Contrastive clustering
In this paper, we propose an online clustering method called Contrastive Clustering (CC)
which explicitly performs the instance-and cluster-level contrastive learning. To be specific …
which explicitly performs the instance-and cluster-level contrastive learning. To be specific …
Unsupervised representation learning for time series: A review
Unsupervised representation learning approaches aim to learn discriminative feature
representations from unlabeled data, without the requirement of annotating every sample …
representations from unlabeled data, without the requirement of annotating every sample …
TEST: Text prototype aligned embedding to activate LLM's ability for time series
This work summarizes two strategies for completing time-series (TS) tasks using today's
language model (LLM): LLM-for-TS, design and train a fundamental large model for TS data; …
language model (LLM): LLM-for-TS, design and train a fundamental large model for TS data; …
Vi2clr: Video and image for visual contrastive learning of representation
In this paper, we introduce a novel self-supervised visual representation learning method
which understands both images and videos in a joint learning fashion. The proposed neural …
which understands both images and videos in a joint learning fashion. The proposed neural …
MHCCL: masked hierarchical cluster-wise contrastive learning for multivariate time series
Learning semantic-rich representations from raw unlabeled time series data is critical for
downstream tasks such as classification and forecasting. Contrastive learning has recently …
downstream tasks such as classification and forecasting. Contrastive learning has recently …
Large scale holistic video understanding
Video recognition has been advanced in recent years by benchmarks with rich annotations.
However, research is still mainly limited to human action or sports recognition-focusing on a …
However, research is still mainly limited to human action or sports recognition-focusing on a …
Crs-cont: a well-trained general encoder for facial expression analysis
Existing facial expression recognition (FER) methods train encoders with different large-
scale training data for specific FER applications. In this paper, we propose a new task in this …
scale training data for specific FER applications. In this paper, we propose a new task in this …
Slic: Self-supervised learning with iterative clustering for human action videos
SH Khorasgani, Y Chen… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Self-supervised methods have significantly closed the gap with end-to-end supervised
learning for image classification [13, 24]. In the case of human action videos, however …
learning for image classification [13, 24]. In the case of human action videos, however …
Graph contrastive partial multi-view clustering
With the diversity of information acquisition, data is stored and transmitted in an increasing
number of modalities. Nevertheless, it is not unusual for parts of the data to be lost in some …
number of modalities. Nevertheless, it is not unusual for parts of the data to be lost in some …
Clusterscl: Cluster-aware supervised contrastive learning on graphs
We study the problem of supervised contrastive (SupCon) learning on graphs. The SupCon
loss has been recently proposed for classification tasks by pulling data points in the same …
loss has been recently proposed for classification tasks by pulling data points in the same …