Our experiments demonstrate how integrating group-based cues improves the activity recognition accuracies in detail and show that all of the key parts of GLCIM ...

Images with wider angles usually capture more persons in wider scenes, and recognizing individuals' activities in these images based on existing contextual ...

2015 ACM. Images with wider angles usually capture more persons in wider scenes, and recognizing individuals' activities in these images based on existing ...

ABSTRACT. Images with wider angles usually capture more persons in wider scenes, and recognizing individuals' activities in these images based.

Recognizing Human Activity in Still Images by Integrating Group-Based Contextual Cues · Zheng ZhouKan LiXiangjian He. Computer Science. ACM Multimedia. 2015.

Recognizing multiple mixed group activities from one still image is not a hard problem for humans but remains highly challenging for computer recogni-.

Recognizing human activity in still images by integrating group-based contextual cues. Z Zhou, K Li, X He. Proceedings of the 23rd ACM international ...

Zheng Zhou and Kan Li and Xiangjian He. Recognizing Human Activity in Still Images by Integrating Group-Based Contextual Cues Published in ACM MM, 2015.

The goal of human activity recognition is to examine activities from video sequences or still images. Motivated by this fact, human activity recognition systems ...

We propose a novel method to group individuals in daily life images based on their interactions. It is extremely useful to automatically understand the mutual ...