research
∙
10/14/2022
Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization
Decentralized optimization is effective to save communication in large-s...
share
research
∙
05/08/2022
Recurrent Dynamic Embedding for Video Object Segmentation
Space-time memory (STM) based video object segmentation (VOS) networks u...
research
∙
04/13/2022
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis
3D-aware image synthesis aims to generate images of objects from multipl...
research
∙
03/14/2022
RCL: Recurrent Continuous Localization for Temporal Action Detection
Temporal representation is the cornerstone of modern action detection te...
research
∙
03/14/2022
Disentangled Representation Learning for Text-Video Retrieval
Cross-modality interaction is a critical component in Text-Video Retriev...
research
∙
10/26/2021
Exponential Graph is Provably Efficient for Decentralized Deep Training
Decentralized SGD is an emerging training method for deep learning known...
research
∙
05/19/2021
Accelerating Gossip SGD with Periodic Global Averaging
Communication overhead hinders the scalability of large-scale distribute...
research
∙
04/24/2021
DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training
The scale of deep learning nowadays calls for efficient distributed trai...
research
∙
04/08/2021
Multiple Object Tracking with Correlation Learning
Recent works have shown that convolutional networks have substantially i...
research
∙
04/07/2021
Few-Shot Incremental Learning with Continually Evolved Classifiers
Few-shot class-incremental learning (FSCIL) aims to design machine learn...
research
∙
02/09/2021
Distribution Adaptive INT8 Quantization for Training CNNs
Researches have demonstrated that low bit-width (e.g., INT8) quantizatio...
research
∙
02/09/2021
Fashion Focus: Multi-modal Retrieval System for Video Commodity Localization in E-commerce
Nowadays, live-stream and short video shopping in E-commerce have grown ...
research
∙
08/25/2020
Weakly Supervised Learning with Side Information for Noisy Labeled Images
In many real-world datasets, like WebVision, the performance of DNN base...
research
∙
03/10/2019
Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
We present a deep reinforcement learning method of progressive view inpa...
research
∙
11/29/2018