Asia
LearningLatentSeasonal-TrendRepresentationsfor TimeSeriesForecasting
However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components.
Self-supervised Object-Centric Learning for Videos Görkay Aydemir
From these temporally-aware slots, the training objective is to reconstruct the middle frame in a high-level semantic feature space. We propose a masking strategy by dropping a significant portion of tokens in the feature space for efficiency and regularization. Additionally, we address over-clustering by merging slots based on similarity.
Cross-Domain Transferability of Adversarial Perturbations
Muhammad Muzammal Naseer, Salman H. Khan, Muhammad Haris Khan, Fahad Shahbaz Khan, Fatih Porikli
Neural Information Processing Systems http://nips.cc/
Multi-domain Causal Structure Learning in Linear Systems
AmirEmad Ghassami, Negar Kiyavash, Biwei Huang, Kun Zhang
Neural Information Processing Systems http://nips.cc/
Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering
Ilias Diakonikolas, Daniel Kane, Sushrut Karmalkar, Eric Price, Alistair Stewart
Neural Information Processing Systems http://nips.cc/
ATransformer-BasedObjectDetectorwith Coarse-FineCrossingRepresentations
Compared with convolutional neural networks limited bytherelativelysmall receptive fields, the advantage of transformer for visual tasks is the capacity to perceivelong-range dependencies amongallimagepatches,whilethedeficiency is that the local fine-grained information is not fully excavated.