Výsledky vyhledávání - "Govindarajan, Lakshmi Narasimhan"

Report

Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning

Autor: Govindarajan, Lakshmi Narasimhan, Liu, Rex G, Linsley, Drew, Ashok, Alekh Karkada, Reuter, Max, Frank, Michael J, Serre, Thomas

Humans learn by interacting with their environments and perceiving the outcomes of their actions. A landmark in artificial intelligence has been the development of deep reinforcement learning (dRL) algorithms capable of doing the same in video games,

Externí odkaz: http://arxiv.org/abs/2309.13181

Zobrazit plný text záznamu

Report

Computing a human-like reaction time metric from stable recurrent vision models

Autor: Goetschalckx, Lore, Govindarajan, Lakshmi Narasimhan, Ashok, Alekh Karkada, Ahuja, Aarit, Sheinberg, David L., Serre, Thomas

The meteoric rise in the adoption of deep neural networks as computational models of vision has inspired efforts to "align" these models with humans. One dimension of interest for alignment includes behavioral choices, but moving beyond characterizin

Externí odkaz: http://arxiv.org/abs/2306.11582

Zobrazit plný text záznamu

Report

Stable and expressive recurrent vision models

Autor: Linsley, Drew, Ashok, Alekh Karkada, Govindarajan, Lakshmi Narasimhan, Liu, Rex, Serre, Thomas

Primate vision depends on recurrent processing for reliable perception. A growing body of literature also suggests that recurrent connections improve the learning efficiency and generalization of vision models on classic computer vision challenges. W

Externí odkaz: http://arxiv.org/abs/2005.11362

Zobrazit plný text záznamu

Report

Robust pose tracking with a joint model of appearance and shape

Autor: Guo, Yuliang, Govindarajan, Lakshmi Narasimhan, Kimia, Benjamin, Serre, Thomas

We present a novel approach for estimating the 2D pose of an articulated object with an application to automated video analysis of small laboratory animals. We have found that deformable part models developed for humans, exemplified by the flexible m

Externí odkaz: http://arxiv.org/abs/1806.11011

Zobrazit plný text záznamu

Report

An Interval-Based Bayesian Generative Model for Human Complex Activity Recognition

Autor: Liu, Li, Yang, Yongzhong, Govindarajan, Lakshmi Narasimhan, Wang, Shu, Hu, Bin, Cheng, Li, Rosenblum, David S.

Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We

Externí odkaz: http://arxiv.org/abs/1701.00903

Zobrazit plný text záznamu

Report

Lie-X: Depth Image Based Articulated Object Pose Estimation, Tracking, and Action Recognition on Lie Groups

Autor: Xu, Chi, Govindarajan, Lakshmi Narasimhan, Zhang, Yu, Cheng, Li

Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, whic

Externí odkaz: http://arxiv.org/abs/1609.03773

Zobrazit plný text záznamu

Report

Hand Action Detection from Ego-centric Depth Sequences with Error-correcting Hough Transform

Autor: Xu, Chi, Govindarajan, Lakshmi Narasimhan, Cheng, Li

Detecting hand actions from ego-centric depth sequences is a practically challenging problem, owing mostly to the complex and dexterous nature of hand articulations as well as non-stationary camera motion. We address this problem via a Hough transfor

Externí odkaz: http://arxiv.org/abs/1606.02031

Zobrazit plný text záznamu