Can I read Prediction and Description of Near-Future Activities in Video on EtoBox?

Prediction and Description of Near-Future Activities in Video by Tahmida Mahmud; Mohammad Billah; Mahmudul Hasan; Amit K. Roy-Chowdhury is a Computer Science article available to read on EtoBox.

What is Prediction and Description of Near-Future Activities in Video about?

Most of the existing works on human activity analysis focus on recognition or early recognition of the activity labels from complete or partial observations. Similarly, almost all of the existing video captioning approaches focus on the observed events in videos. Predicting the labels and the captions of future activities where no frames of the predicted activities have been observed is a challenging problem, with important applications that require anticipatory response. In this work, we propose a system that can infer the labels and the captions of a sequence of future activities. Our proposed network for label prediction of a future activity sequence has three branches where the first branch takes visual features from the objects present in the scene, the second branch takes observed sequential activity features, and the third branch captures the last observed activity features. The predicted labels and the observed scene context are then mapped to meaningful captions using a sequence-to-sequence learning-based method. Experiments on four challenging activity analysis datasets and a video description dataset demonstrate that our label prediction approach achieves comparable perf

Who reads Prediction and Description of Near-Future Activities in Video?

Author

Tahmida Mahmud; Mohammad Billah; Mahmudul Hasan; Amit K. Roy-Chowdhury

Publisher

Elsevier BV

Published

2021

Language

EN

Field

Computer Science (Physical Sciences)