Related papers: Mesoscopic Insights: Orchestrating Multi-scale & H…
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years. Researchers manage to boost clustering accuracy from different points of view. However, many state-of-the-art MVSC algorithms, typically…
We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby…
A key processing step in ground-based astronomy involves combining multiple noisy and blurry exposures to produce an image of the night sky with an improved signal-to-noise ratio. Typically, this is achieved via image coaddition, and can be…
We present a visual localization system that learns to estimate camera poses in the real world with the help of synthetic data. Despite significant progress in recent years, most learning-based approaches to visual localization target at a…
Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce…
Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. During the generative process, new samples (images) are generated from an unknown high-dimensional distribution.…
Interactive image restoration aims to restore images by adjusting several controlling coefficients, which determine the restoration strength. Existing methods are restricted in learning the controllable functions under the supervision of…
Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We…
The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in…
The deep convolutional neural networks have achieved significant improvements in accuracy and speed for single image super-resolution. However, as the depth of network grows, the information flow is weakened and the training becomes harder…
Multiple-instance Learning (MIL) is commonly used to undertake computational pathology (CPath) tasks, and the use of multi-scale patches allows diverse features across scales to be learned. Previous studies using multi-scale features in…
Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-specific and semantic features. In this paper, however, we…
Deploying transformer-based neural networks on resource-constrained edge devices presents a significant challenge. This challenge is often addressed through various techniques, such as low-rank approximation and mixed-precision…
Holographic cloud probes provide unprecedented information on cloud particle density, size and position. Each laser shot captures particles within a large volume, where images can be computationally refocused to determine particle size and…
Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible…
The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently…
Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…
Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dominant VLP models adopt a CNN-Transformer architecture, which…
Recent advances in image editing techniques have posed serious challenges to the trustworthiness of multimedia data, which drives the research of image tampering detection. In this paper, we propose ObjectFormer to detect and localize image…
Image set classification (ISC), which can be viewed as a task of comparing similarities between sets consisting of unordered heterogeneous images with variable quantities and qualities, has attracted growing research attention in recent…