Related papers: Modality-Aware Contrastive Instance Learning with …

Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focused on English speakers describing a single picture (e.g., the…

Multiple instance learning (MIL) has been extensively applied to whole slide histopathology image (WSI) analysis. The existing aggregation strategy in MIL, which primarily relies on the first-order distance (e.g., mean difference) between…

Multiple instance learning (MIL) has emerged as a powerful framework for weakly supervised whole slide image (WSI) classification, enabling slide-level predictions without requiring detailed patch-level annotations. Despite its success, a…

The recent success of audio-visual representation learning can be largely attributed to their pervasive property of audio-visual synchronization, which can be used as self-annotated supervision. As a state-of-the-art solution, Audio-Visual…

Audio-visual segmentation (AVS) aims to segment objects in videos based on audio cues. Existing AVS methods are primarily designed to enhance interaction efficiency but pay limited attention to modality representation discrepancies and…

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS)…

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation…

In this paper, we address the Multi-Instance-Learning (MIL) problem when bag labels are naturally represented as ordinal variables (Multi--Instance--Ordinal Regression). Moreover, we consider the case where bags are temporal sequences of…

In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and…

In the field of 3D object detection for autonomous driving, the sensor portfolio including multi-modality and single-modality is diverse and complex. Since the multi-modal methods have system complexity while the accuracy of single-modal…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Multi-Instance Learning (MIL) is pivotal for analyzing complex, weakly labeled datasets, such as whole-slide images (WSIs) in computational pathology, where bags comprise unordered collections of instances with sparse diagnostic relevance.…

Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing…

Multimodal learning integrates diverse modalities but suffers from modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing methods predominantly rely on static modulation or…

Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask. To increase the ability of encoder-decoder neural networks to perform this task across large…

In this paper, we propose to make a systematic study on machines multisensory perception under attacks. We use the audio-visual event recognition task against multimodal adversarial attacks as a proxy to investigate the robustness of…

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…

Unlike traditional Multimodal Class-Incremental Learning (MCIL) methods that focus only on vision and text, this paper explores MCIL across vision, audio and text modalities, addressing challenges in integrating complementary information…

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned…