Search Results - "Ryou, Serim"

Anchor Loss: Modulating Loss Scale Based on Prediction Difficulty by Ryou, Serim, Jeong, Seong-Gyun, Perona, Pietro

“…We propose a novel loss function that dynamically re-scales the cross entropy based on prediction difficulty regarding a sample. Deep neural network…”
Get full text

Multilabel Classification Models for the Prediction of Cross-Coupling Reaction Conditions by Maser, Michael R, Cui, Alexander Y, Ryou, Serim, DeLano, Travis J, Yue, Yisong

“…Machine-learned ranking models have been developed for the prediction of substrate-specific cross-coupling reaction conditions. Data sets of published…”
Get full text

Representation of the Semantic Structures: From Discovery to Applications by Ryou, Serim

“…The world surrounding us is full of structured entities. Scenes can be structured as the sum of objects arranged in space, objects can be decomposed into…”
Get full text

Self-Supervised Keypoint Discovery in Behavioral Videos by Sun, Jennifer J., Ryou, Serim, Goldshmid, Roni H., Weissbourd, Brandon, Dabiri, John O., Anderson, David J., Kennedy, Ann, Yue, Yisong, Perona, Pietro

“…We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are…”
Get full text

BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos by Sun, Jennifer J., Karashchuk, Lili, Dravid, Amil, Ryou, Serim, Fereidooni, Sonia, Tuthill, John C., Katsaggelos, Aggelos, Brunton, Bingni W., Gkioxari, Georgia, Kennedy, Ann, Yue, Yisong, Perona, Pietro

“…Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to…”
Get full text

Weakly Supervised Keypoint Discovery by Ryou, Serim, Perona, Pietro

“…In this paper, we propose a method for keypoint discovery from a 2D image using image-level supervision. Recent works on unsupervised keypoint discovery…”
Get full text

Anchor Loss: Modulating Loss Scale based on Prediction Difficulty by Ryou, Serim, Jeong, Seong-Gyun, Perona, Pietro

“…We propose a novel loss function that dynamically rescales the cross entropy based on prediction difficulty regarding a sample. Deep neural network…”
Get full text

BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos by Sun, Jennifer J, Karashchuk, Lili, Dravid, Amil, Ryou, Serim, Fereidooni, Sonia, Tuthill, John, Katsaggelos, Aggelos, Brunton, Bingni W, Gkioxari, Georgia, Kennedy, Ann, Yue, Yisong, Perona, Pietro

“…Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to…”
Get full text

Self-Supervised Keypoint Discovery in Behavioral Videos by Sun, Jennifer J, Ryou, Serim, Goldshmid, Roni, Weissbourd, Brandon, Dabiri, John, Anderson, David J, Kennedy, Ann, Yue, Yisong, Perona, Pietro

“…We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are…”
Get full text

Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions by Ryou, Serim, Maser, Michael R, Cui, Alexander Y, DeLano, Travis J, Yue, Yisong, Reisman, Sarah E

“…We present a systematic investigation using graph neural networks (GNNs) to model organic chemical reactions. To do so, we prepared a dataset collection of…”
Get full text