Compact Representations of Videos Through Dominant and Multiple Motion Estimation
Explore this paper's citation graph
Summary
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.
- Type
- article
- Published
- 1996-08-01
- Cited by
- 384
- References
- 44
- Access
- Open access
- OpenAlex
- https://openalex.org/W2119444142
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2594648
Keywords
Computer science, Search engine indexing, Computer vision, Motion (physics), Artificial intelligence
References
- Sequential and competitive methods for estimation of multiple motions
- Model-based 2D&3D dominant motion estimation for mosaicing and video representation
- Automatic and semiautomatic methods for image annotation and retrieval in query by image content (QBIC)
- Robust statistics: the approach based on influence functions
- Salient video stills: content and context preserved
- Robust motion analysis
- Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects
- Estimation of parameters for a mixture of normal distributions
- Robust Multiresolution Estimation of Parametric Motion Models
- QBIC project: querying images by content, using color, texture, and shape
- Ordinal characteristics of transparency.
- Representation of scenes from collections of images
- A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH
- Direct methods for visual scene reconstruction
- Mixture models for optical flow computation
- Mosaic based representations of video sequences and their applications
- Layered representation of motion video using robust maximum-likelihood estimation of mixture models and MDL encoding
- Direct multi-resolution estimation of ego-motion and structure from motion
- Direct recovery of shape from multiple views: a parallax based approach
- Layered representation for motion analysis
Cited by
- Detection and generalization of spatio-temporal trajectories for motion imagery
- Mining Home Video for Photos
- SOFSEM 2002: Theory and Practice of Informatics
- Panoramic Image Mosaics
- Détection et suivi d'objets en mouvement dans des scenes complexes, application a la surveillance des conducteurs
- Multimedia asset management for post-production
- Parallax-Based View Synthesis from Uncalibrated Images
- PanoramaExcdrpts: Video Cataloging by Automatic Synthesis and Layout of Panoramic Images
- Model- and Exemplar-based Robust Head Pose Tracking Under Occlusion and Varying Expression
- Homography Optimization for Circular Panorama Generation Using Freely Taken Images
- Extraction et analyse d'objets-clés pour la structuration d'images et de vidéos. (Extraction and Analysis of Key-Objects for Image and Video Structuring)
- On the synergy between indexing and compression representations for video sequences
- Dynamic Video Mosaics and Augmented Reality for Subsea Inspection and Monitoring
- Segmentation and tracking of multiple objects in video sequences
- Spatiotemporal Video Modeling for Content Summarization
- Object tracking: Appearance modeling and feature learning
- Les tubes de mouvement : nouvelle représentation pour les séquences d'images. (Motion tubes: a new representation for image sequences)
- Estimation et analyse de champs denses de vitesses d'écoulements fluides. (Estimation and analysis of dense fluid flows)
- 3D reconstruction of dynamic scenes
- Sprite learning and object category recognition using invariant features
Related papers
- A closer look on indexing and indexing parameters
- A Review on Indexing Techniques and its application in Multilingual Information Retrieval System
- Analysis in indexing: document and domain centered approaches
- Indexing: Another way for authors to communicate
- The problems of Chinese Library Classification(CLC) in indexing of scientific and technical journals and the indexing principles
- Discussion on the Accurate Modeling of Cylindrical Indexing Cam
- Multiple Entry Indexing and Double Indexing
- The NLM Indexing Initiative
- General motion estimation and segmentation