Related papers: HAVIR: HierArchical Vision to Image Reconstruction…

Many image restoration (IR) tasks require both pixel-level fidelity and high-level semantic understanding to recover realistic photos with fine-grained details. However, previous approaches often struggle to effectively leverage both the…

The task of multi-label image classification involves recognizing multiple objects within a single image. Considering both valuable semantic information contained in the labels and essential visual features presented in the image, tight…

Understanding how the brain encodes visual information is a central challenge in neuroscience and machine learning. A promising approach is to reconstruct visual stimuli, essentially images, from functional Magnetic Resonance Imaging (fMRI)…

Text-Aware Image Restoration (TAIR) aims to recover high-quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong generative priors for general image restoration, they often produce…

This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant…

The success of CLIP has driven substantial progress in text-video retrieval. However, current methods often suffer from "blind" feature interaction, where the model struggles to discern key visual information from background noise due to…

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…

Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches focus primarily on image features, revealing limitations in…

As the boosting development of large vision-language models like Contrastive Language-Image Pre-training (CLIP), many CLIP-like methods have shown impressive abilities on visual recognition, especially in low-data regimes scenes. However,…

Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input…

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…

To address the limitations of existing open-vocabulary object recognition methods, specifically high system complexity, substantial training costs, and limited generalization, this paper proposes a novel Open-Vocabulary Object Recognition…

Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their…

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding.…

Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single stage, achieving only marginal gains over initial baseline.…

Most existing image restoration methods use neural networks to learn strong image-level priors from huge data to estimate the lost information. However, these works still struggle in cases when images have severe information deficits.…

Extending CLIP models to semantic segmentation remains challenging due to the misalignment between their image-level pre-training objectives and the pixel-level visual understanding required for dense prediction. While prior efforts have…

In neuroscience, all kinds of computation models were designed to answer the open question of how sensory stimuli are encoded by neurons and conversely, how sensory stimuli can be decoded from neuronal activities. Especially, functional…

Existing Visual Language Models (VLMs) suffer structural limitations where a few low contribution tokens may excessively capture global semantics, dominating the information aggregation process and suppressing the discriminative features in…

While image dehazing has advanced substantially in the past decade, most efforts have focused on short-range scenarios, leaving long-range haze removal under-explored. As distance increases, intensified scattering leads to severe haze and…