activity
20162021
most citedNatural Language Video Localization: A Revisit in Span-based Question Answering Framework

93 citations · 100 across the 6 of their papers we have counts for

collaborators

12 papers

cs.LG2021

RCT: Resource Constrained Training for Edge AI

Tian Huang, Tao Luo, Ming Yan +2

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…

cs.CL202193 cited

Natural Language Video Localization: A Revisit in Span-based Question Answering Framework

Hao Zhang, Aixin Sun, Wei Jing +3

Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve th…

cs.CV2020

Deep N-ary Error Correcting Output Codes

Hao Zhang, Joey Tianyi Zhou, Tianying Wang +2

Ensemble learning consistently improves the performance of multi-class classification through aggregating a series of base classifiers. To this end, data-independent ensemble metho…

cs.LG2020

EDCompress: Energy-Aware Model Compression for Dataflows

Zhehui Wang, Tao Luo, Joey Tianyi Zhou +1

Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compressi…

cs.DC2020

Two-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning

Renuga Kanagavelu, Zengxiang Li, Juniarto Samsudin +7

Countries across the globe have been pushing strict regulations on the protection of personal or private data collected. The traditional centralized machine learning method, where…

cs.CV2020

Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations

Shaohua Li, Xiuchao Sui, Jie Fu +2

Convolutional Neural Networks (CNNs) are known to be brittle under various image transformations, including rotations, scalings, and changes of lighting conditions. We observe that…