14 citations · 18 across the 16 of their papers we have counts for
18 papers
Feeling Through the Load: Compliant Quadruped Locomotion under Payload Interactions
Shaunak A. Mehta, Mayank Mishra, Prajit KrisshnaKumar +2
Quadruped robots are increasingly expected to carry objects while moving through human environments. But what happens when a person interacts directly with the payload rather than…
Return-to-Home Feasible Micro-Aerial Vehicle Exploration for 3D Gaussian Splatting Reconstruction
Prajit Krisshnakumar, Fan Yang, Koichiro Niinuma
Micro aerial vehicles (MAVs) enable rapid indoor 3D reconstruction for inspection and time-critical situational awareness, but must operate under strict flight-time budgets and saf…
Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation
Oren Wright, Haoming Jing, Qiaoan Shen +3
A neural network's layers can be treated as time steps of a state-space model, turning Bayesian training into a smoothing problem: a forward pass propagates Gaussian moments throug…
Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations
Yi Fei Cheng, Fan Yang, Iremsu Bas +3
As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. While prior work has examined beh…
SemanticSlider3D: Training-Free Continuous Semantic Editing for 3D Objects
Ru Wang, Rahul Jain, Koichiro Niinuma +1
Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional 3D modeling workflows or prom…
Ultra-fast Traffic Nowcasting and Control via Differentiable Agent-based Simulation
Fumiyasu Makinoshima, Yuya Yamaguchi, Eigo Segawa +2
Traffic digital twins, which inform policymakers of effective interventions based on large-scale, high-fidelity computational models calibrated to real-world traffic, hold promise…
Map2Video: Street View Imagery Driven AI Video Generation
Hye-Young Jo, Mose Sakashita, Aditi Mishra +3
AI video generation has lowered barriers to video creation, but current tools still struggle with inconsistency. Filmmakers often find that clips fail to match characters and backg…
Scalable Dynamic Origin-Destination Demand Estimation Enhanced by High-Resolution Satellite Imagery Data
Jiachao Liu, Pablo Guarda, Koichiro Niinuma +1
This study presents a novel integrated framework for dynamic origin-destination demand estimation (DODE) in multi-class mesoscopic network models, incorporating high-resolution sat…
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Rohan Choudhury, Guanglei Zhu, Sihan Liu +3
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninf…
Gaussian Splatting Lucas-Kanade
Liuyue Xie, Joel Julin, Koichiro Niinuma +1
Gaussian Splatting and its dynamic extensions are effective for reconstructing 3D scenes from 2D images when there is significant camera movement to facilitate motion parallax and…
GHOST: Grounded Human Motion Generation with Open Vocabulary Scene-and-Text Contexts
Zoltán Á. Milacski, Koichiro Niinuma, Ryosuke Kawamura +2
The connection between our 3D surroundings and the descriptive language that characterizes them would be well-suited for localizing and generating human motion in context but for o…
CoGS: Controllable Gaussian Splatting
Heng Yu, Joel Julin, Zoltán Á. Milacski +2
Capturing and re-animating the 3D structure of articulated objects present significant barriers. On one hand, methods requiring extensively calibrated multi-view setups are prohibi…
Zero-Shot Video Question Answering with Procedural Programs
Rohan Choudhury, Koichiro Niinuma, Kris M. Kitani +1
We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. We present Proc…
Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
Pedro Valois, Koichiro Niinuma, Kazuhiro Fukui
Deep Learning of neural networks has gained prominence in multiple life-critical applications like medical diagnoses and autonomous vehicle accident investigations. However, concer…
DyLiN: Making Light Field Networks Dynamic
Heng Yu, Joel Julin, Zoltan A. Milacski +2
Light Field Networks, the re-formulations of radiance fields to oriented rays, are magnitudes faster than their coordinate network counterparts, and provide higher fidelity with re…
CoNFies: Controllable Neural Face Avatars
Heng Yu, Koichiro Niinuma, Laszlo A. Jeni
Neural Radiance Fields (NeRF) are compelling techniques for modeling dynamic 3D scenes from 2D image collections. These volumetric representations would be well suited for synthesi…
Adaptive occlusion sensitivity analysis for visually explaining video recognition networks
Tomoki Uchiyama, Naoya Sogi, Satoshi Iizuka +2
This paper proposes a method for visually explaining the decision-making process of video recognition networks with a temporal extension of occlusion sensitivity analysis, called A…
Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions
Koichiro Niinuma, Itir Onal Ertugrul, Jeffrey F Cohn +1
Critical obstacles in training classifiers to detect facial actions are the limited sizes of annotated video databases and the relatively low frequencies of occurrence of many acti…