all AI news
View while Moving: Efficient Video Recognition in Long-untrimmed Videos
March 21, 2024, 4:46 a.m. | Ye Tian, Mengyu Yang, Lanshan Zhang, Zhizhen Zhang, Yang Liu, Xiaohui Xie, Xirong Que, Wendong Wang
cs.CV updates on arXiv.org arxiv.org
Abstract: Recent adaptive methods for efficient video recognition mostly follow the two-stage paradigm of "preview-then-recognition" and have achieved great success on multiple video benchmarks. However, this two-stage paradigm involves two visits of raw frames from coarse-grained to fine-grained during inference (cannot be parallelized), and the captured spatiotemporal features cannot be reused in the second stage (due to varying granularity), being not friendly to efficiency and computation optimization. To this end, inspired by human cognition, we propose …
abstract arxiv benchmarks cs.cv fine-grained however inference moving multiple paradigm raw recognition stage success type video videos view
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Data Engineering Manager
@ Microsoft | Redmond, Washington, United States
Machine Learning Engineer
@ Apple | San Diego, California, United States