Related papers: CycleCL: Self-supervised Learning for Periodic Vid…

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…

Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene. We approach this problem by learning a generative model for regular motion…

Learning universal time series representations applicable to various types of downstream tasks is challenging but valuable in real applications. Recently, researchers have attempted to leverage the success of self-supervised contrastive…

Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos,…

Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements. It can be a promising alternative to…

We present an approach that incorporates expert knowledge for time-series representation learning. Our method employs expert features to replace the commonly used data transformations in previous contrastive learning approaches. We do this…

Aligning video sequences is a fundamental yet still unsolved component for a broad range of applications in computer graphics and vision. Most classical image processing methods cannot be directly applied to related video problems due to…

This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding…

Time series widely exists in real-world applications and many deep learning models have performed well on it. Current research has shown the importance of learning strategy for models, suggesting that the benefit is the order and size of…

Monocular 3D reconstruction of articulated object categories is challenging due to the lack of training data and the inherent ill-posedness of the problem. In this work we use video self-supervision, forcing the consistency of consecutive…

Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection…

Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be…

Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings. However, unsupervised video anomaly detection methods are quite sparse, likely because anomalies are less frequent in occurrence…

Unpaired video-to-video translation aims to translate videos between a source and a target domain without the need of paired training data, making it more feasible for real applications. Unfortunately, the translated videos generally suffer…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training. In this work, we exploit an end-to-end Siamese…

What can we learn about a scene by watching it for months or years? A video recorded over a long timespan will depict interesting phenomena at multiple timescales, but identifying and viewing them presents a challenge. The video is too long…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

Disease diagnosis from medical images via supervised learning is usually dependent on tedious, error-prone, and costly image labeling by medical experts. Alternatively, semi-supervised learning and self-supervised learning offer…