Search Results for author:
Found 18 papers, 4 papers with code
Estimation of Reliable Proposal Quality for Temporal Action Detection
For the region perspective, we introduce Region Evaluate Module (REM) which uses a new and efficient sampling method for proposal feature representation containing more contextual information compared with point feature to refine category score and proposal boundary.
Dense Learning based Semi-Supervised Object Detection
Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data.
Structure-Aware Motion Transfer with Deformable Anchor Model
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
Learning Pixel-Level Distinctions for Video Highlight Detection
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
This shows that DMA-Net provides a good tradeoff between segmentation quality and speed for semantic segmentation in street scenes.
Move As You Like: Image Animation in E-Commerce Scenario
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting
In crowd counting, due to the problem of laborious labelling, it is perceived intractability of collecting a new large-scale dataset which has plentiful images with large diversity in density, scene, etc.
VirFace: Enhancing Face Recognition via Unlabeled Shallow Data
In this paper, we propose a novel face recognition method, named VirFace, to effectively apply the unlabeled shallow data for face recognition.
Interactive Self-Training With Mean Teachers for Semi-Supervised Object Detection
Specifically, to alleviate the instability among the detection results in different iterations, we propose using nonmaximum suppression to fuse the detection results from different iterations.
Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources
This is because the classification paradigm needs to train a fully connected layer as the category classifier, and its parameters will be in the hundreds of millions if the training dataset contains millions of identities.
On Identification of Boolean Control Networks
A new analytical framework consisting of two phenomena: single sample and multiple samples, is proposed to deal with the identification problem of Boolean control networks (BCNs) systematically and comprehensively.
All-fiber mode-locked ytterbium-doped fiber laser with a saturable absorber based on nonlinear Kerr beam cleanup effect
We theoretically and experimentally demonstrate a novel mode-locked ytterbium-doped fiber laser with a saturable absorber based on nonlinear Kerr beam cleanup effect.
Optics
AIBench Training: Balanced Industry-Standard AI Training Benchmarking
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
Continual Local Replacement for Few-shot Learning
The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data.
SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery
Renewable energy such as solar power is critical to fight the ever more serious climate change.
Learning Continually from Low-shot Data Stream
To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data stream over time without forgetting the previous knowledge.
AIBench: An Industry Standard Internet Service AI Benchmark Suite
On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.
