Related papers: Annotating Motion Primitives for Simplifying Actio…
Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming,…
The problem of determining whether an object is in motion, irrespective of camera motion, is far from being solved. We address this challenging task by learning motion patterns in videos. The core of our approach is a fully convolutional…
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages…
In this paper we are interested in analyzing behaviour in crowded public places at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of "normal behaviour" for a particular…
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…
Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…
This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The…
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known.…
Human action analysis and understanding in videos is an important and challenging task. Although substantial progress has been made in past years, the explainability of existing methods is still limited. In this work, we propose a novel…
While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide…
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by…
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a…
Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to…
Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a…
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance…
Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation…
Contact-rich manipulation plays an important role in human daily activities, but uncertain parameters pose significant challenges for robots to achieve comparable performance through planning and control. To address this issue, domain…
Enabling computational systems with the ability to localize actions in video-based content has manifold applications. Traditionally, such a problem is approached in a fully-supervised setting where video-clips with complete frame-by-frame…
Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research,…
For training a video-based action recognition model that accepts multi-view video, annotating frame-level labels is tedious and difficult. However, it is relatively easy to annotate sequence-level labels. This kind of coarse annotations are…