Search Results for author:
Found 18 papers, 9 papers with code
Ego-Surfing First-Person Videos
We incorporate this feature into our proposed approach that computes the motion correlation over supervoxel hierarchies to localize target instances in observer videos.
Recognizing Micro-Actions and Reactions From Paired Egocentric Videos
We aim to understand the dynamics of social interactions between two people by recognizing their actions and reactions using a head-mounted camera.
Ego-Surfing: Person Localization in First-Person Videos Using Ego-Motion Signatures
We envision a future time when wearable cameras are worn by the masses and recording first-person point-of-view videos of everyday life.
Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data.
Future Person Localization in First-Person Videos
We present a new task that predicts future locations of people observed in first-person videos.
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Specifically, FedCS solves a client selection problem with resource constraints, which allows the server to aggregate as many client updates as possible and to accelerate performance improvement in ML models.
MGpi: A Computational Model of Multiagent Group Perception and Interaction
Toward enabling next-generation robots capable of socially intelligent interaction with humans, we present a $\mathbf{computational\; model}$ of interactions in a social environment of multiple agents and multiple groups.
Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data
Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e. g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients.
Decentralized Learning of Generative Adversarial Networks from Non-iid Data
This work addresses a new problem that learns generative adversarial networks (GANs) from multiple data collections that are each i) owned separately by different clients and ii) drawn from a non-identical distribution that comprises different classes.
MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics
Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks.
Crowd Density Forecasting by Modeling Patch-based Dynamics
To address this task, we have developed the patch-based density forecasting network (PDFN), which enables forecasting over a sequence of crowd density maps describing how crowded each location is in each video frame.
L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-aware Robot Navigation
This work presents a deep reinforcement learning framework for interactive navigation in a crowded place.
Adaptive Distillation for Decentralized Learning from Heterogeneous Clients
This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models pre-trained with their own data resources.
Path Planning using Neural A* Search
We present Neural A*, a novel data-driven search method for path planning problems.
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives
We present ShinRL, an open-source library specialized for the evaluation of reinforcement learning (RL) algorithms from both theoretical and practical perspectives.
CTRMs: Learning to Construct Cooperative Timed Roadmaps for Multi-agent Path Planning in Continuous Spaces
Multi-agent path planning (MAPP) in continuous spaces is a challenging problem with significant practical importance.
Risk-aware Path Planning via Probabilistic Fusion of Traversability Prediction for Planetary Rovers on Heterogeneous Terrains
Machine learning (ML) plays a crucial role in assessing traversability for autonomous rover operations on deformable terrains but suffers from inevitable prediction errors.
Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints
This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms.
