Related papers: FiCo-ITR: bridging fine-grained and coarse-grained…

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the problem of retrieving a particular photo instance given a user's query sketch. Its widespread applicability is however hindered by the fact that drawing a sketch takes time,…

Cross-view geo-localization is a promising solution for large-scale localization problems, requiring the sequential execution of retrieval and metric localization tasks to achieve fine-grained predictions. However, existing methods…

High-quality annotation of fine-grained visual categories demands great expert knowledge, which is taxing and time consuming. Alternatively, learning fine-grained visual representation from enormous unlabeled images (e.g., species, brands)…

Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge. Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) addresses these issues by grounding LLM…

Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…

Fine-grained recognition distinguishes among categories with subtle visual differences. In order to differentiate between these challenging visual categories, it is helpful to leverage additional information. Geolocation is a rich source of…

Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computation cost mainly from…

In-Context Learning (ICL) enables Large Language Models (LLMs) to perform new tasks by conditioning on prompts with relevant information. Retrieval-Augmented Generation (RAG) enhances ICL by incorporating retrieved documents into the LLM's…

With the rapid development of OCR technology, mixed-scene text recognition has become a key technical challenge. Although deep learning models have achieved significant results in specific scenarios, their generality and stability still…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conventiona RAG systems under-perform on structured tabular data, largely due to coarse…

Retrieving relevant images from a catalog based on a query image together with a modifying caption is a challenging multimodal task that can particularly benefit domains like apparel shopping, where fine details and subtle variations may be…

The advent of text-image models, most notably CLIP, has significantly transformed the landscape of information retrieval. These models enable the fusion of various modalities, such as text and images. One significant outcome of CLIP is its…

Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe that accuracy gains often come at the cost of reasoning…

Ultra-fine-grained image recognition (UFGIR) is a challenging task that involves classifying images within a macro-category. While traditional FGIR deals with classifying different species, UFGIR goes beyond by classifying sub-categories…

Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity. In this paper, we investigate a new…

Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained…

One of the challenges in Content-Based Image Retrieval (CBIR) is to reduce the semantic gaps between low-level features and high-level semantic concepts. In CBIR, the images are represented in the feature space and the performance of CBIR…

Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to…

Recent vision-language models outperform vision-only models on many image classification tasks. However, because of the absence of paired text/image descriptions, it remains difficult to fine-tune these models for fine-grained image…

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…