Related papers: Deep Joint Embeddings of Context and Content for R…

Contrastive learning is widely used for sentence representation learning. Despite this prevalence, most studies have focused exclusively on English and few concern domain adaptation for domain-specific downstream tasks, especially for…

As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing…

Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…

Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted…

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…

Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by constructing and explaining their predictions using a set of high-level concepts. A special property of these models is that they permit concept interventions,…

Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…

With the tremendous growth in the number of scientific papers being published, searching for references while writing a scientific paper is a time-consuming process. A technique that could add a reference citation at the appropriate place…

A comprehensive artificial intelligence system needs to not only perceive the environment with different `senses' (e.g., seeing and hearing) but also infer the world's conditional (or even causal) relations and corresponding uncertainty.…

Joint caching and recommendation has been recently proposed as a new paradigm for increasing the efficiency of mobile edge caching. Early findings demonstrate significant gains for the network performance. However, previous works evaluated…

Automatic art analysis aims to classify and retrieve artistic representations from a collection of images by using computer vision and machine learning techniques. In this work, we propose to enhance visual representations from neural…

Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of…

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to…

This paper describes two approaches for content-based image retrieval and pattern spotting in document images using deep learning. The first approach uses a pre-trained CNN model to cope with the lack of training data, which is fine-tuned…

Social network platforms can use the data produced by their users to serve them better. One of the services these platforms provide is recommendation service. Recommendation systems can predict the future preferences of users using their…

Recommender systems are widely used to help people find items that are tailored to their interests. These interests are often influenced by social networks, making it important to use social network information effectively in recommender…

We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…

This dissertation establishes the contexture theory to mathematically characterize the mechanism of representation learning, or pretraining. Despite the remarkable empirical success of foundation models, it is not very clear what…

Quizlet is the most popular online learning tool in the United States, and is used by over 2/3 of high school students, and 1/2 of college students. With more than 95% of Quizlet users reporting improved grades as a result, the platform has…

Semantic segmentation of outdoor scenes is problematic when there are variations in imaging conditions. It is known that albedo (reflectance) is invariant to all kinds of illumination effects. Thus, using reflectance images for semantic…