Existing methods on video-based action recognition are generally view-dependent, ie,
performing recognition from the same views seen in the training data. We present a novel …

Recent progress in deep learning is essentially based on a “big data for small tasks”
paradigm, under which massive amounts of data are used to train a classifier for a single …

Action recognition and pose estimation from video are closely related tasks for
understanding human motion, most methods, however, learn separate models and combine …

Many videos depict people, and it is their interactions that inform us of their activities, relation
to one another and the cultural and social setting. With advances in human action …

In this paper, we present a 4D human-object interaction (4DHOI) model for solving three
vision tasks jointly: i) event segmentation from a video sequence, ii) event recognition and …

Image animation is to animate a still image of the object of interest using poses extracted
from another video sequence. Through training on a large-scale video dataset, most existing …

An optical flow based approach for recognizing human actions and human-human
interactions in video sequences has been addressed in this paper. We propose a local …

In this paper, we proposed a deep convolutional network architecture for recognizing human
actions in videos using action bank features. Action bank features computed against of a …

This paper presents a novel method for automatically detecting and tracking news topics
from multimodal TV news data. We propose a multimodal topic and-or graph (MT-AOG) to …

Developing an expert text detection system for video indexing and retrieving is a challenging
task due to low resolution, complex background, non-illumination and movement of text …