Inferring the Future by Imagining the Past
- URL: http://arxiv.org/abs/2305.17195v2
- Date: Mon, 30 Oct 2023 13:24:39 GMT
- Title: Inferring the Future by Imagining the Past
- Authors: Kartik Chandra, Tony Chen, Tzu-Mao Li, Jonathan Ragan-Kelley, Josh
Tenenbaum
- Abstract summary: Humans routinely infer complex sequences of past and future events from a static snapshot of adynamic scene.
In this paper, we model how humans make such rapid and flexible inferences.
Our key technical insight is a surprising connection between our inference problem and Monte Carlo path tracing.
- Score: 16.94725365663225
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A single panel of a comic book can say a lot: it can depict not only where
the characters currently are, but also their motions, their motivations, their
emotions, and what they might do next. More generally, humans routinely infer
complex sequences of past and future events from a *static snapshot* of a
*dynamic scene*, even in situations they have never seen before.
In this paper, we model how humans make such rapid and flexible inferences.
Building on a long line of work in cognitive science, we offer a Monte Carlo
algorithm whose inferences correlate well with human intuitions in a wide
variety of domains, while only using a small, cognitively-plausible number of
samples. Our key technical insight is a surprising connection between our
inference problem and Monte Carlo path tracing, which allows us to apply
decades of ideas from the computer graphics community to this
seemingly-unrelated theory of mind task.
Related papers
- Acting as Inverse Inverse Planning [19.267798639508946]
We offer a novel computational framework for such tools.
To simulate the audience, we borrow an established principle from cognitive science.
We treat storytelling as "*inverse* inverse planning," the task of choosing actions to manipulate an inverse planner's inferences.
arXiv Detail & Related papers (2023-05-26T13:26:36Z) - Neural Novel Actor: Learning a Generalized Animatable Neural
Representation for Human Actors [98.24047528960406]
We propose a new method for learning a generalized animatable neural representation from a sparse set of multi-view imagery of multiple persons.
The learned representation can be used to synthesize novel view images of an arbitrary person from a sparse set of cameras, and further animate them with the user's pose control.
arXiv Detail & Related papers (2022-08-25T07:36:46Z) - A-ACT: Action Anticipation through Cycle Transformations [89.83027919085289]
We take a step back to analyze how the human capability to anticipate the future can be transferred to machine learning algorithms.
A recent study on human psychology explains that, in anticipating an occurrence, the human brain counts on both systems.
In this work, we study the impact of each system for the task of action anticipation and introduce a paradigm to integrate them in a learning framework.
arXiv Detail & Related papers (2022-04-02T21:50:45Z) - The Abduction of Sherlock Holmes: A Dataset for Visual Abductive
Reasoning [113.25016899663191]
Humans have remarkable capacity to reason abductively and hypothesize about what lies beyond the literal content of an image.
We present Sherlock, an annotated corpus of 103K images for testing machine capacity for abductive reasoning beyond literal image contents.
arXiv Detail & Related papers (2022-02-10T02:26:45Z) - Visual Perspective Taking for Opponent Behavior Modeling [22.69165968663182]
We propose an end-to-end long-term visual prediction framework for robots.
We demonstrate our approach in the context of visual hide-and-seek.
We suggest that visual behavior modeling and perspective taking skills will play a critical role in the ability of physical robots to fully integrate into real-world multi-agent activities.
arXiv Detail & Related papers (2021-05-11T16:02:32Z) - Perpetual Motion: Generating Unbounded Human Motion [61.40259979876424]
We focus on long-term prediction; that is, generating long sequences of human motion that is plausible.
We propose a model to generate non-deterministic, textitever-changing, perpetual human motion.
We train this using a heavy-tailed function of the KL divergence of a white-noise Gaussian process, allowing latent sequence temporal dependency.
arXiv Detail & Related papers (2020-07-27T21:50:36Z) - Machine Common Sense [77.34726150561087]
Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI)
This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
arXiv Detail & Related papers (2020-06-15T13:59:47Z) - Visual Prediction of Priors for Articulated Object Interaction [37.759459329701194]
Humans are able to build on prior experience quickly and efficiently.
Adults also exhibit this behavior when entering new spaces such as kitchens.
We develop a method, Contextual Prior Prediction, which provides a means of transferring knowledge between interactions in similar domains through vision.
arXiv Detail & Related papers (2020-06-06T21:17:03Z) - Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike
Common Sense [142.53911271465344]
We argue that the next generation of AI must embrace "dark" humanlike common sense for solving novel tasks.
We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense.
arXiv Detail & Related papers (2020-04-20T04:07:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.