Related papers: Cross-Modal Implicit Relation Reasoning and Aligni…
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims at learning modality-invariant features from unlabeled cross-modality dataset, which is crucial for practical applications in video surveillance systems. The…
In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To overcome these challenges, we introduce a novel Visual…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…
Recent advances in image understanding have enabled methods that leverage large language models for multimodal reasoning in remote sensing. However, existing approaches still struggle to steer models to the user-relevant regions when only…
Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language models (VLMs) excel in logical reasoning and multi-task…
Recent multimodal retrieval methods have endowed text-based retrievers with multimodal capabilities by utilizing pre-training strategies for visual-text alignment. They often directly fuse the two modalities for cross-reference during the…
Current multimodal large language models (MLLMs) face a critical challenge in modality alignment, often exhibiting a bias towards textual information at the expense of other modalities like vision. This paper conducts a systematic…
Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…
Given the remarkable success that large visual language models (LVLMs) have achieved in image perception tasks, the endeavor to make LVLMs perceive the world like humans is drawing increasing attention. Current multi-modal benchmarks…
Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic gap between the two modalities, previous studies mainly focus…
Traditional cross-modal retrieval assumes explicit association of concepts across modalities, where there is no ambiguity in how the concepts are linked to each other, e.g., when we do the image search with a query "dogs", we expect to see…
Cross-Modal sponsored search displays multi-modal advertisements (ads) when consumers look for desired products by natural language queries in search engines. Since multi-modal ads bring complementary details for query-ads matching, the…
The development of image time series retrieval (ITSR) methods is a growing research interest in remote sensing (RS). Given a user-defined image time series (i.e., the query time series), ITSR methods search and retrieve from large archives…
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.…
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…
For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…
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…
In recent years, multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets, enabling them to generally understand images well. However, the inherent difficulty in explicitly…
Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of…
Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…