[HTML][HTML] Dark, beyond deep: A paradigm shift to cognitive ai with humanlike common sense
Recent progress in deep learning is essentially based on a “big data for small tasks”
paradigm, under which massive amounts of data are used to train a classifier for a single …
paradigm, under which massive amounts of data are used to train a classifier for a single …
Benchmarking progress to infant-level physical reasoning in AI
To what extent do modern AI systems comprehend the physical world? We introduce the
open-access Infant-Level Physical Reasoning Benchmark (InfLevel) to gain insight into this …
open-access Infant-Level Physical Reasoning Benchmark (InfLevel) to gain insight into this …
X-voe: Measuring explanatory violation of expectation in physical events
Intuitive physics is pivotal for human understanding of the physical world, enabling
prediction and interpretation of events even in infancy. Nonetheless, replicating this level of …
prediction and interpretation of events even in infancy. Nonetheless, replicating this level of …
Learning object permanence from video
A Shamsian, O Kleinfeld, A Globerson… - Computer Vision–ECCV …, 2020 - Springer
Object Permanence allows people to reason about the location of non-visible objects, by
understanding that they continue to exist even when not perceived directly. Object …
understanding that they continue to exist even when not perceived directly. Object …
Joint inference of states, robot knowledge, and human (false-) beliefs
Aiming to understand how human (false-) belief—a core socio-cognitive ability—would affect
human interactions with robots, this paper proposes to adopt a graphical model to unify the …
human interactions with robots, this paper proposes to adopt a graphical model to unify the …
Can i pour into it? robot imagining open containability affordance of previously unseen objects via physical simulations
H Wu, GS Chirikjian - IEEE Robotics and Automation Letters, 2020 - ieeexplore.ieee.org
Open containers, ie, containers without covers, are an important and ubiquitous class of
objects in human life. In this letter, we propose a novel method for robots to “imagine” the …
objects in human life. In this letter, we propose a novel method for robots to “imagine” the …
Learning a Generative Model for Multi‐Step Human‐Object Interactions from Videos
Creating dynamic virtual environments consisting of humans interacting with objects is a
fundamental problem in computer graphics. While it is well‐accepted that agent interactions …
fundamental problem in computer graphics. While it is well‐accepted that agent interactions …
Functional workspace optimization via learning personal preferences from virtual experiences
The functionality of a workspace is one of the most important considerations in both virtual
world design and interior design. To offer appropriate functionality to the user, designers …
world design and interior design. To offer appropriate functionality to the user, designers …
Object-agnostic Affordance Categorization via Unsupervised Learning of Graph Embeddings
Acquiring knowledge about object interactions and affordances can facilitate scene
understanding and human-robot collaboration tasks. As humans tend to use objects in many …
understanding and human-robot collaboration tasks. As humans tend to use objects in many …
Deep video representation learning: a survey
This paper provides a review on representation learning for videos. We classify recent spatio-
temporal feature learning methods for sequential visual data and compare their pros and …
temporal feature learning methods for sequential visual data and compare their pros and …