Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 5
Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition
Mohamed Amer , Michael J. Black , Ivan Laptev
Video in druga učna gradiva
Oznake: computer science;computer vision;video analysis
This paper addresses a new problem, that of multiscale activity recognition. Our goal is to detect and localize a wide range of activities, including individual actions and group activities, which may simultaneously co-occur in high-resolution video. The video resolution allows for digital zoom-in ( ...
Leto: 2012 Vir: videolectures.net
A Unified Framework for Multi-Target Tracking and Collective Activity Recognition
Wongun Choi , Michael J. Black , Ivan Laptev
Video in druga učna gradiva
Oznake: computer science;computer vision;motion and tracking
We present a coherent, discriminative framework for simultaneously tracking multiple people and estimating their collective activities. Instead of treating the two problems separately, our model is grounded in the intuition that a strong correlation exists between a person's motion, their activity, ...
Leto: 2012 Vir: videolectures.net
Detecting Actions, Poses, and Objects with Relational Phraselets
Deva Ramanan , Michael J. Black , Ivan Laptev
Video in druga učna gradiva
Oznake: computer science;computer vision;object recognition;motion and tracking
We present a novel approach to modeling human pose, together with interacting objects, based on compositional models of local visual interactions and their relations. Skeleton models, while flexible enough to capture large articulations, fail to accurately model selfocclusions and interactions. Pose ...
Leto: 2012 Vir: videolectures.net
Action Recognition with Exemplar Based 2.5D Graph Matching
Bangpeng Yao , Michael J. Black , Ivan Laptev
Video in druga učna gradiva
Oznake: computer science;computer vision
This paper deals with recognizing human actions in still images. We make two key contributions. (1) We propose a novel, 2.5D representation of action images that considers both viewindependent pose information and rich appearance information. A 2.5D graph of an action image consists of a set of node ...
Leto: 2012 Vir: videolectures.net
Activity Forecasting
Kris M. Kitani , Michael J. Black , Ivan Laptev
Video in druga učna gradiva
Oznake: computer science;computer vision;semantic computing
We address the task of inferring the future actions of people from noisy visual input. We denote this task activity forecasting. To achieve accurate activity forecasting, our approach models the effect of the physical environment on the choice of human actions. This is accomplished by the use of sta ...
Leto: 2012 Vir: videolectures.net
Št. zadetkov: 5
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: