Related papers: 1st Place Solution in Google Universal Images Embe…
Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…
Underwater image enhancement (UIE) presents a significant challenge within computer vision research. Despite the development of numerous UIE algorithms, a thorough and systematic review is still absent. To foster future advancements, we…
Fine-grained multi-label classification models have broad applications in e-commerce, such as visual based label predictions ranging from fashion attribute detection to brand recognition. One challenge to achieve satisfactory performance…
Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We consider an occluded point to be one that is imaged in the first frame but not in the next, a slight overloading of the standard definition…
This paper presents our 7th place solution to the second YouTube-8M video understanding competition which challenges participates to build a constrained-size model to classify millions of YouTube videos into thousands of classes. Our final…
Motivated by recent work on ordinal embedding (Kleindessner and von Luxburg, 2014), we derive large sample consistency results and rates of convergence for the problem of embedding points based on triple or quadruple distance comparisons.…
A significant challenge in object detection is accurate identification of an object's position in image space, whereas one algorithm with one set of parameters is usually not enough, and the fusion of multiple algorithms and/or parameters…
Heterogeneous graphs (HGs) also known as heterogeneous information networks have become ubiquitous in real-world scenarios; therefore, HG embedding, which aims to learn representations in a lower-dimension space while preserving the…
In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM)…
Given a collection of $m$ sets from a universe $\mathcal{U}$, the Maximum Set Coverage problem consists of finding $k$ sets whose union has largest cardinality. This problem is NP-Hard, but the solution can be approximated by a polynomial…
Image Matching Challenge 2024 is a competition focused on building 3D maps from diverse image sets, requiring participants to solve fundamental computer vision challenges in image matching across varying angles, lighting, and seasonal…
Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…
Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline…
The goal of this paper is to retrieve an image based on instance, attribute and category similarity notions. Different from existing works, which usually address only one of these entities in isolation, we introduce a cooperative embedding…
In vision transformers, position embedding (PE) plays a crucial role in capturing the order of tokens. However, in vision transformer structures, there is a limitation in the expressiveness of PE due to the structure where position…
Image Retrieval is a fundamental task of obtaining images similar to the query one from a database. A common image retrieval practice is to firstly retrieve candidate images via similarity search using global image features and then re-rank…
Recent work in image processing suggests that operating on (overlapping) patches in an image may lead to state-of-the-art results. This has been demonstrated for a variety of problems including denoising, inpainting, deblurring, and…
Ensembling is a method that aims to maximize the detection performance by fusing individual detectors. While rarely mentioned in deep-learning articles applied to remote sensing, ensembling methods have been widely used to achieve high…
We resolve a longstanding open problem by reformulating the Grassmannian fusion frames to the case of mixed dimensions and show that this satisfies the proper properties for the problem. In order to compare elements of mixed dimension, we…
Text embeddings are essential for many tasks, such as document retrieval, clustering, and semantic similarity assessment. In this paper, we study how to contrastively train text embedding models in a compute-optimal fashion, given a suite…