
-
Horizontal-to-Vertical Video Conversion
Alongside the prevalence of mobile videos, the general public leans towa...
read it
-
Multi-shot Temporal Event Localization: a Benchmark
Current developments in temporal event or action localization usually ta...
read it
-
Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework
Since the label collecting is prohibitive and time-consuming, unsupervis...
read it
-
LAMP: Label Augmented Multimodal Pretraining
Multi-modal representation learning by pretraining has become an increas...
read it
-
SRG-Net: Unsupervised Segmentation for Terracotta Warrior Point Cloud with 3D Pointwise CNN methods
In this paper, we present a seed-region-growing CNN(SRG-Net) for unsuper...
read it
-
Spherical Knowledge Distillation
Knowledge distillation aims at obtaining a small but effective deep mode...
read it
-
Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
Multi-label zero-shot classification aims to predict multiple unseen cla...
read it
-
Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
Click-through rate (CTR) prediction is an essential task in industrial a...
read it
-
CSID: Center, Scale, Identity and Density-aware Pedestrian Detection in a Crowd
Pedestrian detection in a crowd is very challenging due to vastly differ...
read it
-
Correlation Maximized Structural Similarity Loss for Semantic Segmentation
Most semantic segmentation models treat semantic segmentation as a pixel...
read it
-
Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning
An increasing number of well-trained deep networks have been released on...
read it
-
Multi-Objective Generalized Linear Bandits
In this paper, we study the multi-objective bandits (MOB) problem, where...
read it