We introduce OpenEvents V1, a large-scale benchmark dataset designed to advance event-centric vision-language understanding. Unlike conventional image captioning and retrieval datasets that focus on surface-level descriptions, OpenEvents V1 dataset emphasizes contextual and temporal grounding through three primary tasks: (1) generating rich, event-aware image captions, (2) retrieving event-relevant news articles from image queries, and (3) retrieving event-relevant images from narrative-style textual queries. The dataset comprises over 200,000 news articles and 400,000 associated images sourced from CNN and The Guardian, spanning diverse domains and time periods. We provide extensive baseline results and standardized evaluation protocols for all tasks. OpenEvents V1 establishes a robust foundation for developing multimodal AI systems capable of deep reasoning over complex real-world events. The dataset is publicly available at https://ltnghia.github.io/eventa/openevents-v1.

The Event-Enriched Image Analysis (EVENTA) Grand Challenge, hosted at ACM Multimedia 2025, introduces the first large-scale benchmark for event-level multimodal understanding. Traditional captioning and retrieval tasks largely focus on surface-level recognition of people, objects, and scenes, often overlooking the contextual and semantic dimensions that define real-world events. EVENTA addresses this gap by integrating contextual, temporal, and semantic information to capture the who, when, where, what, and why behind an image. Built upon the OpenEvents V1 dataset, the challenge features two tracks: Event-Enriched Image Retrieval and Captioning, and Event-Based Image Retrieval. A total of 45 teams from six countries participated, with evaluation conducted through Public and Private Test phases to ensure fairness and reproducibility. The top three teams were invited to present their solutions at ACM Multimedia 2025. EVENTA establishes a foundation for context-aware, narrative-driven multimedia AI, with applications in journalism, media analysis, cultural archiving, and accessibility. Further details about the challenge are available at the official homepage: https://ltnghia.github.io/eventa/eventa-2025.

Hybrid analog digital (HDA) architectures have been widely used in communication systems for analog source over discrete-time memoryless Gaussian channels. They employ a linear coding scheme in the analog parts, while considering separately the design of source and channel codes in the digital parts. To the best of our knowledge, none of the previous HDA schemes exploit the advantages of maintaining a joint source and channel coding design in the digital segment. In this paper, we investigate the effect of the analog parts on various outputs of the digital modules in a HDA communication system, and introduce a novel HDA architecture with adaptation for the digital parts. Such adaptation allows our system to exploit the joint effect of the analog components and the channel noise on outputs of the digital components, while simultaneously taking into consideration the unequal distribution of source code outputs. Our simulations illustrate that the proposed HDA system provides robust and graceful performance (on both bandwidth compression and expansion modes) for a wide range of channel conditions.

Hybrid digital-analog (HDA) architectures have been widely developed for efficient digital transmission of analog speech, audio or video data. By considering the advantage of both digital and analog components, HDA systems gain better performances than purely analog and digital schemes in a wide range of channel conditions. However, HDA systems described in previous works are mostly designed for continuous-valued sources. In this paper, we address the problem of transmission of discrete sources over noisy channels. In particular, our work focuses on digital speech data in PCM format. We proposed two analog schemes, linear mapping, and non-linear mappings. The linear analog mapping employs an equal error protection scheme while the non-linear mapping takes into account the heterogeneous nature of error values to provide better protection to important values. The experiment results show that our HDA systems provide a better performance on a wide range of channel qualities in comparison with traditional purely digital systems.