Related papers: CSI: Contrastive Data Stratification for Interacti…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Many applications require linking individuals, firms, or locations across datasets. Most widely used methods, especially in social science, do not employ deep learning, with record linkage commonly approached using string matching…

Detecting feature interactions is imperative for accurately predicting performance of highly-configurable systems. State-of-the-art performance prediction techniques rely on supervised machine learning for detecting feature interactions,…

Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal…

Recommending cold-start items is a long-standing and fundamental challenge in recommender systems. Without any historical interaction on cold-start items, CF scheme fails to use collaborative signals to infer user preference on these items.…

We generalize the theory of supervised contrastive learning, previously applied to physical systems at equilibrium or steady state, to systems following any dynamics described by coupled ordinary differential equations. We show that if…

We focus on the problem of segmenting a certain object referred by a natural language sentence in video content, at the core of formulating a pinpoint vision-language relation. While existing attempts mainly construct such relation in an…

Achieving high-performance in multi-object tracking algorithms heavily relies on modeling spatio-temporal relationships during the data association stage. Mainstream approaches encompass rule-based and deep learning-based methods for…

The identification of compound-protein interactions (CPI) plays a critical role in drug screening, drug repurposing, and combination therapy studies. The effectiveness of CPI prediction relies heavily on the features extracted from both…

As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the…

Collaborative learning enables distributed clients to learn a shared model for prediction while keeping the training data local on each client. However, existing collaborative learning methods require fully-labeled data for training, which…

Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based…

User representation is essential for providing high-quality commercial services in industry. Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model…

Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for…

Identifying unique characteristics in a network through comparison with another network is an essential network analysis task. For example, with networks of protein interactions obtained from normal and cancer tissues, we can discover…

Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an…

Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements. Meanwhile, contrastive learning has been an effective…

Self-supervised representation learning has achieved impressive empirical success, yet its theoretical understanding remains limited. In this work, we provide a theoretical perspective by formulating self-supervised representation learning…

To understand the visual world, a machine must not only recognize individual object instances but also how they interact. Humans are often at the center of such interactions and detecting human-object interactions is an important practical…