Related papers: Human-in-the-loop Adaptation in Group Activity Fea…

An appropriate reward function is of paramount importance in specifying a task in reinforcement learning (RL). Yet, it is known to be extremely challenging in practice to design a correct reward function for even simple tasks.…

Wearable robots offer a promising solution for quantitatively monitoring gait and providing systematic, adaptive assistance to promote patient independence and improve gait. However, due to significant interpersonal and intrapersonal…

In group activity recognition, hierarchical framework is widely adopted to represent the relationships between individuals and their corresponding group, and has achieved promising performance. However, the existing methods simply employed…

Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between…

Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to…

Modern AI algorithms require labeled data. In real world, majority of data are unlabeled. Labeling the data are costly. this is particularly true for some areas requiring special skills, such as reading radiology images by physicians. To…

Video generation models have recently achieved impressive visual fidelity and temporal coherence. Yet, they continue to struggle with complex, non-rigid motions, especially when synthesizing humans performing dynamic actions such as sports,…

Designing a scheme that can achieve a good performance in predicting single person activities and group activities is a challenging task. In this paper, we propose a novel robust and efficient human activity recognition scheme called ReHAR,…

This paper proposes dynamic human group detection in videos. For detecting complex groups, not only the local appearance features of in-group members but also the global context of the scene are important. Such local and global appearance…

Integrating human expertise into machine learning systems often reduces the role of experts to labeling oracles, a paradigm that limits the amount of information exchanged and fails to capture the nuances of human judgment. We address this…

Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate…

Research on Inverse Reinforcement Learning (IRL) from third-person videos has shown encouraging results on removing the need for manual reward design for robotic tasks. However, most prior works are still limited by training from a…

Time series forecasting models often produce systematic, predictable errors even in critical domains such as energy, finance, and healthcare. We introduce a novel post training adaptive optimization framework that improves forecast accuracy…

Person re-identification is an important task in video surveillance that aims to associate people across camera views at different locations and time. View variability is always a challenging problem seriously degrading person…

Autonomous driving systems require huge amounts of data to train. Manual annotation of this data is time-consuming and prohibitively expensive since it involves human resources. Therefore, active learning emerged as an alternative to ease…

Video generation has achieved significant advances through rectified flow techniques, but issues like unsmooth motion and misalignment between videos and prompts persist. In this work, we develop a systematic pipeline that harnesses human…

Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF…

High-quality human annotations are necessary for creating effective machine learning-driven stream processing systems. We study hybrid stream processing systems based on a Human-In-The-Loop Machine Learning (HITL-ML) paradigm, in which one…

We introduce the task of human action anomaly detection (HAAD), which aims to identify anomalous motions in an unsupervised manner given only the pre-determined normal category of training action samples. Compared to prior human-related…

Modern video recommendation systems aim to optimize user engagement and platform objectives, yet often face structural exposure imbalances caused by behavioral biases. In this work, we focus on the post-ranking stage and present LAFB…