Graph-Based Visual Manipulation Relationship Reasoning Network for Robotic Grasping

To grasp the target object stably and orderly in the object-stacking scenes, it is important for the robot to reason the relationships between objects and obtain intelligent manipulation order for more advanced interaction between the robot and the environment. This paper proposes a novel graph-based visual manipulation relationship reasoning network (GVMRN) that directly outputs object relationships and manipulation order. The GVMRN model first extracts features and detects objects from RGB images, and then adopts graph convolutional network (GCN) to collect contextual information between objects. To improve the efficiency of relation reasoning, a relationship filtering network is built to reduce object pairs before reasoning. The experiments on the Visual Manipulation Relationship Dataset (VMRD) show that our model significantly outperforms previous methods on reasoning object relationships in object-stacking scenes. The GVMRN model is also tested on the images we collected and applied on the robot grasping platform. The results demonstrated the generalization and applicability of our method in real environment.

Acquisitive Desire in Early Childhood: Rethinking Rivalry in the Playroom

What if we could observe the normal operation of mimetic desire in a rivalry-free environment? What would object relationships look like? Would acquisitive desire make an appearance without the encouragement of the model-obstacle dynamic? Montessori’s teacher training method offers a rigorous approach to removing rivalry from the student-teacher relationship. It is designed and functions to prevent the model-obstacle phenomenon from occurring. Therefore it provides us with a laboratory for observing mimetic desire in as close to a pre-lapsarian state as we can approximate this side of the gates of Eden.

Developmental differences in children’s and adults’ use of geometric information in map-reading tasks

Using maps effectively requires the ability to scale distances while preserving angle and orientation, the three properties of Euclidean geometry. The aim of the current study was twofold: first, to examine how the ability to represent and use these Euclidean properties changes with development when scaling maps in object-to-object relationships and, second, to explore the effects on the scaling performance of two variables of the array of objects, type of angular configuration and relative vector length. To this end, we tested seventy-five 4-, 6-, and 8-year-old children, as well as twenty-five adults, in a simple completion task with different linear and triangular configurations of objects. This study revealed important developmental changes between 4 and 6 years of age and between 8 years of age and adulthood for both distance and angle representation, while it also showed that the configuration variables affected younger and older children’s performances in different ways when scaling distances and preserving angles and orientation. This study was instrumental in showing that, from an early age, children are able to exploit an intrinsic system of reference to scale geometrical configurations of objects.

Object-Aware Multi-Branch Relation Networks for Spatio-Temporal Video Grounding

Spatio-temporal video grounding aims to retrieve the spatio-temporal tube of a queried object according to the given sentence. Currently, most existing grounding methods are restricted to well-aligned segment-sentence pairs. In this paper, we explore spatio-temporal video grounding on unaligned data and multi-form sentences. This challenging task requires to capture critical object relations to identify the queried target. However, existing approaches cannot distinguish notable objects and remain in ineffective relation modeling between unnecessary objects. Thus, we propose a novel object-aware multi-branch relation network for object-aware relation discovery. Concretely, we first devise multiple branches to develop object-aware region modeling, where each branch focuses on a crucial object mentioned in the sentence. We then propose multi-branch relation reasoning to capture critical object relationships between the main branch and auxiliary branches. Moreover, we apply a diversity loss to make each branch only pay attention to its corresponding object and boost multi-branch learning. The extensive experiments show the effectiveness of our proposed method.

The neurons that mistook a hat for a face

Despite evidence that context promotes the visual recognition of objects, decades of research have led to the pervasive notion that the object processing pathway in primate cortex consists of multiple areas that each process the intrinsic features of a few particular categories (e.g. faces, bodies, hands, objects, and scenes). Here we report that such category-selective neurons do not in fact code individual categories in isolation but are also sensitive to object relationships that reflect statistical regularities of the experienced environment. We show by direct neuronal recording that face-selective neurons respond not just to an image of a face, but also to parts of an image where contextual cues—for example a body—indicate a face ought to be, even if what is there is not a face.