Related papers: MICO: A Multi-alternative Contrastive Learning Fra…
Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…
Multi-modal pre-training and knowledge discovery are two important research topics in multi-modal machine learning. Nevertheless, none of existing works make attempts to link knowledge discovery with knowledge guided multi-modal…
Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…
Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive…
Learning multi-label image recognition with incomplete annotation is gaining popularity due to its superior performance and significant labor savings when compared to training with fully labeled datasets. Existing literature mainly focuses…
Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of…
Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…
Many contrastive and meta-learning approaches learn representations by identifying common features in multiple views. However, the formalism for these approaches generally assumes features to be shared across views to be captured…
Generative commonsense reasoning refers to the task of generating acceptable and logical assumptions about everyday situations based on commonsense understanding. By utilizing an existing dataset such as Korean CommonGen, language…
In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited…
Unsupervised representation learning with contrastive learning achieved great success. This line of methods duplicate each training batch to construct contrastive pairs, making each training batch and its augmented version forwarded…
A comprehensive knowledge graph (KG) contains an instance-level entity graph and an ontology-level concept graph. The two-view KG provides a testbed for models to "simulate" human's abilities on knowledge abstraction, concretization, and…
This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contribute a structured collection of hand images, well suited…
To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations.…
Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive learning process in GCL is performed on top of the…
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…
Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We…
Human understanding of narrative texts requires making commonsense inferences beyond what is stated explicitly in the text. A recent model, COMET, can generate such implicit commonsense inferences along several dimensions such as pre- and…
The task of video-based commonsense captioning aims to generate event-wise captions and meanwhile provide multiple commonsense descriptions (e.g., attribute, effect and intention) about the underlying event in the video. Prior works explore…