Decentralized optimization is effective to save communication in large-s...
Space-time memory (STM) based video object segmentation (VOS) networks
u...
3D-aware image synthesis aims to generate images of objects from multipl...
Temporal representation is the cornerstone of modern action detection
te...
Cross-modality interaction is a critical component in Text-Video Retriev...
Decentralized SGD is an emerging training method for deep learning known...
Communication overhead hinders the scalability of large-scale distribute...
The scale of deep learning nowadays calls for efficient distributed trai...
Recent works have shown that convolutional networks have substantially
i...
Few-shot class-incremental learning (FSCIL) aims to design machine learn...
Researches have demonstrated that low bit-width (e.g., INT8) quantizatio...
Nowadays, live-stream and short video shopping in E-commerce have grown
...
In many real-world datasets, like WebVision, the performance of DNN base...
We present a deep reinforcement learning method of progressive view
inpa...
With the prevalence of accessible depth sensors, dynamic human body skel...