Related papers: Geometry-Aware CLIP Retrieval via Local Cross-Moda…

Modern reconstruction techniques can effectively model complex 3D scenes from sparse 2D views. However, automatically assessing the quality of novel views and identifying artifacts is challenging due to the lack of ground truth images and…

We consider the problem of composed image retrieval that takes an input query consisting of an image and a modification text indicating the desired changes to be made on the image and retrieves images that match these changes. Current…

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

Diffusion-based re-ranking is a common method used for retrieving instances by performing similarity propagation in a nearest neighbor graph. However, existing techniques that construct the affinity graph based on pairwise instances can…

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…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

Pixel-accurate tracking of objects is a key element in many computer vision applications, often solved by iterated individual object tracking or instance segmentation followed by object matching. Here we introduce cross-classification…

In the field of design patent analysis, traditional tasks such as patent classification and patent image retrieval heavily depend on the image data. However, patent images -- typically consisting of sketches with abstract and structural…

In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken. Existing two-stage approaches involve…

Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art performance at aligning visual and textual representations…

We investigate the success conditions for compositional generalization of CLIP models on real-world data through performance prediction. Prior work shows that CLIP requires exponentially more pretraining data for linear performance gains on…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Instance-level alignment is widely exploited for person re-identification, e.g. spatial alignment, latent semantic alignment and triplet alignment. This paper probes another feature alignment modality, namely cluster-level feature alignment…

Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept…

Place recognition is a challenging but crucial task in robotics. Current description-based methods may be limited by representation capabilities, while pairwise similarity-based methods require exhaustive searches, which is time-consuming.…

Beyond the success of Contrastive Language-Image Pre-training (CLIP), recent trends mark a shift toward exploring the applicability of lightweight vision-language models for resource-constrained scenarios. These models often deliver…

Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivial task due to appearance variations between similar poses…

Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers…

In this paper, we address the problem of global-scale image geolocation, proposing a mixed classification-retrieval scheme. Unlike other methods that strictly tackle the problem as a classification or retrieval task, we combine the two…

Benefiting from the inductive biases learned from large-scale datasets, open-vocabulary semantic segmentation (OVSS) leverages the power of vision-language models, such as CLIP, to achieve remarkable progress without requiring task-specific…