Weakly supervised video anomaly detection (WSAD) aims to localise anomalous events in untrimmed videos using only video-level labels. Existing multiple instance learning (MIL) methods often suffer from poor generalisation to unseen anomaly types, unstable temporal attention, and limited adaptability when only a few labelled examples are available. To address these challenges, we propose a meta-learning framework that combines Model-Agnostic Meta-Learning (MAML) with a dual-memory, transformer-based architecture. The model incorporates a dual-branch temporal attention module that captures both long-range semantic dependencies and local temporal proximity, separate memory banks for normal and abnormal prototypes with gated inhibition, metric-learning constraints, and variational latent regularisation. MAML explicitly trains the model for rapid adaptation across heterogeneous anomaly distributions, forcing it to acquire task-invariant representations rather than memorising static training statistics. Extensive experiments on two standard benchmarks yield competitive frame-level AUC of 93.60% on XD-Violence and 86.10% on UCF-Crime. One of our main contributions is the demonstration of very good metrics for zero and few-shot cross dataset transfer experiments, using only a handful of weakly labelled videos. We thus provide a useful proof of concept where MAML has been shown to learn generalized anomaly and non-anomaly representations with a transformer based architecture and a dual memory backbone. A t-SNE analysis of the memory prototypes confirms that MAML produces well-separated normal and abnormal clusters, while without meta-learning the memory banks collapse into entangled representations. The model is also shown to be computationally efficient, confirming its practical value for real-world surveillance deployment.
Shradha Mahadev Naik, Suja Palaniswamy, Nicola Conci· Journal of King Saud Univers...· 0 citations
Motion blending in character animation enables the synthesis of new motions by interpolating between existing examples. Current methods are typically restricted to fixed skeleton topologies, requiring identical or near-identical skeletal structures across characters. We present a novel framework for motion blending across heterogeneous skeletons. The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder, which reconstructs character-specific motion conditioned on this latent code. At inference, blended motions are obtained by interpolating the latent representations of two input motions. We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies, demonstrating the ability to achieve smooth and plausible blending in a variety of scenarios.
Motion blending remains a core tool in character animation, yet standard workflows are still largely constrained by fixed skeleton representations. When characters differ in topology, proportions, or hierarchy, artists often need manual correspondence design, retargeting, and substantial cleanup before they can explore even simple blended motions. We present BlendAnything, a Blender plugin that brings cross-topology motion blending into a familiar animation workflow. The plugin is powered by a skeleton-agnostic diffusion autoencoding backend that maps motions from different skeletal structures into a learned shared per-frame latent space, where high-level motion attributes such as action, phase, and global pose dynamics can be interpolated independently of rig topology, and then decodes the result into motion that remains structurally compatible with the chosen output skeleton. This design allows users to select reference and target motions, control the transition, and preview cross-topology blends directly inside Blender. We demonstrate the approach on the Truebones Zoo dataset with both quantitative and qualitative results in in-skeleton and cross-skeleton settings. By embedding this capability into Blender, BlendAnything turns cross-topology motion blending into a practical authoring tool for animation.
