Search Results for author:
Found 10 papers, 4 papers with code
Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
We present a new computational model for gaze prediction in egocentric videos by exploring patterns in temporal shift of gaze fixations (attention transition) that are dependent on egocentric manipulation tasks.
Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes
In the proposed model, we explore various semantic relationships between actions, grasp types and object attributes, and show how the context can be used to boost the recognition of each component.
Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions
In this work, we address two coupled tasks of gaze prediction and action recognition in egocentric videos by exploring their mutual context.
Manipulation-skill Assessment from Videos with Spatial Attention Network
Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in performing a task, which breeds many important applications in domains such as health rehabilitation and manufacturing.
What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis
However, techniques for analyzing the first-person video can be fundamentally different from those for the third-person video, and it is even more difficult to explore the shared information from both viewpoints.
Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation
To this end, we propose a Bayesian CNN-based model adaptation framework for hand segmentation, which introduces and considers two key factors: 1) prediction uncertainty when the model is applied in a new domain and 2) common information about hand shapes shared across domains.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection
We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) the joint alignment of distributions for inputs (feature alignment) and outputs (self-training) is needed.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022: Team HNU-FPV Technical Report
Then the global information from videos frames and local information from image patches are processed by an existing video adaptation method, i. e., TA3N, in order to perform feature alignment for the source domain and the target domain.
