相关论文: Learning Goals from Failure

We present a novel approach to estimating physical properties of objects from video. Our approach consists of a physics engine and a correction estimator. Starting from the initial observed state, object behavior is simulated forward in…

Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcoming actions. Existing transformer-based approaches, which…

Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors and inefficiency. While Vision-Language Models (VLMs)…

To anticipate how a human would act in the future, it is essential to understand the human intention since it guides the human towards a certain goal. In this paper, we propose a hierarchical architecture which assumes a sequence of human…

The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided agents and assistive AI that supports humans to perform…

This paper presents an online intention prediction framework for estimating the goal state of autonomous systems in real time, even when intention is time-varying, and system dynamics or objectives include unknown parameters. The problem is…

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…

Object concepts play a foundational role in human visual cognition, enabling perception, memory, and interaction in the physical world. Inspired by findings in developmental neuroscience - where infants are shown to acquire object…

Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future. In contrast to current…

Understanding human actions is a key problem in computer vision. However, recognizing actions is only the first step of understanding what a person is doing. In this paper, we introduce the problem of predicting why a person has performed…

Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications.…

Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction…

We propose a method to learn image representations from uncurated videos. We combine a supervised loss from off-the-shelf object detectors and self-supervised losses which naturally arise from the video-shot-frame-object hierarchy present…

This paper describes a methodology for learning flight control systems from human demonstrations and interventions while considering the estimated uncertainty in the learned models. The proposed approach uses human demonstrations to train…

This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…

Latent action models (LAMs) aim to learn action-like representations from unlabeled videos by compressing frame-to-frame changes. The frames of in-the-wild videos, however, contain not only the agent's own state but exogenous state such as…

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

With the advancement in computer vision deep learning, systems now are able to analyze an unprecedented amount of rich visual information from videos to enable applications such as autonomous driving, socially-aware robot assistant and…

Predicting future scene representations is a crucial task for enabling robots to understand and interact with the environment. However, most existing methods rely on videos and simulations with precise action annotations, limiting their…

Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider…