论文信息 - Self-Similarity is all You Need for Fast and Light-Weight Generic Event Boundary Detection - 字舞流文

Self-Similarity is all You Need for Fast and Light-Weight Generic Event Boundary Detection

Sourabh Vasant Gothe | Jayesh Rajkumar Vachhani | Rishabh Khurana | Pranay Kashyap

[1] Chen Qian,et al. Submission to Generic Event Boundary Detection Challenge@CVPR 2022: Local Context Modeling and Global Boundary Decoding Approach , 2022, ArXiv.

[2] Longyin Wen,et al. SC-Transformer++: Structured Context Transformer for Generic Event Boundary Detection , 2022, ArXiv.

[3] Ruifei He,et al. Masked Autoencoders for Generic Event Boundary Detection CVPR'2022 Kinetics-GEBD Challenge , 2022, ArXiv.

[4] Aaron B. Adcock,et al. PyTorchVideo: A Deep Learning Library for Video Understanding , 2021, ACM Multimedia.

[5] Seon Joo Kim,et al. Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach , 2021, ArXiv.

[6] Lukasz Kaiser,et al. Attention is All you Need , 2017, NIPS.

[7] Fabio Viola,et al. The Kinetics Human Action Video Dataset , 2017, ArXiv.

[8] Luc Van Gool,et al. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition , 2016, ECCV.

[9] Gregory D. Hager,et al. Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation , 2016, ECCV.

[10] D. Reisberg. The Oxford Handbook of Cognitive Psychology , 2013 .