scholarly journals Learning Long-Term Dependencies for Action Recognition with a Biologically-Inspired Deep Network

2017 ◽  
Author(s):  
Yemin Shi ◽  
Yonghong Tian ◽  
Yaowei Wang ◽  
Wei Zeng ◽  
Tiejun Huang
Keyword(s):  
Action Recognition ◽  
Biologically Inspired ◽  
Deep Network

Action Recognition Based on a Hybrid Deep Network

2021 ◽  
Vol 2 (6) ◽  
Author(s):  
Yiping Zou ◽  
Xuan Zhou ◽  
Xuemei Ren
Keyword(s):  
Action Recognition ◽  
Deep Network

scholarly journals ODN: Opening the Deep Network for Open-Set Action Recognition

2018 ◽  
Author(s):  
Yu Shu ◽  
Yemin Shi ◽  
Yaowei Wang ◽  
Yixiong Zou ◽  
Qingsheng Yuan ◽  
...  
Keyword(s):  
Action Recognition ◽  
Deep Network ◽  
Open Set

ADAPTIVE CEREBELLAR SPIKING MODEL EMBEDDED IN THE CONTROL LOOP: CONTEXT SWITCHING AND ROBUSTNESS AGAINST NOISE

2011 ◽  
Vol 21 (05) ◽  
pp. 385-401 ◽  
Author(s):  
N. R. LUQUE ◽  
J. A. GARRIDO ◽  
R. R. CARRILLO ◽  
S. TOLU ◽  
E. ROS
Keyword(s):  
Degrees Of Freedom ◽  
Mossy Fibers ◽  
Long Term Potentiation ◽  
Biologically Inspired ◽  
Context Switching ◽  
Term Potentiation ◽  
Spiking Network ◽  
Three Degrees Of Freedom ◽  
Spiking Model

This work evaluates the capability of a spiking cerebellar model embedded in different loop architectures (recurrent, forward, and forward&recurrent) to control a robotic arm (three degrees of freedom) using a biologically-inspired approach. The implemented spiking network relies on synaptic plasticity (long-term potentiation and long-term depression) to adapt and cope with perturbations in the manipulation scenario: changes in dynamics and kinematics of the simulated robot. Furthermore, the effect of several degrees of noise in the cerebellar input pathway (mossy fibers) was assessed depending on the employed control architecture. The implemented cerebellar model managed to adapt in the three control architectures to different dynamics and kinematics providing corrective actions for more accurate movements. According to the obtained results, coupling both control architectures (forward&recurrent) provides benefits of the two of them and leads to a higher robustness against noise.

scholarly journals Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

2021 ◽  
Author(s):  
Dima Damen ◽  
Hazel Doughty ◽  
Giovanni Maria Farinella ◽  
Antonino Furnari ◽  
Evangelos Kazakos ◽  
...  
Keyword(s):  
Action Recognition ◽  
Domain Adaptation ◽  
Weak Supervision ◽  
Action Detection ◽  
Previous Version ◽  
Fine Grained ◽  
Unsupervised Domain Adaptation ◽  
Egocentric Vision ◽  
New Challenges

AbstractThis paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version (Damen in Scaling egocentric vision: ECCV, 2018), EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the “test of time”—i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics.

Sign in / Sign up

Export Citation Format

Share Document