Related papers: Graphical Contrastive Losses for Scene Graph Parsi…

Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph annotation or labeling, we face a severe graph label-scarcity…

Contrastive learning has recently achieved remarkable success in many domains including graphs. However contrastive loss, especially for graphs, requires a large number of negative samples which is unscalable and computationally prohibitive…

Gaze estimation methods commonly use facial appearances to predict the direction of a person gaze. However, previous studies show three major challenges with convolutional neural network (CNN)-based, transformer-based, and contrastive…

Graph Collaborative Filtering (GCF), one of the most widely adopted recommendation system methods, effectively captures intricate relationships between user and item interactions. Graph Contrastive Learning (GCL) based GCF has gained…

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize…

Graph Contrastive Learning (GCL) has emerged as a promising approach in the realm of graph self-supervised learning. Prevailing GCL methods mainly derive from the principles of contrastive learning in the field of computer vision: modeling…

Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

This paper describes an end-to-end solution for the relationship prediction task in heterogeneous, multi-relational graphs. We particularly address two building blocks in the pipeline, namely heterogeneous graph representation learning and…

In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations. Current…

Recent work has shown the potential of graph neural networks to efficiently predict material properties, enabling high-throughput screening of materials. Training these models, however, often requires large quantities of labelled data,…

Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different…

Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can…

Context-aware methods achieved great success in supervised scene text recognition via incorporating semantic priors from words. We argue that such prior contextual information can be interpreted as the relations of textual primitives due to…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

Recent works have widely explored the contextual dependencies to achieve more accurate segmentation results. However, most approaches rarely distinguish different types of contextual dependencies, which may pollute the scene understanding.…

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how…