Related papers: M-PACT: An Open Source Platform for Repeatable Act…
Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective may inadvertently compromise the performance of another. A…
Skeleton-based human action recognition is a longstanding challenge due to its complex dynamics. Some fine-grain details of the dynamics play a vital role in classification. The existing work largely focuses on designing incremental neural…
Addressing the large distribution gap between training and testing data has long been a challenge in machine learning, giving rise to fields such as transfer learning and domain adaptation. Recently, Continuous Domain Adaptation (CDA) has…
Modern multi-object tracking (MOT) systems usually model the trajectories by associating per-frame detections. However, when camera motion, fast motion, and occlusion challenges occur, it is difficult to ensure long-range tracking or even…
Current gait recognition methodologies generally necessitate retraining when encountering new datasets. Nevertheless, retrained models frequently encounter difficulties in preserving knowledge from previous datasets, leading to a…
In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data. The second phase is…
Data-driven autonomous driving motion generation tasks are frequently impacted by the limitations of dataset size and the domain gap between datasets, which precludes their extensive application in real-world scenarios. To address this…
Open set recognition is an emerging research area that aims to simultaneously classify samples from predefined classes and identify the rest as 'unknown'. In this process, one of the key challenges is to reduce the risk of generalizing the…
We develop a three-component Model Predictive Control (MPC) algorithm to achieve output-reference tracking with prescribed performance for continuous-time nonlinear systems. One component is so-called funnel MPC, which achieves reference…
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a…
A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…
To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions…
Existing image-based activity understanding methods mainly adopt direct mapping, i.e. from image to activity concepts, which may encounter performance bottleneck since the huge gap. In light of this, we propose a new path: infer human part…
One of the main challenges in the Simultaneous Localization and Mapping (SLAM) loop closure problem is the recognition of previously visited places. In this work, we tackle the two main problems of real-time SLAM systems: 1) loop closure…
Next-basket recommendation considers the problem of recommending a set of items into the next basket that users will purchase as a whole. In this paper, we develop a novel mixed model with preferences, popularities and transitions (M2) for…
When applying LLMs to real-world enterprise operations, LLMs need to handle proprietary knowledge in small domains of specific operations ($\textbf{micro domains}$). A previous study shows micro domain-adaptive pre-training…
Dynamic multi-objective optimization problems (DMOPs) are widely accepted to be more challenging than stationary problems due to the time-dependent nature of the objective functions and/or constraints. Evaluation of purpose-built algorithms…
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…
Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses a straightforward learning context, wherein all data…
Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often…