• Publications
  • Influence
Geodesic flow kernel for unsupervised domain adaptation
In real-world applications of visual recognition, many factors - such as pose, illumination, or image quality - can cause a significant mismatch between the source domain on which classifiers areExpand
  • 1,334
  • 361
  • PDF
The pyramid match kernel: discriminative classification with sets of image features
Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification methods can learnExpand
  • 1,526
  • 128
  • PDF
Relative attributes
  • D. Parikh, K. Grauman
  • Computer Science
  • International Conference on Computer Vision
  • 6 November 2011
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person is ‘smiling’ or not, aExpand
  • 814
  • 101
  • PDF
Kernelized locality-sensitive hashing for scalable image search
  • B. Kulis, K. Grauman
  • Computer Science
  • IEEE 12th International Conference on Computer…
  • 1 December 2009
Fast retrieval methods are critical for large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance functions into aExpand
  • 811
  • 94
  • PDF
Key-segments for video object segmentation
We present an approach to discover and segment foreground object(s) in video. Given an unannotated video sequence, the method first identifies object-like regions in any frame according to bothExpand
  • 455
  • 82
  • PDF
Video Summarization with Long Short-Term Memory
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequentialExpand
  • 292
  • 69
  • PDF
Kernelized Locality-Sensitive Hashing
  • B. Kulis, K. Grauman
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 June 2012
Fast retrieval methods are critical for many large-scale and data-driven vision applications. Recent work has explored ways to embed high-dimensional features or complex distance functions into aExpand
  • 294
  • 54
  • PDF
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos
We propose an end-to-end learning framework for segmenting generic objects in videos. Our method learns to combine appearance and motion information to produce pixel level segmentation masks for allExpand
  • 202
  • 50
  • PDF
Discovering important people and objects for egocentric video summarization
We developed an approach to summarize egocentric video. We introduced novel egocentric features to train a regressor that predicts important regions. Using the discovered important regions, ourExpand
  • 555
  • 49
  • PDF
Observe locally, infer globally: A space-time MRF for detecting abnormal activities with incremental updates
We propose a space-time Markov random field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboringExpand
  • 331
  • 48