Related papers: RED: Reinforced Encoder-Decoder Networks for Actio…
The predictive processing (PP) hypothesizes that the predictive inference of our sensorimotor system is encoded implicitly in the regularities between perception and action. We propose a neural architecture in which such regularities of…
In contrast to the widely studied problem of recognizing an action given a complete sequence, action anticipation aims to identify the action from only partially available videos. As such, it is therefore key to the success of computer…
Life and physical sciences have always been quick to adopt the latest advances in machine learning to accelerate scientific discovery. Examples of this are cell segmentation or cancer detection. Nevertheless, these exceptional results are…
Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars. While recent works have addressed prediction of raw RGB pixel values, we focus on…
Classic reinforcement learning (RL) frequently confronts challenges in tasks involving delays, which cause a mismatch between received observations and subsequent actions, thereby deviating from the Markov assumption. Existing methods…
Forecasting the future behavior of all traffic agents in the vicinity is a key task to achieve safe and reliable autonomous driving systems. It is a challenging problem as agents adjust their behavior depending on their intentions, the…
Models play an important role in inverse problems, serving as the prior for representing the original signal to be recovered. REgularization by Denoising (RED) is a recently introduced general framework for constructing such priors using…
Predicting distant future trajectories of agents in a dynamic scene is not an easy problem because the future trajectory of an agent is affected by not only his/her past trajectory but also the scene contexts. To tackle this problem, we…
Action anticipation, the task of predicting future actions from partially observed videos, is crucial for advancing intelligent systems. Unlike action recognition, which operates on fully observed videos, action anticipation must handle…
We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an…
Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short- and…
Reinforcement Learning (RL) agents have demonstrated their potential across various robotic tasks. However, they still heavily rely on human-engineered reward functions, requiring extensive trial-and-error and access to target behavior…
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action experiences. Our proposed unsupervised deep episodic memory model…
Efficient action prediction is of central importance for the fluent workflow between humans and equally so for human-robot interaction. To achieve prediction, actions can be encoded by a series of events, where every event corresponds to a…
Action Prediction is aimed to determine what action is occurring in a video as early as possible, which is crucial to many online applications, such as predicting a traffic accident before it happens and detecting malicious actions in the…
Forecasting future events based on evidence of current conditions is an innate skill of human beings, and key for predicting the outcome of any decision making. In artificial vision for example, we would like to predict the next human…
Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We introduce EAST, a simple and efficient framework that enables a model to reason about…
Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system. To encourage an early and accurate decision, existing…
Neuromorphic visual sensors are artificial retinas that output sequences of asynchronous events when brightness changes occur in the scene. These sensors offer many advantages including very high temporal resolution, no motion blur and…
Action anticipation is the task of forecasting future activity from a partially observed sequence of events. However, this task is exposed to intrinsic future uncertainty and the difficulty of reasoning upon interconnected actions. Unlike…