Related papers: Fourier-Attentive Representation Learning: A Fouri…

Zero-Shot Learning (ZSL) aims to recognise unseen object classes, which are not observed during the training phase. The existing body of works on ZSL mostly relies on pretrained visual features and lacks the explicit attribute localisation…

Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual question answering. However, their robustness to physically…

Few-shot learning aims to recognize novel queries with limited support samples by learning from base knowledge. Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains,…

In the rapidly evolving field of artificial intelligence, multimodal models, e.g., integrating vision and language into visual-language models (VLMs), have become pivotal for many applications, ranging from image captioning to multimodal…

Synthetic aperture radar automatic target recognition (SAR-ATR) systems have rapidly evolved to tackle incremental recognition challenges in operational settings. Data scarcity remains a major hurdle that conventional SAR-ATR techniques…

Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual…

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics…

Multimodal emotion recognition (MMER) is an active research field that aims to accurately recognize human emotions by fusing multiple perceptual modalities. However, inherent heterogeneity across modalities introduces distribution gaps and…

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted…

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual…

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Designing for manufacturing poses significant challenges in part due to the computation bottleneck of Computer-Aided Manufacturing (CAM) simulations. Although deep learning as an alternative offers fast inference, its performance is…

Image and language modeling is of crucial importance for vision-language pre-training (VLP), which aims to learn multi-modal representations from large-scale paired image-text data. However, we observe that most existing VLP methods focus…

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segmentation (DGSS) holds unique challenges as the cross-domain…

Real-image super-resolution (Real-ISR) seeks to recover HR images from LR inputs with mixed, unknown degradations. While diffusion models surpass GANs in perceptual quality, they under-reconstruct high-frequency (HF) details due to a…

Existing continual relation learning (CRL) methods rely on plenty of labeled training data for learning a new task, which can be hard to acquire in real scenario as getting large and representative labeled data is often expensive and…

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…

Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual…

Logic-based machine learning aims to learn general, interpretable knowledge in a data-efficient manner. However, labelled data must be specified in a structured logical form. To address this limitation, we propose a neural-symbolic learning…