Search Results for author:
Found 22 papers, 7 papers with code
Fusing Domain-Specific Content from Large Language Models into Knowledge Graphs for Enhanced Zero Shot Object State Classification
Domain-specific knowledge can significantly contribute to addressing a wide variety of vision tasks.
Leveraging Knowledge Graphs for Zero-Shot Object-agnostic State Classification
We investigate the problem of Object State Classification (OSC) as a zero-shot learning problem.
TAPE: Temporal Attention-based Probabilistic human pose and shape Estimation
Existing methods ignore the ambiguities of the reconstruction and provide a single deterministic estimate for the 3D pose.
Ranked #49 on
3D Human Pose Estimation
on 3DPW
Graphing the Future: Activity and Next Active Object Prediction using Graph-based Activity Representations
We present a novel approach for the visual prediction of human-object interactions in videos.
Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental Study
This study enables the setup of a baseline on the performance of SD, as well as its relative performance in comparison to OD, in a variety of scenarios.
PE-former: Pose Estimation Transformer
Vision transformer architectures have been demonstrated to work very effectively for image classification tasks.
Ranked #10 on
Pose Estimation
on MS COCO
Even Faster SNN Simulation with Lazy+Event-driven Plasticity and Shared Atomics
It offers higher bandwidth than event-driven plasticity alone and achieves a 1. 5x-2x speedup over our closest competitor.
H-GAN: the power of GANs in your Hands
Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands.
Multi-GPU SNN Simulation with Static Load Balancing
We present a SNN simulator which scales to millions of neurons, billions of synapses, and 8 GPUs.
A Review on Deep Learning Techniques for Video Prediction
The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems.
A Review on Intelligent Object Perception Methods Combining Knowledge-based Reasoning and Machine Learning
Object perception is a fundamental sub-field of Computer Vision, covering a multitude of individual areas and having contributed high-impact results.
Faster and Simpler SNN Simulation with Work Queues
We present a clock-driven Spiking Neural Network simulator which is up to 3x faster than the state of the art while, at the same time, being more general and requiring less programming effort on both the user's and maintainer's side.
ReActNet: Temporal Localization of Repetitive Activities in Real-World Videos
On top of this representation, we design, implement and evaluate ReActNet, a lightweight convolutional neural network that classifies a given frame as belonging (or not) to a repetitive video segment.
Accurate Hand Keypoint Localization on Mobile Devices
We present a novel approach for 2D hand keypoint localization from regular color input.
Learning to Infer the Depth Map of a Hand from its Color Image
We propose the first approach to the problem of inferring the depth map of a human hand based on a single RGB image.
HANDS18: Methods, Techniques and Applications for Hand Observation
The fourth instantiation of this workshop attracted significant interest from both academia and the industry.
On the Feasibility of Real-Time 3D Hand Tracking using Edge GPGPU Acceleration
This paper presents the case study of a non-intrusive porting of a monolithic C++ library for real-time 3D hand tracking, to the domain of edge-based computation.
Using a single RGB frame for real time 3D hand pose estimation in the wild
We present a method for the real-time estimation of the full 3D pose of one or more human hands using a single commodity RGB camera.
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
Back to RGB: 3D tracking of hands and hand-object interactions based on short-baseline stereo
Unfortunately, this does not work well in practice because the stereo-based, dense 3D reconstruction of hands is far less accurate than the one obtained by RGBD cameras.
Scalable 3D Tracking of Multiple Interacting Objects
We consider the problem of tracking multiple interacting objects in 3D, using RGBD input and by considering a hypothesize-and-test approach.
Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis
In several hand-object(s) interaction scenarios, the change in the objects' state is a direct consequence of the hand's motion.
