• Publications
  • Influence
A generic framework of user attention model and its application in video summarization
TLDR
In this paper, we present a generic framework of a user attention model, which estimates the attentions viewers may pay to video contents. Expand
  • 503
  • 40
Tag ranking
Social media sharing web sites like Flickr allow users to annotate images with free tags, which significantly facilitate Web image search and organization. However, the tags associated with an imageExpand
  • 461
  • 39
  • PDF
Spatio-Temporal AutoEncoder for Video Anomaly Detection
TLDR
Anomalous events detection in real-world video scenes is a challenging problem due to the complexity of "anomaly" as well as the cluttered backgrounds, objects and motions in the scenes. Expand
  • 101
  • 18
  • PDF
Clickage: towards bridging semantic and intent gaps via mining click logs of search engines
TLDR
The semantic gap between low-level visual features and high-level semantics has been investigated for decades but still remains a big challenge in multimedia. Expand
  • 96
  • 17
  • PDF
Ensemble Manifold Regularization
TLDR
We propose an ensemble manifold regularization (EMR) framework to approximate the intrinsic manifold by combining several initial guesses. Expand
  • 227
  • 14
  • PDF
Unified Video Annotation via Multigraph Learning
TLDR
We propose a method named optimized multigraph-based semi-supervised learning (OMG-SSL), which aims to simultaneously tackle these difficulties in a unified scheme. Expand
  • 446
  • 13
  • PDF
Correlative multi-label video annotation
TLDR
We propose a third paradigm which simultaneously classifies concepts and models correlations between them in a single step by using a novel Correlative Multi-Label (CML) framework. Expand
  • 453
  • 13
  • PDF
Joint multi-label multi-instance learning for image classification
TLDR
We propose an integrated multi- label multi-instance learning (MLMIL) approach based on hidden conditional random fields (HCRFs), which simultaneously captures both the connections between semantic labels and regions, and the correlations among the labels in a single formulation. Expand
  • 237
  • 13
  • PDF
Online video recommendation based on multimodal fusion and relevance feedback
TLDR
This paper presents a novel online video recommendation system based on multimodal fusion and relevance feedback to automatically adjust intra-weights within each modality by users' click-though data. Expand
  • 128
  • 13
  • PDF
MSRA-MM 2.0: A Large-Scale Web Multimedia Dataset
TLDR
In this paper, we introduce the second version of Microsoft Research Asia Multimedia (MSRA-MM), a dataset that aims to facilitate research in multimedia information retrieval and related areas. Expand
  • 90
  • 12
  • PDF
...
1
2
3
4
5
...