|
Swathikiran Sudhakaran, Sergio Escalera, & Oswald Lanz. (2021). Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, .
Abstract: We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.
|
|
|
Frederic Sampedro, Sergio Escalera, & Anna Puig. (2014). Iterative Multiclass Multiscale Stacked Sequential Learning: definition and application to medical volume segmentation. PRL - Pattern Recognition Letters, 46, 1–10.
Abstract: In this work we present the iterative multi-class multi-scale stacked sequential learning framework (IMMSSL), a novel learning scheme that is particularly suited for medical volume segmentation applications. This model exploits the inherent voxel contextual information of the structures of interest in order to improve its segmentation performance results. Without any feature set or learning algorithm prior assumption, the proposed scheme directly seeks to learn the contextual properties of a region from the predicted classifications of previous classifiers within an iterative scheme. Performance results regarding segmentation accuracy in three two-class and multi-class medical volume datasets show a significant improvement with respect to state of the art alternatives. Due to its easiness of implementation and its independence of feature space and learning algorithm, the presented machine learning framework could be taken into consideration as a first choice in complex volume segmentation scenarios.
Keywords: Machine learning; Sequential learning; Multi-class problems; Contextual learning; Medical volume segmentation
|
|
|
Anastasios Doulamis, Nikolaos Doulamis, Marco Bertini, Jordi Gonzalez, & Thomas B. Moeslund. (2016). Introduction to the Special Issue on the Analysis and Retrieval of Events/Actions and Workflows in Video Streams. MTAP - Multimedia Tools and Applications, 75(22), 14985–14990.
|
|
|
O. Rodriguez-Leor, E Fernandez-Nofrerias, J. Mauri, C. Garcia, R. Villuendas, V. Valle, et al. (2003). Intravascular ultrasound segmentation using local binary patterns. European Heart Journal (IF: 5.997), ESC Congress 2003.
|
|
|
Sergio Escalera, Oriol Pujol, J. Mauri, & Petia Radeva. (2009). Intravascular Ultrasound Tissue Characterization with Sub-class Error-Correcting Output Codes. Journal of Signal Processing Systems, 55(1-3), 35–47.
Abstract: Intravascular ultrasound (IVUS) represents a powerful imaging technique to explore coronary vessels and to study their morphology and histologic properties. In this paper, we characterize different tissues based on radial frequency, texture-based, and combined features. To deal with the classification of multiple tissues, we require the use of robust multi-class learning techniques. In this sense, error-correcting output codes (ECOC) show to robustly combine binary classifiers to solve multi-class problems. In this context, we propose a strategy to model multi-class classification tasks using sub-classes information in the ECOC framework. The new strategy splits the classes into different sub-sets according to the applied base classifier. Complex IVUS data sets containing overlapping data are learnt by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. The method automatically characterizes different tissues, showing performance improvements over the state-of-the-art ECOC techniques for different base classifiers. Furthermore, the combination of RF and texture-based features also shows improvements over the state-of-the-art approaches.
|
|