Related papers: SECaps: A Sequence Enhanced Capsule Model for Char…

Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-time deployment. In this paper, an optimized deep learning framework is proposed using a…

This paper proposes a self-explainable Deep Learning (SE-DL) system for an image classification problem that performs self-error detection. The self-error detection is key to improving the DL system's safe operation, especially in…

Accident anticipation aims to predict impending collisions from dashcam videos and trigger early alerts. Existing methods rely on binary supervision with manually annotated "anomaly onset" frames, which are subjective and inconsistent,…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Semi-supervised anomaly detection (AD) has shown great promise by effectively leveraging limited labeled data. However, existing methods are typically structured around scoring individual points or simple pairs. Such {point- or…

We present a general framework for compositional action recognition -- i.e. action recognition where the labels are composed out of simpler components such as subjects, atomic-actions and objects. The main challenge in compositional action…

Causal discovery is essential for advancing data-driven fields such as scientific AI and data analysis, yet existing approaches face significant time- and space-efficiency bottlenecks when scaling to large graphs. To address this challenge,…

Unsupervised learning of compact and relevant state representations has been proved very useful at solving complex reinforcement learning tasks. In this paper, we propose a recurrent capsule network that learns such representations by…

Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

This paper presents a new approach to statistical similarity assessment based on sequence alignment. The algorithm performs mutual matching of two random sequences by successively searching for common elements and by applying sequence…

The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…

The perception of motion behavior in a dynamic environment holds significant importance for autonomous driving systems, wherein class-agnostic motion prediction methods directly predict the motion of the entire point cloud. While most…

A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a…

Anticipating the future actions of a human is a widely studied problem in robotics that requires spatio-temporal reasoning. In this work we propose a deep learning approach for anticipation in sensory-rich robotics applications. We…

We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual cortex does not…

Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence…

In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds. Considering the impact of deep neural networks, state-of-the-art network architectures have…

The task of weakly supervised temporal action localization targets at generating temporal boundaries for actions of interest, meanwhile the action category should also be classified. Pseudo-label-based methods, which serve as an effective…

Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The quality of annotations tends to deteriorate with the transition…