文件列表:

snippets\code\classify_npairs.m (510, 2009-10-12)
snippets\code\classify_ova.m (371, 2009-10-12)
snippets\code\crossvalidation.m (10487, 2009-10-13)
snippets\code\crossval_boundaries.m (368, 2009-10-12)
snippets\code\extract_pca_descriptors.m (646, 2009-10-12)
snippets\code\features.m (2876, 2009-10-15)
snippets\code\filters\extract_flowfeatures.m (2729, 2009-10-12)
snippets\code\filters\flowmap.m (2528, 2009-10-12)
snippets\code\filters\flowmap_withties.m (2952, 2009-10-12)
snippets\code\filters\gaborconvolve.m (7461, 2009-10-12)
snippets\code\filters\imgshift.m (705, 2009-10-12)
snippets\code\filters\magnitude.m (162, 2009-10-12)
snippets\code\frame2vec.m (864, 2009-10-12)
snippets\code\learn_classification_npairs.m (795, 2009-10-12)
snippets\code\learn_classification_ova.m (633, 2009-10-12)
snippets\code\learn_pca.m (944, 2009-10-12)
snippets\code\learn_pca_representation.m (1064, 2009-10-12)
snippets\code\majority_vote.m (636, 2009-10-12)
snippets\code\max_pooling.m (1150, 2009-10-12)
snippets\code\pooling.m (1254, 2009-10-15)
snippets\code\project_pca.m (269, 2009-10-12)
snippets\code\read_exp.m (753, 2009-10-12)
snippets\code\read_features.m (469, 2009-10-12)
snippets\code\scramble_subjects.m (565, 2009-10-12)
snippets\code\split_data.m (596, 2009-10-12)
snippets\code\svm\consist.m (2604, 2009-10-12)
snippets\code\svm\distance.m (1091, 2009-10-12)
snippets\code\svm\ecoc.m (1567, 2009-10-12)
snippets\code\svm\ecocfwd.m (1955, 2009-10-12)
snippets\code\svm\ecoctrain.m (2709, 2009-10-12)
snippets\code\svm\svm.m (4814, 2009-10-12)
snippets\code\svm\svmfwd.m (2374, 2009-10-12)
snippets\code\svm\svmkernel.m (2810, 2009-10-12)
snippets\code\svm\svmtrain.m (21759, 2009-10-12)
snippets\code\write_features.m (465, 2009-10-12)
snippets\data\weizmann.txt (1648, 2009-10-14)
snippets\data\ws01bend.001.png (3448, 2007-10-05)
snippets\data\ws01bend.002.png (3459, 2007-10-05)
snippets\data\ws01bend.003.png (3460, 2007-10-05)
snippets\data\ws01bend.004.png (3457, 2007-10-05)
... ...

Action Snippets V1.0 ==================== Code written by Konrad Schindler, using components provided by Peter Kovesi and Anton Schweighofer. Research by Konrad Schindler and L. van Gool. Quick start ----------- 1) uncompress the archive with TAR or WINZIP. 2) change to directory snippets/code 3) open MATLAB 4) run the feature extraction, using the provided data ad control file: > features('../data/weizmann.txt'); This takes a while. Features are written to file, so you need not do this again, unless you change the parameters of feature extraction. 5) run the feature pooling: > pooling('../data/weizmann.txt'); Again, the pooled features are written to file, so unless you change the pooling size, you need not do this again. 6) test the classification: > crossvalidation('../data/weizmann.txt'); This takes a LONG while, because the PCA-basis is recomputed for each fold. The PCA-bases are written to file, so that you can later load them from file, as long as you are using the same snippet length - change the variable . Overview -------- Welcome to this software release, which implements the functionality reported in [1]: - extracting features from action videos - training a classifier for the actions - testing the classifier with crossvalidation The release includes the complete Matlab source code. It is recommend to use the code only with Matlab 8 or higher. In addition to the code, this release also includes the cropped frames of the WEIZMANN dataset [2]. The crops were generated automatically, using the author's silhouette annotations. Parameter Settings ------------------ All parameters are set directly in the top-level files. Look for variables names . Variable names and code comments should be self-explanatory, if you read the paper [1]. Using your dataset ------------------ To use other data than the provided Weizmann frames: - split the video into single files; all frames must be the same size, and all clips must have the same number of frames. The frames from one clip must follow the naming convention . - prepare a control file, using the template . Class labels are integer numbers starting from 1. - run the three steps of the program with your controlfile. Support ------- For any query/suggestion/complaint or simply to say you like/use this software, just drop me an email: schindler@cs.tu-darmstadt.de I wish you a good time using this software, Konrad References ---------- [1] K. Schindler and L. van Gool. Action snippets: how many frames does human action recognition require? CVPR 2009. [2] L. Gorelick, M. Blank, E. Shechtman, M. Irani and R. Basri. Actions as space-time shapes. ICCV 2005.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：