Related papers: Dual-AI: Dual-path Actor Interaction Learning for …
Many semantic events in team sport activities e.g. basketball often involve both group activities and the outcome (score or not). Motion patterns can be an effective means to identify different activities. Global and local motions have…
In this paper, we efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. Previous adaptation methods have simultaneously…
Our goal is to transfer the motion of real people from a source video to a target video with realistic results. While recent advances significantly improved image-to-image translations, only few works account for body motions and temporal…
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications, due to non-interactivity between agents, curse of dimensionality and computation complexity. Hence, several…
Learning to coordinate actions among agents is essential in complicated multi-agent systems. Prior works are constrained mainly by the assumption that all agents act simultaneously, and asynchronous action coordination between agents is…
Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models often struggle with this temporal hierarchy, offering solutions…
With recent advancements in multi-agent generative AI (Gen AI), technology organizations like Microsoft are adopting these complex tools, redefining AI agents as active collaborators in complex workflows rather than as passive tools. In…
Creating realistic characters that can react to the users' or another character's movement can benefit computer graphics, games and virtual reality hugely. However, synthesizing such reactive motions in human-human interactions is a…
In open multi-agent environments, the agents may encounter unexpected teammates. Classical multi-agent learning approaches train agents that can only coordinate with seen teammates. Recent studies attempted to generate diverse teammates to…
Effective coordination and cooperation among agents are crucial for accomplishing individual or shared objectives in multi-agent systems. In many real-world multi-agent systems, agents possess varying abilities and constraints, making it…
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions.…
Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactive feedback, robots must recognize human actions as early as possible from incomplete…
Previous group activity recognition approaches were limited to reasoning using human relations or finding important subgroups and tended to ignore indispensable group composition and human-object interactions. This absence makes a partial…
Multi-agent deep reinforcement learning makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions. The Mean-Field Actor-Critic reinforcement…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
The rapid growth of wearable sensor technologies holds substantial promise for the field of personalized and context-aware Human Activity Recognition. Given the inherently decentralized nature of data sources within this domain, the…
We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can be difficult, since coordination is often implicit in the…
Understanding interaction is an essential part of video action detection. We propose the Asynchronous Interaction Aggregation network (AIA) that leverages different interactions to boost action detection. There are two key designs in it:…
Group activity recognition aims to understand the activity performed by a group of people. In order to solve it, modeling complex spatio-temporal interactions is the key. Previous methods are limited in reasoning on a predefined graph,…
As Augmented Reality (AR) and Artificial Intelligence (AI) continue to converge, new opportunities emerge for AI agents to actively support human collaboration in immersive environments. While prior research has primarily focused on dyadic…