Video Flame Recognition Based on Feature Fusion and Extreme Learning Machine

Zhong, Chen; Tian, Zhijia; Ding, Hongjun; Ke, Wang

doi:10.1109/cacre50138.2020.9230253

Cited by 1 publication

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another of the many systems performing data fusion and one that is closer to Look&Learn is given in [5]. This system operates on a single image of a video sequence like Look&Learn.…”

Section: Related Work: Image Based Fusion Techniquesmentioning

confidence: 99%

“…This is a major departure from Look&Learn that explicitly through detection creates a Forced Attention Look&Learn image which emphasizes the important semantic features/areas of the scene for video activity recognition. Also, compared to Look&Learn the use of learning is very minimal in [5] involving a single layer network at the end trained on features procedurally extracted from the fused image.…”

Section: Related Work: Image Based Fusion Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Look and learn: forcing attention through input-fusing of important features and raw image data

Grewe

Mahajan

Jain

et al. 2023

Signal Processing, Sensor/Information Fusion, and Target Recognition XXXII

View full text Add to dashboard Cite

This work examines how a forced-attention technique can be applied to the task of Video Activity Recognition. The Look&Learn system performs early fusion of critical detected areas of attention with the original raw image data for training a system for video activity recognition, specifically the task of Squat "Quality" Detection. Look & Learn is compared to previous work, USquat, and achieved a 98.96% accuracy on average compared to the USquat system which achieved 93.75% accuracy demonstrating the improvement that can be gained by Look&Learn's forced-attention technique. Look&Learn is deployed in an Android Application for proof of concept and results presented.

show abstract

“…Another of the many systems performing data fusion and one that is closer to Look&Learn is given in [5]. This system operates on a single image of a video sequence like Look&Learn.…”

Section: Related Work: Image Based Fusion Techniquesmentioning

confidence: 99%

Section: Related Work: Image Based Fusion Techniquesmentioning

confidence: 99%