相关论文: Anticipating Visual Representations from Unlabeled…

Pretraining general-purpose visual features has become a crucial part of tackling many computer vision tasks. While one can learn such features on the extensively-annotated ImageNet dataset, recent approaches have looked at ways to allow…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Action anticipation and forecasting in videos do not require a hat-trick, as far as there are signs in the context to foresee how actions are going to be deployed. Capturing these signs is hard because the context includes the past. We…

We propose to learn tasks directly from visual demonstrations by learning to predict the outcome of human and robot actions on an environment. We enable a robot to physically perform a human demonstrated task without knowledge of the…

We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct…

Unsupervised pre-training was a critical technique for training deep neural networks years ago. With sufficient labeled data and modern training techniques, it is possible to train very deep neural networks from scratch in a purely…

Video prediction aims to generate realistic future frames by learning dynamic visual patterns. One fundamental challenge is to deal with future uncertainty: How should a model behave when there are multiple correct, equally probable future?…

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…

Human visual perception carves a scene at its physical joints, decomposing the world into objects, which are selectively attended, tracked, and predicted as we engage our surroundings. Object representations emancipate perception from the…

Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning…

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is…

Action recognition is a key problem in computer vision that labels videos with a set of predefined actions. Capturing both, semantic content and motion, along the video frames is key to achieve high accuracy performance on this task. Most…

Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for training models with broad, general capabilities for text, images, and other modalities. However, for many sequential decision domains such as…

The abundance of instructional videos and their narrations over the Internet offers an exciting avenue for understanding procedural activities. In this work, we propose to learn video representation that encodes both action steps and their…

Cognitive planning is the structural decomposition of complex tasks into a sequence of future behaviors. In the computational setting, performing cognitive planning entails grounding plans and concepts in one or more modalities in order to…

The labeled data required to learn pose estimation for articulated objects is difficult to provide in the desired quantity, realism, density, and accuracy. To address this issue, we develop a method to learn representations, which are very…

The ultimate goal of video prediction is not forecasting future pixel-values given some previous frames. Rather, the end goal of video prediction is to discover valuable internal representations from the vast amount of available unlabeled…

A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a…

This paper presents a framework for the analysis of changes in visual streams: ordered sequences of images, possibly separated by significant time gaps. We propose a new approach to incorporating unlabeled data into training to generate…