Related papers: iEBAKER: Improved Remote Sensing Image-Text Retrie…
Recent advances in image editing have heightened the need for reliable Image Editing Quality Assessment (IEQA). Unlike traditional methods, IEQA requires complex reasoning over multimodal inputs and multi-dimensional assessments. Existing…
Remote sensing cross-modal text-image retrieval (RSCTIR) has gained attention for its utility in information mining. However, challenges remain in effectively integrating global and local information due to variations in remote sensing…
With the proliferation of images in online content, language-guided image retrieval (LGIR) has emerged as a research hotspot over the past decade, encompassing a variety of subtasks with diverse input forms. While the development of large…
Pairwise image quality assessment (IQA) in professional photography requires a model not only to identify the preferred image between two candidates, but also to provide convincing and image-grounded reasoning. In the NTIRE 2026 RAIM…
This work is to develop a general framework, namely analytical iterative reconstruction (AIR) method, to incorporate analytical reconstruction (AR) method into iterative reconstruction (IR) method, for enhanced CT image quality and…
Despite the evolution of deep-learning-based visual-textual processing systems, precise multi-modal matching remains a challenging task. In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on…
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representation (INR)-based approaches: it avoids quantization and enables…
Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly reducing the labor-intensive annotation process. Despite…
Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes…
Remote sensing imagery has attracted significant attention in recent years due to its instrumental role in global environmental monitoring, land usage monitoring, and more. As image databases grow each year, performing automatic…
Image-text retrieval is a widely studied topic in the field of computer vision due to the exponential growth of multimedia data, whose core concept is to measure the similarity between images and text. However, most existing retrieval…
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many…
Remote sensing (RS) images are usually stored in compressed format to reduce the storage size of the archives. Thus, existing content-based image retrieval (CBIR) systems in RS require decoding images before applying CBIR (which is…
As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cover all the potential biased features. In this paper, we…
The Tsetlin Machine (TM) has gained significant attention in Machine Learning (ML). By employing logical fundamentals, it facilitates pattern learning and representation, offering an alternative approach for developing comprehensible…
Semantic text matching is a critical problem in information retrieval. Recently, deep learning techniques have been widely used in this area and obtained significant performance improvements. However, most models are black boxes and it is…
Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due…
Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream…
Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish…
Entity Resolution (ER) is typically implemented as a batch task that processes all available data before identifying duplicate records. However, applications with time or computational constraints, e.g., those running in the cloud, require…