Related papers: Zero-Shot Satellite Image Retrieval through Joint …
Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains including product…
Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…
Conventional supervised climate downscaling struggles to generalize to Global Climate Models (GCMs) due to the lack of paired training data and inherent domain gaps relative to reanalysis. Meanwhile, current zero-shot methods suffer from…
Effectively and efficiently retrieving images from remote sensing databases is a critical challenge in the realm of remote sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages,…
In this work, we present a camera geopositioning system based on matching a query image against a database with panoramic images. For matching, our system uses memory vectors aggregated from global image descriptors based on convolutional…
Rapid situational awareness is critical in post-disaster response. While remote sensing damage assessment is evolving from pixel-level change detection to high-level semantic analysis, existing vision-language methodologies still struggle…
Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks -…
Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot generate-and-encode pipeline: a vision-language model first…
Generalizing metric monocular depth estimation presents a significant challenge due to its ill-posed nature, while the entanglement between camera parameters and depth amplifies issues further, hindering multi-dataset training and zero-shot…
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on text prompts, which is essential for applications such as robotics. However, existing 3DVG methods encounter two main challenges: first, they struggle to handle the…
Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic…
In the immediate aftermath of natural disasters, rapid situational awareness is critical. Traditionally, satellite observations are widely used to estimate damage extent. However, they lack the ground-level perspective essential for…
We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstructions require good camera coverage, but ground imagery is…
Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize unseen classes without labeled training data by exploiting semantic information, which contains knowledge between seen and unseen classes. Existing ZSL…
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to the cross-domain nature of sketches and photos, as well as the semantic gap between seen and unseen image distributions. Previous methods fine-tune pre-trained models…
This paper studies zero-shot object recognition using event camera data. Guided by CLIP, which is pre-trained on RGB images, existing approaches achieve zero-shot object recognition by optimizing embedding similarities between event data…
Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by…
Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieval systems fail to reflect this flexibility, relying on a fixed, monolithic metric that…
Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP,…
Accurate flood detection from visual data is a critical step toward improving disaster response and risk assessment, yet datasets for flood segmentation remain scarce due to the challenges of collecting and annotating large-scale imagery.…