Timezone: »

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Zuxuan Wu · Caiming Xiong · Yu-Gang Jiang · Larry Davis

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #175

This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios. Exploiting decent yet computationally efficient features derived at a coarse scale with a lightweight CNN model, LiteEval dynamically decides on-the-fly whether to compute more powerful features for incoming video frames at a finer scale to obtain more details. This is achieved by a coarse LSTM and a fine LSTM operating cooperatively, as well as a conditional gating module to learn when to allocate more computation. Extensive experiments are conducted on two large-scale video benchmarks, FCVID and ActivityNet, and the results demonstrate LiteEval requires substantially less computation while offering excellent classification accuracy for both online and offline predictions.

Author Information

Zuxuan Wu (University of Maryland)
Caiming Xiong (Salesforce)
Yu-Gang Jiang (Fudan University)
Larry Davis (University of Maryland)

More from the Same Authors