Pose Guided Dynamic Image Network for Human Action Recognition in Person Centric Videos

Chaudhary, Sachin; Dudhane, Akshay; Patil, Prashant W.; Murala, Subrahmanyam

doi:10.1109/avss.2019.8909835

Cited by 15 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the number of videos from Internet Protocol cameras (IP cameras) for video surveillance increases, understanding video contents such as action recognition [3,16,21] and action localization [14,36] becomes crucial. Moreover, videos with textual descriptions (e.g., titles, captions, or keywords) have encouraged research on multi-modal problems such as video captioning [18,25] and temporal video grounding [4,6,22,35].…”

Section: Introductionmentioning

confidence: 99%

Position-aware Location Regression Network for Temporal Video Grounding

Kim

Yun²,

Choi

2021

2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

The key to successful grounding for video surveillance is to understand a semantic phrase corresponding to important actors and objects. Conventional methods ignore comprehensive contexts for the phrase or require heavy computation for multiple phrases. To understand comprehensive contexts with only one semantic phrase, we propose Position-aware Location Regression Network (PLRN) which exploits position-aware features of a query and a video. Specifically, PLRN first encodes both the video and query using positional information of words and video segments. Then, a semantic phrase feature is extracted from an encoded query with attention. The semantic phrase feature and encoded video are merged and made into a contextaware feature by reflecting local and global contexts. Finally, PLRN predicts start, end, center, and width values of a grounding boundary. Our experiments show that PLRN achieves competitive performance over existing methods with less computation time and memory.

show abstract