• Publications
  • Influence
IBM Research TRECVID-2007 Video Retrieval System
TLDR
In this paper, we describe the IBM Research system for indexing, analysis, and retrieval of video as applied to the TREC-2007 video retrieval benchmark. Expand
  • 436
  • 43
  • PDF
Semantic Model Vectors for Complex Video Event Recognition
TLDR
We propose semantic model vectors, an intermediate level semantic representation, as a basis for modeling and detecting complex events in unconstrained real-world videos, such as those from YouTube. Expand
  • 153
  • 9
  • PDF
Recognizing Groceries in situ Using in vitro Training Data
TLDR
We present a new multimedia database of 120 grocery products, GroZi-120. Expand
  • 103
  • 9
  • PDF
Diversity in Faces
TLDR
Face recognition is a long standing challenge in the field of Artificial Intelligence (AI). Expand
  • 52
  • 6
  • PDF
IBM Research and Columbia University TRECVID-2012 Multimedia Event Detection (MED), Multimedia Event Recounting (MER), and Semantic Indexing (SIN) Systems
TLDR
For this year’s TRECVID Multimedia Event Detection task, our team studied high-level visual and audio semantic features, midlevel visual attributes, and sophisticated low-level features. Expand
  • 23
  • 4
  • PDF
IBM Research TRECVID-2010 Video Copy Detection and Multimedia Event Detection System
TLDR
In this paper, we describe the system jointly developed by IBM Research and Columbia University for video copy detection and multimedia event detection applied to the TRECVID-2010 video retrieval benchmark. Expand
  • 37
  • 3
  • PDF
IBM T.J. Watson Research Center, Multimedia Analytics: Modality Classification and Case-Based Retrieval Tasks of ImageCLEF2012
TLDR
In this paper we present the modeling strategies that were applied by the IBM T.J. Watson research team to the modality classi- cation and case-based retrieval tasks of ImageCLEF 2012. Expand
  • 4
  • 2
  • PDF
Large-scale multimedia semantic concept modeling using robust subspace bagging and MapReduce
TLDR
We first propose the robust subspace bagging (RB-SBag) algorithm by augmenting random sub space bagging with forward model selection, which achieves a 10-fold speedup with comparable or even better classification performance than baseline SVMs. Expand
  • 41
  • 1
Learning to Make Better Mistakes: Semantics-aware Visual Food Recognition
TLDR
We propose a visual food recognition framework that integrates the inherent semantic relationships among fine-grained classes. Expand
  • 26
  • 1
  • PDF
You are what you tweet…pic! gender prediction based on semantic analysis of social media images
TLDR
We propose a method to extract user attributes from the pictures posted in social media feeds, specifically gender information, and apply them to the images in each user's feed. Expand
  • 27
  • 1
  • PDF