Related papers: Heterogeneous co-occurrence embedding for visual i…
Standard dual-encoder vision-language models that map images and text to deterministic points on a shared unit hypersphere through $\ell_2$ normalization typically expose neither \emph{aleatoric} uncertainty (cross-modal ambiguity) nor…
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from…
In Computer Vision, edge detection is one of the favored approaches for feature and object detection in images since it provides information about their objects boundaries. Other region-based approaches use probabilistic analysis such as…
Domain adaptation aims to assist the modeling tasks of the target domain with knowledge of the source domain. The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging…
Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning…
The prosperous development of e-commerce has spawned diverse recommendation systems. As a matter of fact, there exist rich and complex interactions among various types of nodes in real-world recommendation systems, which can be constructed…
Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials…
The meaning of a word often varies depending on its usage in different domains. The standard word embedding models struggle to represent this variation, as they learn a single global representation for a word. We propose a method to learn…
An important task in visualization is the extraction and highlighting of dominant features in data to support users in their analysis process. Topological methods are a well-known means of identifying such features in deterministic fields.…
Most real-world data can be modeled as heterogeneous information networks (HINs) consisting of vertices of multiple types and their relationships. Search for similar vertices of the same type in large HINs, such as bibliographic networks…
Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative. By transforming unsupervised learning problems into decompositions of co-occurrence statistics, spectral algorithms provide…
In the past few years, augmented reality (AR) and virtual reality (VR) technologies have experienced terrific improvements in both accessibility and hardware capabilities, encouraging the application of these devices across various domains.…
Structuring latent representations in a hierarchical manner enables models to learn patterns at multiple levels of abstraction. However, most prevalent image understanding models focus on visual similarity, and learning visual hierarchies…
The use of high-dimensional features has become a normal practice in many computer vision applications. The large dimension of these features is a limiting factor upon the number of data points which may be effectively stored and processed,…
Music retrieval and recommendation applications often rely on content features encoded as embeddings, which provide vector representations of items in a music dataset. Numerous complementary embeddings can be derived from processing items…
Heterogeneous information networks (HINs) are ubiquitous in real-world applications. Due to the heterogeneity in HINs, the typed edges may not fully align with each other. In order to capture the semantic subtlety, we propose the concept of…
Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual…
Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set…
Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurrence among attributes. Considering that this known a prior is highly variable and unforeseeable regarding the specific…
We propose a novel method for multiple clustering that assumes a co-clustering structure (partitions in both rows and columns of the data matrix) in each view. The new method is applicable to high-dimensional data. It is based on a…