Related papers: Dynamic Sub-region Search in Homogeneous Collectio…
Obtaining semantic labels on a large scale radiology image database (215,786 key images from 61,845 unique patients) is a prerequisite yet bottleneck to train highly effective deep convolutional neural network (CNN) models for image…
Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…
Underwater surveys provide long-term data for informing management strategies, monitoring coral reef health, and estimating blue carbon stocks. Advances in broad-scale survey methods, such as robotic underwater vehicles, have increased the…
High-dimensional similarity search underpins modern retrieval systems, yet uniform search strategies fail to exploit the heterogeneous nature of real-world query distributions. We present an adaptive prefiltering framework that leverages…
In recent years, video semantic segmentation has made great progress with advanced deep neural networks. However, there still exist two main challenges \ie, information inconsistency and computation cost. To deal with the two difficulties,…
Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…
While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and…
Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…
Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology. We leverage the evolving nature of images…
Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine…
Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…
Ambiguity poses persistent challenges in natural language understanding for large language models (LLMs). To better understand how lexical ambiguity can be resolved through the visual domain, we develop an interpretable Visual Word Sense…
We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich…
Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many…
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…
This paper attempts to discuss the evolution of the retrieval approaches focusing on development, challenges and future direction of the image retrieval. It highlights both the already addressed and outstanding issues. The explosive growth…
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. There has been considerable research on generating efficient image representation via the deep-network-based hashing…
Climate change's destruction of marine biodiversity is threatening communities and economies around the world which rely on healthy oceans for their livelihoods. The challenge of applying computer vision to niche, real-world domains such as…
We address the problem of segmenting an object given a natural language expression that describes it. Current techniques tackle this task by either (\textit{i}) directly or recursively merging linguistic and visual information in the…
We study the problem of deep recall model in industrial web search, which is, given a user query, retrieve hundreds of most relevance documents from billions of candidates. The common framework is to train two encoding models based on…