Goto

Collaborating Authors

 dance pattern


Dreamweaver: Learning Compositional World Representations from Pixels

Baek, Junyeob, Wu, Yi-Fu, Singh, Gautam, Ahn, Sungjin

arXiv.org Artificial Intelligence

Humans have an innate ability to decompose their perceptions of the world into objects and their attributes, such as colors, shapes, and movement patterns. This cognitive process enables us to imagine novel futures by recombining familiar concepts. However, replicating this ability in artificial intelligence systems has proven challenging, particularly when it comes to modeling videos into compositional concepts and generating unseen, recomposed futures without relying on auxiliary data, such as text, masks, or bounding boxes. In this paper, we propose Dreamweaver, a neural architecture designed to discover hierarchical and compositional representations from raw videos and generate compositional future simulations. Our approach leverages a novel Recurrent Block-Slot Unit (RBSU) to decompose videos into their constituent objects and attributes. In addition, Dreamweaver uses a multi-future-frame prediction objective to capture disentangled representations for dynamic concepts more effectively as well as static concepts. In experiments, we demonstrate our model outperforms current state-of-the-art baselines for world modeling when evaluated under the DCI framework across multiple datasets. Furthermore, we show how the modularized concept representations of our model enable compositional imagination, allowing the generation of novel videos by recombining attributes from different objects.


Honey Bee Dance Modeling in Real-time using Machine Learning

Saghafi, Abolfazl, Tsokos, Chris P.

arXiv.org Machine Learning

The waggle dance that honeybees perform is an astonishing way of communicating the location of food source. After over 60 years of its discovery, researchers still use manual labeling by watching hours of dance videos to detect different transitions between dance components thus extracting information regarding the distance and direction to the food source. We propose an automated process to monitor and segment different components of honeybee waggle dance. The process is highly accurate, runs in real-time, and can use shared information between multiple dances. Keywords: Classification, Machine Learning, Honey Bee, Real-time 1. Introduction Honey bees perform a special dance known as waggle dance within the beehive to communicate the information regarding the distance and direction of food sources.