Related papers: STMI: Segmentation-Guided Token Modulation with Cr…
Cross-modal retrieval aims to retrieve relevant data across different modalities (e.g., texts vs. images). The common strategy is to apply element-wise constraints between manually labeled pair-wise items to guide the generators to learn…
Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality…
A key challenge in visible-infrared person re-identification (V-I ReID) is training a backbone model capable of effectively addressing the significant discrepancies across modalities. State-of-the-art methods that generate a single…
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived…
Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible…
Multimodal Large Language Models (MLLMs) face significant computational overhead when processing long videos due to the massive number of visual tokens required. To improve efficiency, existing methods primarily reduce redundancy by pruning…
Although deep learning has advanced remote sensing change detection (RSCD), most methods rely solely on image modality, limiting feature representation, change pattern modeling, and generalization especially under illumination and noise…
Currently, most low-light image enhancement methods only consider information from a single view, neglecting the correlation between cross-view information. Therefore, the enhancement results produced by these methods are often…
RGB-Infrared (IR) cross-modality person re-identification (re-ID), which aims to search an IR image in RGB gallery or vice versa, is a challenging task due to the large discrepancy between IR and RGB modalities. Existing methods address…
Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer…
Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additional visual modalities to enhance robustness through complementary information. However,…
Understanding high-resolution (HR) images remains a critical challenge for multimodal large language models (MLLMs). Recent approaches leverage vision-based retrieval-augmented generation (RAG) to retrieve query-relevant crops from HR…
Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information.…
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation. Given the significant gap across visible and infrared modality, estimating…
Multimodal foundation models can process several modalities. However, since the space of possible modalities is large and evolving over time, training a model from scratch to encompass all modalities is unfeasible. Moreover, integrating a…
Image retrieval with hybrid-modality queries, also known as composing text and image for image retrieval (CTI-IR), is a retrieval task where the search intention is expressed in a more complex query format, involving both vision and text…
We address the problem of referring image segmentation that aims to generate a mask for the object specified by a natural language expression. Many recent works utilize Transformer to extract features for the target object by aggregating…
Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the…
Referring remote sensing image segmentation (RRSIS) is a novel visual task in remote sensing images segmentation, which aims to segment objects based on a given text description, with great significance in practical application. Previous…
Re-identification (ReID) is to identify the same instance across different cameras. Existing ReID methods mostly utilize alignment-based or attention-based strategies to generate effective feature representations. However, most of these…