Therefore, they overlook the underlying relationships between objects and the surrounding background, which could have…

Cross-domain knowledge alignment is essential for integrating heterogeneous medical systems, yet existing approaches typically treat entity alignment as a static matching problem, ignoring query context and cross-system asymmetry. This…

Distributed representations of medical concepts have been used to support downstream clinical tasks recently. Electronic Health Records (EHR) capture different aspects of patients' hospital encounters and serve as a rich source for…

Single-modal object re-identification (ReID) faces great challenges in maintaining robustness within complex visual scenarios. In contrast, multi-modal object ReID utilizes complementary information from diverse modalities, showing great…

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning, yet limited annotated datasets restrict medical-specific model development. While vision-language models (VLMs) like CLIP offer strong…

Medical AI assistants support doctors in disease diagnosis, medical image analysis, and report generation. However, they still face significant challenges in clinical use, including limited accuracy with multimodal content and insufficient…

Real-world object re-identification (ReID) systems often face modality inconsistencies, where query and gallery images come from different sensors (e.g., RGB, NIR, TIR). However, most existing methods assume modality-matched conditions,…

Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…

Learning medical visual representations from paired images and reports is a promising direction in representation learning. However, current vision-language pretraining methods in the medical domain often simplify clinical reports into…

Detecting anatomical landmarks in medical imaging is essential for diagnosis and intervention guidance. However, object detection models rely on costly bounding box annotations, limiting scalability. Weakly Semi-Supervised Object Detection…

Multimodal Emotion Recognition (MER) aims to perceive human emotions through three modes: language, vision, and audio. Previous methods primarily focused on modal fusion without adequately addressing significant distributional differences…

Recent approaches have shown that large-scale vision-language models such as CLIP can improve semantic segmentation performance. These methods typically aim for pixel-level vision-language alignment, but often rely on low resolution image…

Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for…

The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable…

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been…

Understanding human intentions (e.g., emotions) from videos has received considerable attention recently. Video streams generally constitute a blend of temporal data stemming from distinct modalities, including natural language, facial…

Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived…

Multimodal recommender systems (MMRS) leverage images, text, and interaction signals to enrich item representations. However, recent alignment based MMRSs that enforce a unified embedding space often blur modality specific structures and…