![]() ![]() In: ICPRĭuta IC, Uijlings JRR, Nguyen TA, Aizawa K, Hauptmann AG, Ionescu B, Sebe N (2016) Histograms of motion gradients for real-time video classification. In: ECCVĭuta IC, Nguyen TA, Aizawa K, Ionescu B, Sebe N (2016) Boosting VLAD with double assignment using deep features for action recognition in videos. In: ECCVĭe Souza CR, Gaidon A, Vig E, López AM (2016) Sympathy for the details: Dense trajectories and hybrid classification architectures for action recognition. In: CVPRĭalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. In: ECCVĭalal N, Triggs B (2005) Histograms of oriented gradients for human detection. TPAMI 33(3):500–513īrox T, Bruhn A, Papenberg N, Weickert J (2004) High accuracy optical flow estimation based on a theory for warping. Mach Learn 45(1):5–32īrox T, Malik J (2011) Large displacement optical flow: descriptor matching in variational motion estimation. In: CVPRīilen H, Fernando B, Gavves E, Vedaldi A, Gould S (2016) Dynamic image networks for action recognition. ![]() In: CVPRĪrandjelovic R, Zisserman A (2013) All about VLAD. We validated our proposed pipeline for action recognition on three challenging datasets UCF50, UCF101 and HMDB51, and we propose also a real-time framework for action recognition.Īrandjelović R, Zisserman A (2012) Three things everyone should know to improve object retrieval. In this work we propose Shape Difference VLAD (SD-VLAD), an encoding method which brings complementary information by using the shape information within the encoding process. For the encoding step a widely adopted method is the Vector of Locally Aggregated Descriptors (VLAD), which is an efficient encoding method, however, it considers only the difference between local descriptors and their centroids. Our proposed descriptor, Histograms of Motion Gradients (HMG), is based on a simple temporal and spatial derivation, which captures the changes between two consecutive frames. In this work we propose an efficient approach to capture the motion information within the video. ![]() However, the estimation of optical flow is very demanding in terms of computational cost, in many cases being the most significant processing step within the overall pipeline of the target video analysis application. The common approach to extract the motion information is to compute the optical flow. The motion information represents an important source of information within the video. This work proposes a new approach for feature extraction and encoding that allows us to obtain real-time frame rate processing for an action recognition system. For building a powerful action recognition pipeline it is important that both steps are efficient and in the same time provide reliable performance. Feature extraction and encoding represent two of the most crucial steps in an action recognition system. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |