Understanding human actions in visual data is tied to advances in complementary research
areas including object recognition, human dynamics, domain adaptation and semantic …

The video classification task has gained significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …

Human activity recognition (HAR) is a complex and multifaceted problem. The research
community has reported numerous approaches to perform HAR. Along with HAR …

General human action recognition requires understanding of various visual cues. In this
paper, we propose a network architecture that computes and integrates the most important …

Spatio-temporal representations in frame sequences play an important role in the task of
action recognition. Previously, a method of using optical flow as a temporal information in …

This paper introduces a fast and efficient network architecture, NeXtVLAD, to aggregate
frame-level features into a compact feature vector for large-scale video classification. Briefly …

Zero-shot learning for visual recognition, eg, object and action recognition, has recently
attracted a lot of attention. However, it still remains challenging in bridging the semantic gap …

This paper presents the method that underlies our submission to the untrimmed video
classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal …

Video classification task has gained a significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …

We propose an action recognition framework using Gen-erative Adversarial Networks. Our
model involves train-ing a deep convolutional generative adversarial network (DCGAN) …