8,530 Hits in 5.4 sec

Matching Faces with Textual Cues in Soccer Videos

Marco Bertini, Alberto Bimbo, Walter Nunziati
2006 2006 IEEE International Conference on Multimedia and Expo  
In soccer videos, most significant actions are usually followed by close-up shots of players that take part in the action itself.  ...  text caption showing its name.  ...  Text detection and recognition Text detection and recognition in videos still presents several issues that are to be solved, in particular when dealing with scene text.  ... 
doi:10.1109/icme.2006.262444 dblp:conf/icmcs/BertiniBN06 fatcat:rkzvbc62e5aupnzah5xeukxlhm

Guided Text Spotting for Assistive Blind Navigation in Unfamiliar Indoor Environments [chapter]

Xuejian Rong, Bing Li, J. Pablo Muñoz, Jizhong Xiao, Aries Arditi, Yingli Tian
2016 Lecture Notes in Computer Science  
Specifically, a novel spatial-temporal text localization algorithm is proposed to localize and prune text regions, by integrating strokespecific features with a subsequent text tracking process.  ...  Scene text in indoor environments usually preserves and communicates important contextual information which can significantly enhance the independent travel of blind and visually impaired people.  ...  However, extracting scene text from mobile devices is challenging due to 1) cluttered backgrounds with noise, blur, and non-text background outliers, such as grids and bricks; 2) diversity of text patterns  ... 
doi:10.1007/978-3-319-50832-0_2 fatcat:mrtt5tfsobh4bp5wbrg3qrwbsu

Book2Movie: Aligning video scenes with book chapters

Makarand Tapaswi, Martin Bauml, Rainer Stiefelhagen
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We propose an efficient method to compute an alignment between book chapters and video scenes using matching dialogs and character identities as cues.  ...  Film adaptations of novels often visually display in a few shots what is described in many pages of the source novel. In this paper we present a new problem: to align book chapters with video scenes.  ...  Characters in videos To obtain a list of names which appear in each scene, we first perform face detection and tracking.  ... 
doi:10.1109/cvpr.2015.7298792 dblp:conf/cvpr/TapaswiBS15 fatcat:4u3s7gk4znf4vn5bvl362kgvdi

Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN [article]

Cheng-Bin Jin, Shengzhe Li, Hakil Kim
2017 arXiv   pre-print
The proposed action detection model simultaneously localizes and recognizes the actions of multiple individuals in video surveillance using appearance-based temporal features with multi-CNN.  ...  introduce and make available to the community with this paper.  ...  pedestrian tracking using multiple fixed cameras).  ... 
arXiv:1710.03383v1 fatcat:jdvcynji6bh2tevlmoyb2qbz7e

Comparative Study on Text Detection and Recognition from Lecture Videos

Ashima Godha, Rahul Sharma
2019 International Journal of Information Systems and Computer Sciences  
But, due to variations in text style, size, alignment of text, as well as orientation of text and low contrast of the image and complex background make challenging the extraction of text.  ...  Lecture videos are rich with textual information and to be able to understand the text is quite useful for larger video understanding/analysis applications.  ...  The figures, images and text in lecture videos are vital cues for understanding any lecture video.  ... 
doi:10.30534/ijiscs/2019/01822019 fatcat:3k2nya3hcvdw5h6klw5s6odkcu

Efficient Non-iterative Domain Adaptation of Pedestrian Detectors to Video Scenes

Kyaw Kyaw Htike, David C. Hogg
2014 2014 22nd International Conference on Pattern Recognition  
Pedestrian detection is an essential step in many important applications of Computer Vision.  ...  Unsurprisingly, the performance of a detector on a new scene can be improved by tailoring the detector to the specific viewpoint, background and imaging conditions of the scene.  ...  with pedestrian detections in the frames of the video.  ... 
doi:10.1109/icpr.2014.123 dblp:conf/icpr/HtikeH14 fatcat:hbcifiow4rdojpdtd7h2mjw5x4

Automatic adaptation of a generic pedestrian detector to a specific traffic scene

Meng Wang, Xiaogang Wang
2011 CVPR 2011  
An important feature of the proposed framework is to utilize unsupervisedly learned models of vehicle and pedestrian paths, together with multiple other cues such as locations, sizes, appearance and motions  ...  The effectiveness of different cues and clustering steps is evaluated through experiments.  ...  Introduction Detecting pedestrians from video sequences is of great interest in video surveillance in traffic scenes (see an example in Figure 1 (a) ).  ... 
doi:10.1109/cvpr.2011.5995698 dblp:conf/cvpr/WangW11 fatcat:opoi34ntwff43pzbv75uooxzxu

Exploring object segmentation methods in visual surveillance for human activity recognition

