Related papers: Locality-Aware Inter-and Intra-Video Reconstructio…
Automatic radiology report generation has attracted enormous research interest due to its practical value in reducing the workload of radiologists. However, simultaneously establishing global correspondences between the image (e.g., Chest…
Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate…
Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…
Recent single image unsupervised representation learning techniques show remarkable success on a variety of tasks. The basic principle in these works is instance discrimination: learning to differentiate between two augmented versions of…
Contrastive self-supervised learning has been successfully used in many domains, such as images, texts, graphs, etc., to learn features without requiring label information. In this paper, we propose a new local contrastive feature learning…
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…
Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail…
Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. However, current methods assume i.i.d. image acquisition, which…
Accurate reconstruction of both the geometric and topological details of a 3D object from a single 2D image embodies a fundamental challenge in computer vision. Existing explicit/implicit solutions to this problem struggle to recover…
Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry. We avoid all such supervision and assumptions by…
Magnetic Resonance Imaging (MRI) is an important medical imaging modality, while it requires a long acquisition time. To reduce the acquisition time, various methods have been proposed. However, these methods failed to reconstruct images…
Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of…
Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for…
The task of composed image retrieval (CIR) aims to retrieve images based on the query image and the text describing the users' intent. Existing methods have made great progress with the advanced large vision-language (VL) model in CIR task,…
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank.…
An accurate understanding of omnidirectional environment lighting is crucial for high-quality virtual object rendering in mobile augmented reality (AR). In particular, to support reflective rendering, existing methods have leveraged deep…
Using natural language to query visual information is a fundamental need in real-world applications. Text-Image Retrieval (TIR) retrieves a target image from a gallery based on an image-level description, while Referring Expression…
Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…
We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: a…