• Publications
  • Influence
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
TLDR
Learning effective feature representations and similarity measures are crucial to the retrieval performance of a content-based image retrieval (CBIR) system. Expand
  • 608
  • 36
  • PDF
Hierarchical spatio-temporal context modeling for action recognition
TLDR
The problem of recognizing actions in realistic videos is challenging yet absorbing owing to its great potentials in many practical applications. Expand
  • 319
  • 22
A density-based method for adaptive LDA model selection
TLDR
We study the inherent connection between the best topic structure and the distances among topics in Latent Dirichlet allocation (LDA), and propose a method of adaptively selecting the best LDA model based on density. Expand
  • 248
  • 13
Tracking Web Video Topics: Discovery, Visualization, and Monitoring
Despite the massive growth of web-shared videos in Internet, efficient organization and monitoring of videos remains a practical challenge. While nowadays broadcasting channels are keen to monitorExpand
  • 36
  • 11
  • PDF
Motion compensation memory access optimization strategies for H.264/AVC decoder
  • R. Wang, J. Li, C. Huang
  • Computer Science
  • Proceedings. (ICASSP '05). IEEE International…
  • 18 March 2005
TLDR
H.264/AVC provides up to 50% gain in compression efficiency over a wide range of bit rates and video resolutions compared to previous standards. Expand
  • 41
  • 7
A Novel Method to Compensate Variety of Illumination in Face Detection
TLDR
This paper describes a novel method LogAbout to compensate variety of illumination in face detection. Expand
  • 18
  • 7
  • PDF
Scale-Adaptive Convolutions for Scene Parsing
TLDR
We propose a scale-adaptive convolution to acquire flexiblesize receptive fields during scene parsing, which can be adjusted automatically according to the various sizes of scene images. Expand
  • 121
  • 6
  • PDF
Hierarchical spatio-temporal context modeling for action recognition
TLDR
The problem of recognizing actions in realistic videos is challenging yet absorbing owing to its great potentials in many practical applications. Expand
  • 141
  • 6
  • PDF
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks
TLDR
We propose a novel prediction framework called Deep Temporal Context Networks (DTCN) by incorporating both temporal context and temporal attention into account. Expand
  • 55
  • 6
  • PDF
Automatic Rumor Detection on Microblogs: A Survey
TLDR
The ever-increasing amount of multimedia content on modern social media platforms are valuable in many applications. Expand
  • 22
  • 6
  • PDF