Related papers: Free-Form Composition Networks for Egocentric Acti…

Face performance capture and reenactment techniques use multiple cameras and sensors, positioned at a distance from the face or mounted on heavy wearable devices. This limits their applications in mobile and outdoor environments. We present…

This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR). The proposed STANNCR is based on action component and incorporates the…

For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for understanding short semantic actions cannot be directly…

Temporal action localization has long been researched in computer vision. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e., proposals in two-stage methods and segments in one-stage…

Efficiently modeling spatial-temporal information in videos is crucial for action recognition. To achieve this goal, state-of-the-art methods typically employ the convolution operator and the dense interaction modules such as non-local…

We bring together ideas from recent work on feature design for egocentric action recognition under one framework by exploring the use of deep convolutional neural networks (CNN). Recent work has shown that features such as hand appearance,…

Traffic prediction is a critical component of intelligent transportation systems, enabling applications such as congestion mitigation and accident risk prediction. While recent research has explored both graph-based and grid-based…

Egocentric action anticipation consists in predicting a future action the camera wearer will perform from egocentric video. While the task has recently attracted the attention of the research community, current approaches assume that the…

Network autocorrelation models have been widely used for decades to model the joint distribution of the attributes of a network's actors. This class of models can estimate both the effect of individual characteristics as well as the network…

Existing few-shot learning (FSL) methods assume that there exist sufficient training samples from source classes for knowledge transfer to target classes with few training samples. However, this assumption is often invalid, especially when…

Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation…

Collecting large-scale egocentric video datasets with dense spatial and temporal annotations is costly, slow, and often constrained by environmental biases, privacy constraints, and limited coverage of interaction patterns. While synthetic…

The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition. Currently most systems only classify dataset with a couple of dozens different actions. Moreover, feature…

While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…

Learned video compression has recently emerged as an essential research topic in developing advanced video compression technologies, where motion compensation is considered one of the most challenging issues. In this paper, we propose a…

In this paper we propose a novel Temporal Attentive Relation Network (TARN) for the problems of few-shot and zero-shot action recognition. At the heart of our network is a meta-learning approach that learns to compare representations of…

Videos are more well-organized curated data sources for visual concept learning than images. Unlike the 2-dimensional images which only involve the spatial information, the additional temporal dimension bridges and synchronizes multiple…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming processes. This paper addresses the problem of organizing…

Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…