相关论文: Modality-missing RGBT Tracking: Invertible Prompt …

Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by…

Prompt learning is an effective paradigm that bridges gaps between the pre-training tasks and the corresponding downstream applications. Approaches based on this paradigm have achieved great transcendent results in various applications.…

Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to meet continuously emerging requirements without expensive retraining. MCIT faces two major obstacles: catastrophic forgetting (where old…

Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text…

Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length can grow fast, leading to increased computational…

Red teaming is a common strategy for identifying weaknesses in generative language models (LMs), where adversarial prompts are produced that trigger an LM to generate unsafe responses. Red teaming is instrumental for both model alignment…

Multimodal deep learning, especially vision-language models, have gained significant traction in recent years, greatly improving performance on many downstream tasks, including content moderation and violence detection. However, standard…

An active challenge in developing multimodal machine learning (ML) models for healthcare is handling missing modalities during training and deployment. As clinical datasets are inherently temporal and sparse in terms of modality presence,…

General continual learning (GCL) is a broad concept to describe real-world continual learning (CL) problems, which are often characterized by online data streams without distinct transitions between tasks, i.e., blurry task boundaries. Such…

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…

Multimodal semantic segmentation benefits remote sensing analysis by combining complementary information from different sensor modalities. In real-world remote sensing applications, one or more modalities may be unavailable due to sensor…

3D cross-modal retrieval is gaining attention in the multimedia community. Central to this topic is learning a joint embedding space to represent data from different modalities, such as images, 3D point clouds, and polygon meshes, to…

Multimodal models often converge to a dominant-modality solution, in which a stronger, faster-converging modality overshadows weaker ones. This modality imbalance causes suboptimal performance. Existing methods attempt to balance different…

As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a…

Existing multimodal tracking studies focus on bi-modal scenarios such as RGB-Thermal, RGB-Event, and RGB-Language. Although promising tracking performance is achieved through leveraging complementary cues from different sources, it remains…

RGB-Thermal (RGB-T) pedestrian detection aims to locate the pedestrians in RGB-T image pairs to exploit the complementation between the two modalities for improving detection robustness in extreme conditions. Most existing algorithms assume…

Prompt tuning offers a parameter-efficient way to adapt large pre-trained language models to new tasks, but most existing approaches are designed for single-task settings, failing to share knowledge across related tasks. We propose…

Multimodal learning (MML) aims to jointly exploit the common priors of different modalities to compensate for their inherent limitations. However, existing MML methods often optimize a uniform objective for different modalities, leading to…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily on RGB-derived modalities, which fall short in real-world…