Related papers: PAT: Position-Aware Transformer for Dense Multi-La…

Over the past decade, Deep Convolutional Neural Networks have been widely adopted for medical image segmentation and shown to achieve adequate performance. However, due to the inherent inductive biases present in the convolutional…

Persistent monitoring of dynamic targets is essential in real-world applications such as disaster response, environmental sensing, and wildlife conservation, where mobile agents must continuously gather information under uncertainty. We…

Multi-agent reinforcement learning focuses on training the behaviors of multiple learning agents that coexist in a shared environment. Recently, MARL models, such as the Multi-Agent Transformer (MAT) and ACtion dEpendent deep Q-learning…

Due to the cost of labeling nodes, classifying a node in a sparsely labeled graph while maintaining the prediction accuracy deserves attention. The key point is how the algorithm learns sufficient information from more neighbors with…

Recognizing human activities from multi-channel time series data collected from wearable sensors is ever more practical. However, in real-world conditions, coherent activities and body movements could happen at the same time, like moving…

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant…

Image super-resolution (SR) has significantly advanced through the adoption of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent…

Actions are more than just movements and trajectories: we cook to eat and we hold a cup to drink from it. A thorough understanding of videos requires going beyond appearance modeling and necessitates reasoning about the sequence of…

Modeling dynamic temporal dependencies is a critical challenge in time series pre-training, which evolve due to distribution shifts and multi-scale patterns. This temporal variability severely impairs the generalization of pre-trained…

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer…

Leveraging vast amounts of unlabeled internet video data for embodied AI is currently bottlenecked by the lack of action labels and the presence of action-correlated visual distractors. Although recent latent action policy optimization…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

Cyber attacks are often identified using system and network logs. There have been significant prior works that utilize provenance graphs and ML techniques to detect attacks, specifically advanced persistent threats, which are very difficult…

Action localization networks are often structured as a feature encoder sub-network and a localization sub-network, where the feature encoder learns to transform an input video to features that are useful for the localization sub-network to…

To support the modern machine-type communications, a crucial task during the random access phase is device activity detection, which is to detect the active devices from a large number of potential devices based on the received signal at…

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take…

In the field of autonomous driving, there have been many excellent perception models for object detection, semantic segmentation, and other tasks, but how can we effectively use the perception models for vehicle planning? Traditional…

Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference,…

Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical…

Pretrained foundation models and transformer architectures have driven the success of large language models (LLMs) and other modern AI breakthroughs. However, similar advancements in health data modeling remain limited due to the need for…