|
Daniel Ponsa, A.F. Sole, Antonio Lopez, Cristina Cañero, Petia Radeva, & Jordi Vitria. (2000). Regularized EM..
|
|
|
Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, & Bartlomiej Twardowski. (2023). Revisiting Supervision for Continual Representation Learning.
Abstract: In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, recent studies have highlighted the strengths of self-supervised continual representation learning. The improved transferability of representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning.
|
|
|
Antonio Lopez. (1997). Ridge/Valley-like structures: Creases, separatrices and drainage patterns.
|
|
|
Antonio Lopez, Joan Serrat, J. Saludes, Cristina Cañero, Felipe Lumbreras, & T. Graf. (2005). Ridgeness for Detecting Lane Markings.
|
|
|
A. Pujol, Antonio Lopez, Jose Luis Alba, & Juan J. Villanueva. (2001). Ridges, Valleys and Hausdorff Based Similarity Measures for Face Detection and Matching.
|
|
|
Dani Rowe, Ignasi Rius, Jordi Gonzalez, & Juan J. Villanueva. (2005). Robust Particle Filtering for Object Tracking.
|
|
|
David Pujol Perich, Albert Clapes, & Sergio Escalera. (2023). SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization.
Abstract: Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected in the literature, exposing these solutions to important performance degradation. In this work, we tackle this issue by introducing, for the first time, an approach for Unsupervised Domain Adaptation (UDA) in sparse TAL, which we refer to as Semantic Adversarial unsupervised Domain Adaptation (SADA). Our contributions are threefold: (1) we pioneer the development of a domain adaptation model that operates on realistic sparse action detection benchmarks; (2) we tackle the limitations of global-distribution alignment techniques by introducing a novel adversarial loss that is sensitive to local class distributions, ensuring finer-grained adaptation; and (3) we present a novel set of benchmarks based on EpicKitchens100 and CharadesEgo, that evaluate multiple domain shifts in a comprehensive manner. Our experiments indicate that SADA improves the adaptation across domains when compared to fully supervised state-of-the-art and alternative UDA methods, attaining a performance boost of up to 6.14% mAP.
|
|
|
A. Pujol, A.F. Sole, Daniel Ponsa, Javier Varona, & Juan J. Villanueva. (1999). Satellite Image Segmentation Trough Rotational Invariant Feature Eigenvector Projection..
|
|
|
German Barquero, Sergio Escalera, & Cristina Palmero. (2024). Seamless Human Motion Composition with Blended Positional Encodings.
Abstract: Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without any postprocessing or redundant denoising steps. For this, we introduce the Blended Positional Encodings, a technique that leverages both absolute and relative positional encodings in the denoising chain. More specifically, global motion coherence is recovered at the absolute stage, whereas smooth and realistic transitions are built at the relative stage. As a result, we achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets. FlowMDM excels when trained with only a single description per motion sequence thanks to its Pose-Centric Cross-ATtention, which makes it robust against varying text descriptions at inference time. Finally, to address the limitations of existing HMC metrics, we propose two new metrics: the Peak Jerk and the Area Under the Jerk, to detect abrupt transitions.
|
|
|
Petia Radeva. (1993). Segmentacion de Imagenes Radiograficas con Snakes. Aplicacion a la Determinacion de la Madurez Osea..
|
|
|
Daniel Ponsa, & Antonio Lopez. (2009). Seguimiento Visual de Contornos Computerizado.
|
|
|
Xose M. Pardo, Petia Radeva, & Juan J. Villanueva. (1999). Self-Training Statistic Snake for Image Segmentation and Tracking..
|
|
|
J.M. Sanchez, & X. Binefa. (2001). Semantics from motion in news videos..
|
|
|
Jose Luis Alba, A. Pujol, & Juan J. Villanueva. (2001). Separating Geometry from Texture to Improve Face Analysis..
|
|
|
Fadi Dornaika, & Franck Davoine. (2005). SFM for planar scenes using image derivatives.
|
|