• Publications
  • Influence
Query by Image and Video Content: The QBIC System
The QBIC system is described and its query capabilities are demonstrated, which allows queries on large image and video databases based on example images, user-constructed sketches and drawings, selected color and texture patterns, camera and object motion, and other graphical information.
Fast Similarity Search in the Presence of Noise, Scaling, and Translation in Time-Series Databases
We introduce a new model of similarity of time sequences that captures the intuitive notion that two sequences should be considered similar if they have enough non-overlapping time-ordered pairs of
Efficient Color Histogram Indexing for Quadratic Form Distance Functions
An improved shipping container having novel locking features in the end panel and corner flaps and improved bulge resistance at the end panels from sideward bulge of the product.
Compact Representations of Videos Through Dominant and Multiple Motion Estimation
  • H. Sawhney, S. Ayer
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1 August 1996
This paper presents robust algorithms to automatically derive compact representations of scenes and objects from the motion information and presents simultaneous multiple motion estimation and representation of motion video using layered representations.
Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding
  • S. Ayer, H. Sawhney
  • Mathematics, Computer Science
    Proceedings of IEEE International Conference on…
  • 20 June 1995
This paper presents one such formulation based on maximum likelihood estimation (MLE) of mixture models and the minimum description length (MDL) encoding principle of layered motion representation, and examines how many motion models adequately describe image motion.
A global matching framework for stereo computation
Several key components of this framework are explored including (1) three color segmentation based depth representations, (2) an incremental warping algorithm that dramatically reduces the computational complexity, and (3) scene constraints such as the smoothness constraint and the color similarity constraint.
Evaluation of low-level features and their combinations for complex event detection in open source videos
This paper considers 7 different low-level features, both static and dynamic, using BoW descriptors within an SVM approach for event detection, and presents performance results on the 15 MED11 events for each of the features as well as their combinations using a number of early and late fusion strategies.
Robust Video Mosaicing through Topology Inference and Local to Global Alignment
This research attacked the problem of piecing together individual frames in a video sequence to create seamless panoramas using inexpensive cameras and relatively free hand motions.
Recognition and volume estimation of food intake using a mobile device
This paper combines several vision techniques (visual recognition and 3D reconstruction) to achieve quantitative food intake estimation and presents a system that improves accuracy of food intake assessment using computer vision techniques.
Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection
A novel multi-cue driven adaptive bilateral filter is proposed to substitute the original anisotropic diffusion process, and it is able to adaptively control the diffusion process according to the occlusion detection, image intensity Dissimilarity, and motion dissimilarity.