Sandipkumar M Vaniya, B. Bharathi
2016 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC)  
as security and surveillance, sports and gaming, healthcare, person identification at distance, crowd behavior analysis, suspicious event detection and alarming in public/private places, traffic management  ...  In recent years, human activity recognition in intelligent visual surveillance has drawn much attention in the field of video analysis technology due to the growing demand from many applications, such  ...  In complex and cluttered scene with moderate number of moving objects (e.g. 10-15) the problem of detecting and tracking the objects is significantly complicated by occlusion, where an object may be partially  ... 
doi:10.1109/icgtspicc.2016.7955356 fatcat:stlalaad7jacxkqaxwbhfpnrn4

Wide-area motion imagery (WAMI) exploitation tools for enhanced situation awareness

Erik Blasch, Guna Seetharaman, Kannappan Palaniappan, Haibin Ling, Genshe Chen
2012 2012 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)  
The advent of streaming feeds of full-motion video (FMV) and wide-area motion imagery (WAMI) have overloaded an image analyst's capacity to detect patterns, movements, and patterns of life.  ...  To aid in the process of WAMI exploitation, we explore computer vision and pattern recognition methods to cue the user to salient information.  ...  Cues Cues (targets): Image processing for detection, segmentation, classification, and identification require extensions to semantics and SA, as shown in Fig. 4 .  ... 
doi:10.1109/aipr.2012.6528198 dblp:conf/aipr/BlaschSPLC12 fatcat:iv3ek6pdpfdkxkgob5ogynr56e


Snehal S Gaikwad ., S. L. Nalbalwar .
2019 International Journal of Engineering Applied Sciences and Technology  
Multilingual character detection and recognition from video subtitles, scenes and documents is additionally getting high consideration on this subject.  ...  Different workshops and conferences are being sorted out on global level giving further ascent to advancements in field of character detection and recognition.  ...  Also, scene text detection in video is time consuming.  ... 
doi:10.33564/ijeast.2019.v04i03.062 fatcat:6tswkhkmwbcfnne6tk6z2jm6jm

A New Unified Method for Detecting Text from Marathon Runners and Sports Players in Video [article]

Sauradip Nag, Palaiahnakote Shivakumara, Umapada Pal, Tong Lu, Michael Blumenstein
2020 arXiv   pre-print
Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures  ...  The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions.  ...  We also thank the anonymous reviewers for their constructive suggestions and comments to improve the quality and clarity of the work.  ... 
arXiv:2005.12524v1 fatcat:qbh35nk2mbctdgc5o6lspgkm5i

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection has attracted a lot of interest in computer vision and recently various heuristic computational  ...  It not only focuses on the methods to detect saliency objects, but also reviews the works related to spatio temporal video attention detection technique in video sequences.  ...  The robustness and efficiency The background smoothing is very complex 5 Visual attention detection in video sequences using spatiotemporal cues Zhai, [2006] Spatiotemporal video attention  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

Text Detection and Recognition in Imagery: A Survey

Qixiang Ye, David Doermann
2015 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Special issues associated with the enhancement of degraded text and the processing of video text, multi-oriented, perspectively distorted and multilingual text are also addressed.  ...  This paper analyzes, compares, and contrasts technical challenges, methods, and the performance of text detection and recognition research in color imagery.  ...  Jie Chen, the Associate Editor and the reviewers for their comments and suggestions.  ... 
doi:10.1109/tpami.2014.2366765 pmid:26352454 fatcat:cuz3qhkglnahdebxqptbsgpjmm

Detecting topical events in digital video

Tanveer Syeda-Mahmood, S. Srinivasan
2000 Proceedings of the eighth ACM international conference on Multimedia - MULTIMEDIA '00  
In particular, we use the image content of foils to detect visual events in which the foil is displayed and captured in the video stream.  ...  It is also a very challenging problem requiring the detection and integration of evidence for an event available in multiple information modalities, such as audio, video and language.  ...  Even with the best techniques for visual or audio scene analysis, event detection using the individual cues will continue to possess robustness problems due to detection errors.  ... 
doi:10.1145/354384.354433 dblp:conf/mm/Syeda-MahmoodS00 fatcat:d4rhnxhmcrhtlozjgthtjo7ieq

Track to the future: Spatio-temporal video segmentation with long-range motion cues

Jose Lezama, Karteek Alahari, Josef Sivic, Ivan Laptev
2011 CVPR 2011  
First, we develop an efficient spatiotemporal video segmentation algorithm, which naturally incorporates long-range motion cues from the past and future frames in the form of clusters of point tracks with  ...  Video provides not only rich visual cues such as motion and appearance, but also much less explored long-range temporal interactions among objects.  ...  This work was partly supported by the Quaero Programme, funded by OSEO, and by the MSR-INRIA laboratory.  ... 
doi:10.1109/cvpr.2011.6044588 dblp:conf/cvpr/Anwaar-ul-HaqGM11 fatcat:azc5l2bbxraihpkx72hu2iwj5a
« Previous Showing results 1 — 15 out of 8,530 results