相关论文: Data Augmentation for Instruction Following Polici…

Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large…

Understanding the steps required to perform a task is an important skill for AI systems. Learning these steps from instructional videos involves two subproblems: (i) identifying the temporal boundary of sequentially occurring segments and…

In many cases, such as trajectories clustering and classification, we often divide a trajectory into segments as preprocessing. In this paper, we propose a trajectory semantic segmentation method based on learned behavior models. In the…

We propose a novel method for effective retrieval of multi-agent spatiotemporal tracking data. Retrieval of spatiotemporal tracking data offers several unique challenges compared to conventional text-based retrieval settings. Most notably,…

Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In the former, an agent learns a policy over $\mathbb{R}^d$ and in the latter, over a discrete set of actions…

This paper aims at recognizing partially observed human actions in videos. Action videos acquired in uncontrolled environments often contain corrupt frames, which make actions partially observed. Furthermore, these frames can last for…

Imitation learning is a powerful tool for training agents by leveraging expert knowledge, and being able to replicate a given trajectory is an integral part of it. In complex environments, like modern 3D video games, distribution shift and…

In this paper, we propose a method for semantic segmentation of pedestrian trajectories based on pedestrian behavior models, or agents. The agents model the dynamics of pedestrian movements in two-dimensional space using a linear dynamics…

We study a pursuit-evasion game between two players with car-like dynamics and sensing limitations by formalizing it as a partially observable stochastic zero-sum game. The partial observability caused by the sensing constraints is…

Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential…

Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weather…

This paper studies the performative policy learning problem, where agents adjust their features in response to a released policy to improve their potential outcomes, inducing an endogenous distribution shift. There has been growing interest…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to…

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an…

Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks. To enable learning the…

We apply a generative segmental model of task structure, guided by narration, to action segmentation in video. We focus on unsupervised and weakly-supervised settings where no action labels are known during training. Despite its simplicity,…

Despite advancements in deep reinforcement learning algorithms, developing an effective exploration strategy is still an open problem. Most existing exploration strategies either are based on simple heuristics, or require the model of the…

Trajectory augmentation serves as a means to mitigate distributional shift in imitation learning. However, imitating trajectories that inadequately represent the original expert data can result in undesirable behaviors, particularly in…

Autonomous multi-agent systems such as hospital robots and package delivery drones often operate in highly uncertain environments and are expected to achieve complex temporal task objectives while ensuring safety. While learning-based…