Related papers: Cross-Modal Bidirectional Interaction Model for Re…
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more…
Video-based computer vision tasks can benefit from estimation of the salient regions and interactions between those regions. Traditionally, this has been done by identifying the object regions in the images by utilizing pre-trained models…
Referring Image Segmentation (RIS) aims to segment a target object described by a natural language expression. Existing methods have evolved by leveraging the vision information into the language tokens. To more effectively exploit visual…
The classical human-robot interface in uncalibrated image-based visual servoing (UIBVS) relies on either human annotations or semantic segmentation with categorical labels. Both methods fail to match natural human communication and convey…
The research community has witnessed the powerful potential of self-supervised Masked Image Modeling (MIM), which enables the models capable of learning visual representation from unlabeled data. In this paper, to incorporate both the…
Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing works mainly focus on alleviating the modality gap by aligning…
Image captioning and cross-modal retrieval are examples of tasks that involve the joint analysis of visual and linguistic information. In connection to remote sensing imagery, these tasks can help non-expert users in extracting relevant…
Within this work, we introduce LIMIS: The first purely language-based interactive medical image segmentation model. We achieve this by adapting Grounded SAM to the medical domain and designing a language-based model interaction strategy…
Medical image segmentation is more clinically valuable when it supports diagnosis rather than merely producing lesion masks. However, diagnostically relevant lesion cues are often subtle and localized, while existing models may be…
Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their…
As an important and challenging problem in vision-language tasks, referring expression comprehension (REC) generally requires a large amount of multi-grained information of visual and linguistic modalities to realize accurate reasoning. In…
While vision-language models like CLIP have shown remarkable success in open-vocabulary tasks, their application is currently confined to image-level tasks, and they still struggle with dense predictions. Recent works often attribute such…
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing. A large amount of multi-modal earth observation images, such as multispectral imagery (MSI) or synthetic aperture…
Multi-modal object Re-IDentification (ReID) is devoted to retrieving specific objects through the exploitation of complementary multi-modal image information. Existing methods mainly concentrate on the fusion of multi-modal features, yet…
Multimodal desire understanding, a task closely related to both emotion and sentiment that aims to infer human intentions from visual and textual cues, is an emerging yet underexplored task in affective computing with applications in social…
Remote sensing (RS) images from multiple modalities and platforms exhibit diverse details due to differences in sensor characteristics and imaging perspectives. Existing vision-language research in RS largely relies on relatively…
We introduce Referring 3D Gaussian Splatting Segmentation (R3DGS), a new task that aims to segment target objects in a 3D Gaussian scene based on natural language descriptions, which often contain spatial relationships or object attributes.…
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…
Multimodal semantic segmentation has shown great potential in leveraging complementary information across diverse sensing modalities. However, existing approaches often rely on carefully designed fusion strategies that either use…
Semantic segmentation is essential for analyzing highdefinition remote sensing images (HRSIs) because it allows the precise classification of objects and regions at the pixel level. However, remote sensing data present challenges owing to…