This work reviews the state of the art in multimodal speech emotion recognition methodologies, focusing on audio, text and visual information. We provide a new, descriptive categorization of methods, based on the way they handle the inter-modality and intra-modality dynamics in the temporal dimension: (i) non-temporal architectures (NTA), which do not significantly model the temporal dimension in both unimodal and multimodal interaction; (ii) pseudo-temporal architectures (PTA), which also assume an oversimplification of the temporal dimension, although in one of the unimodal or multimodal interactions; and (iii) temporal architectures (TA), which try to capture both unimodal and cross-modal temporal dependencies. In addition, we review the basic feature representation methods for each modality, and we present aggregated evaluation results on the reported methodologies. Finally, we conclude this work with an in-depth analysis of the future challenges related to validation procedures, representation learning and method robustness.

The exponential growth of user-generated content has increased the need for efficient video summarization schemes. However, most approaches underestimate the power of aural features, while they are designed to work mainly on commercial/professional videos. In this work, we present an approach that uses both aural and visual features in order to create video summaries from user-generated videos. Our approach produces dynamic video summaries, that is, comprising the most “important” parts of the original video, which are arranged so as to preserve their temporal order. We use supervised knowledge from both the aforementioned modalities and train a binary classifier, which learns to recognize the important parts of videos. Moreover, we present a novel user-generated dataset which contains videos from several categories. Every 1 s part of each video from our dataset has been annotated by more than three annotators as being important or not. We evaluate our approach using several classification strategies based on audio, video and fused features. Our experimental results illustrate the potential of our approach.

Cryogenic Electron Microscopy (cryo-EM) has revolutionized structural biology by enabling near-atomic-resolution structure determination of biological macromolecules. Central to cryo-EM analysis are particles, namely 2D projections of biomolecules extracted from micrographs, which serve as the primary input for 3D reconstruction. While data-driven methods have transformed other scientific domains, their impact on cryo-EM remains limited because existing particle datasets are too small, too narrow in protein diversity, and lack rich per-particle annotations. We introduce cryoPANDA (cryo-EM Particles ANnotated DAtaset), comprising over 37 million annotated particles from 252 experiments spanning a wide range of protein types, more than 10-fold larger than prior collections. Each particle is accompanied by detailed annotations covering acquisition, classification, and re-construction metadata, alongside the corresponding 3D electrostatic potential map, the published EMDB map, and, where available, the PDB model. We validate cryoPANDA in two ways: first, by reconstructing hundreds of distinct high-resolution cryo-EM maps; and second, by training a DINOv2 foundation model and evaluating its learned representations on micrograph segmentation, particle picking, and particle clustering.