• Publications
  • Influence
INSTRE: A New Benchmark for Instance-Level Object Retrieval and Recognition
  • S. Wang, S. Jiang
  • Computer Science
  • ACM Trans. Multim. Comput. Commun. Appl.
  • 5 February 2015
TLDR
We introduce INSTRE, a new benchmark for instance-level object retrieval and recognition. Expand
  • 58
  • 13
Scene Recognition with CNNs: Objects, Scales and Dataset Bias
TLDR
We address two related problems: 1) scale induced dataset bias in multi-scale convolutional neural network (CNN) architectures and 2) how to combine effectively scene-centric and object-centric knowledge (i.e. Places and ImageNet) in CNNs. Expand
  • 118
  • 8
  • PDF
Building contextual visual vocabulary for large-scale image applications
TLDR
We propose an effective visual vocabulary generation framework containing three novel contributions: 1) we propose aneffective unsupervised local feature refinement strategy; 2) we consider local features in groups to model their spatial contexts; 3) we further learn a discriminant distance metric between local feature groups, which we call discriminant group distance. Expand
  • 133
  • 8
  • PDF
Event Tactic Analysis Based on Broadcast Sports Video
TLDR
We propose a novel approach to extract tactic information from the attack events in broadcast soccer video and present them in a tactic mode to the coaches and sports professionals. Expand
  • 87
  • 8
  • PDF
Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness
TLDR
In object detection, disparities in distributions between the training samples and the test ones are often inevitable, resulting in degraded performance for application scenarios. Expand
  • 50
  • 8
Affective Visualization and Retrieval for Music Video
TLDR
In modern times, music video (MV) has become an important favorite pastime to people because of its conciseness, convenience, and the ability to bring both audio and visual experiences to audiences. Expand
  • 92
  • 7
  • PDF
Adding Affine Invariant Geometric Constraint for Partial-Duplicate Image Retrieval
TLDR
The spring up of large numbers of partial-duplicate images on the internet brings a new challenge to image retrieval systems. Expand
  • 33
  • 5
  • PDF
Detecting Violent Scenes in Movies by Auditory and Visual Cues
TLDR
To detect violence in movies, we present a three-stage method integrating visual and auditory cues. Expand
  • 58
  • 4
  • PDF
A framework for flexible summarization of racquet sports video using multiple modalities
TLDR
We propose a novel flexible video content summarization framework based on the periodicity of video shot content and audio keywords in racquet sports video. Expand
  • 43
  • 4
  • PDF
Playfield detection using adaptive GMM and its application
TLDR
We propose an adaptive GMM based algorithm for playfield detection. Expand
  • 40
  • 4
  • PDF