相关论文: Lifelong Event Detection via Optimal Transport

Many learning tasks involve multi-modal data streams, where continuous data from different modes convey a comprehensive description about objects. A major challenge in this context is how to efficiently interpret multi-modal information in…

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting. Here we propose a novel method, SupportNet, to…

We study continual event extraction, which aims to extract incessantly emerging event information while avoiding forgetting. We observe that the semantic confusion on event types stems from the annotations of the same text being updated…

Due to their inference, data representation and reconstruction properties, Variational Autoencoders (VAE) have been successfully used in continual learning classification tasks. However, their ability to generate images with specifications…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Machine unlearning has become a crucial role in enabling generative models trained on large datasets to remove sensitive, private, or copyright-protected data. However, existing machine unlearning methods face three challenges in learning…

Event extraction (EE) is the task of identifying interested event mentions from text. Conventional efforts mainly focus on the supervised setting. However, these supervised models cannot generalize to event types out of the pre-defined…

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Event cameras have recently been shown beneficial for practical vision tasks, such as action recognition, thanks to their high temporal resolution, power efficiency, and reduced privacy concerns. However, current research is hindered by 1)…

Accurate trajectory prediction of vehicles is essential for reliable autonomous driving. To maintain consistent performance as a vehicle driving around different cities, it is crucial to adapt to changing traffic circumstances and achieve…

Electronic health record (EHR) data are increasingly used to support real-world evidence (RWE) studies. Yet its ability to generate reliable RWE is limited by the lack of readily available precise information on the timing of clinical…

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos. We define a super-event as a set of multiple events occurring together in…

Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for…

In this paper we propose MECAD, a novel approach for continual anomaly detection using a multi-expert architecture. Our system dynamically assigns experts to object classes based on feature similarity and employs efficient memory management…

Robust object detection for challenging scenarios increasingly relies on event cameras, yet existing Event-RGB datasets remain constrained by sparse coverage of extreme conditions and low spatial resolution (<= 640 x 480), which prevents…

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…

Lane segment topology reasoning provides comprehensive bird's-eye view (BEV) road scene understanding, which can serve as a key perception module in planning-oriented end-to-end autonomous driving systems. Existing lane topology reasoning…