162 citations · 192 across the 10 of their papers we have counts for
11 papers
Learning 3D Affordances for Blade Insertion in Cluttered Stowing
Tianyu Li, Harpreet Sawhney, Minju Jung +3
Many manipulation tasks require reasoning about free-space affordances: discovering volumes where an extended rigid tool can safely navigate, complementary to surface contact affor…
Frequency-aware decomposition learning for sensorless wrench estimation in vibration-rich robotic contact
Hyeonbeen Lee, Min-Jae Jung, Tae-Kyeong Yeu +4
Force and torque (F/T) sensors enable contact-aware control by providing reactive feedback, but they are often fragile and expensive. To overcome these limitations, sensorless meth…
KuraNet: Systems of Coupled Oscillators that Learn to Synchronize
Matthew Ricci, Minju Jung, Yuwei Zhang +3
Networks of coupled oscillators are some of the most studied objects in the theory of dynamical systems. Two important areas of current interest are the study of synchrony in highl…
Iterative VAE as a predictive brain model for out-of-distribution generalization
Victor Boutin, Aimen Zerroug, Minju Jung +1
Our ability to generalize beyond training data to novel, out-of-distribution, image degradations is a hallmark of primate vision. The predictive brain, exemplified by predictive co…
Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory
Minju Jung, Takazumi Matsumoto, Jun Tani
Mental simulation is a critical cognitive function for goal-directed behavior because it is essential for assessing actions and their consequences. When a self-generated or externa…
Generating Goal-Directed Visuomotor Plans Based on Learning Using a Predictive Coding-type Deep Visuomotor Recurrent Neural Network Model
Minkyu Choi, Takazumi Matsumoto, Minju Jung +1
The current paper presents how a predictive coding type deep recurrent neural networks can generate vision-based goal-directed plans based on prior learning experience by examining…
Less-forgetful Learning for Domain Expansion in Deep Neural Networks
Heechul Jung, Jeongwoo Ju, Minju Jung +1
Expanding the domain that deep neural network has already learned without accessing old domain data is a challenging task because deep neural networks forget previously learned inf…
Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition
Minju Jung, Haanvid Lee, Jun Tani
Based on the progress of image recognition, video recognition has been extensively studied recently. However, most of the existing methods are focused on short-term but not long-te…
Less-forgetting Learning in Deep Neural Networks
Heechul Jung, Jeongwoo Ju, Minju Jung +1
A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different senso…
Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks
Haanvid Lee, Minju Jung, Jun Tani
The current paper proposes a novel neural network model for recognizing visually perceived human actions. The proposed multiple spatio-temporal scales recurrent neural network (MST…
Achieving Synergy in Cognitive Behavior of Humanoids via Deep Learning of Dynamic Visuo-Motor-Attentional Coordination
Jungsik Hwang, Minju Jung, Naveen Madapana +3
The current study examines how adequate coordination among different cognitive processes including visual recognition, attention switching, action preparation and generation can be…