Related papers: Weakly-supervised Temporal Path Representation Lea…

Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the…

Unsupervised (a.k.a. Self-supervised) representation learning (URL) has emerged as a new paradigm for time series analysis, because it has the ability to learn generalizable time series representation beneficial for many downstream tasks…

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

Survival analysis plays a crucial role in many healthcare decisions, where the risk prediction for the events of interest can support an informative outlook for a patient's medical journey. Given the existence of data censoring, an…

Road network and trajectory representation learning are essential for traffic systems since the learned representation can be directly used in various downstream tasks (e.g., traffic speed inference, and travel time estimation). However,…

Temporal Heterogeneous Networks play a crucial role in capturing the dynamics and heterogeneity inherent in various real-world complex systems, rendering them a noteworthy research avenue for link prediction. However, existing methods fail…

In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned through this paradigm, much is yet to be understood about how…

Sequential recommender systems identify user preferences from their past interactions to predict subsequent items optimally. Although traditional deep-learning-based models and modern transformer-based models in previous studies capture…

Anomaly detection in multi-variate time series (MVTS) data is a huge challenge as it requires simultaneous representation of long term temporal dependencies and correlations across multiple variables. More often, this is solved by breaking…

Discriminating the traversability of terrains is a crucial task for autonomous driving in off-road environments. However, it is challenging due to the diverse, ambiguous, and platform-specific nature of off-road traversability. In this…

Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary annotation. The crux of this task lies in locating each…

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the…

Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific…

Despite recent progress in reinforcement learning (RL) from raw pixel data, sample inefficiency continues to present a substantial obstacle. Prior works have attempted to address this challenge by creating self-supervised auxiliary tasks,…

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it…

Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the other hand, provides…

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…

As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to…