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.
|
Ayan Banerjee, Sanket Biswas, Josep Llados, & Umapada Pal. (2024). GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation.
Abstract: Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: this https URL.
|
Maya Dimitrova, Ch. Roumenin, Petia Radeva, David Rotger, & Juan J. Villanueva. (2003). Multimodal Intelligent System for Cardiovascular Diagnosis.
|
David Masip, M. Bressan, & Jordi Vitria. (2004). Classifier Combination Applied to Real Time Face Detection and Classification.
|
Bart M. Ter Haar Romeny, W. Niessen, J. Weickert, P. Van Roermund, W. Van Enk, Antonio Lopez, et al. (1996). Orientation detection of trabecular bone.
|
Ferran Diego, Daniel Ponsa, Joan Serrat, & Antonio Lopez. (2009). Video alignment for automotive applications.
Keywords: video alignment
|
Jose Manuel Alvarez, & Antonio Lopez. (2009). Model-based road detection using shadowless features and on-line learning.
|
M. Bressan, David Guillamet, & Jordi Vitria. (2000). Using an ICA representation of local color histograms for object recognition..
|
Bogdan Raducanu, & Jordi Vitria. (2006). Aprendiendo a Aprender: de Maquinas Listas a Maquinas Inteligentes.
|
David Masip, & Jordi Vitria. (2004). Boosted Linear Projections for Discriminant Analysis.
|
Sergio Escalera, & Petia Radeva. (2004). Fast greyscale road sign model matching and recognition.
|
Robert Benavente, & Maria Vanrell. (2004). Fuzzy Colour Naming Based on Sigmoid Membership Functions..
|
Xavier Otazu, & Maria Vanrell. (2004). Building Perceived Colour Images..
|
Francesc Tous, Maria Vanrell, & Ramon Baldrich. (2004). Exploring Colour Constancy Solutions..
|
E. Barakova, Maya Dimitrova, T. Lorents, & Petia Radeva. (2004). The Web as an “Autobiographical Agent”.
|