arXiv AI

EventVL: Understand Event Streams via Multimodal Large Language Model

EventVL introduces the first generative event-based multimodal large language model (MLLM) designed for explicit semantic understanding of event streams. The framework leverages a newly annotated dataset of nearly 1.4 million event–image/video–text pairs and incorporates an Event Spatiotemporal Representation to capture comprehensive event information, along with Dynamic Semantic Alignment to refine sparse semantic spaces. Experiments demonstrate that EventVL outperforms existing MLLM baselines in event captioning and scene description generation tasks, advancing the field of event vision.

arXiv Computer Vision
2d ago

Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation

Hyper-RED introduces a scalable image-to-event pretraining framework that transfers high‑order semantic structures via hypergraphs, avoiding rigid pixel‑wise alignment. By constructing image, event, and cross‑modal hypergraphs and applying a hypergraph relational distillation loss, the method preserves local relational consistency and event‑specific characteristics while inheriting image‑derived semantic organization. Experiments across five event datasets show consistent scaling from ViT‑S to ViT‑L and state‑of‑the‑art performance.

By Meisen Wang, Zhiqiang Tian, Wei Bao, Chengjie Wang, Shaoyi Du, Siqi Li
Hugging Face Trending Papers
Jun 1

WALL-WM: Carving World Action Modeling at the Event Joints

WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent action events as the atomic unit of learning. Existing WAMs commonly initialize from multimodal or video foundation models and then optimize fixed-length action chunks conditioned directly on the current observation and instruction.

arXiv AI
Sep 4

Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning

The paper introduces Seeing Before Synthesizing (SBS), a weakly-supervised dense video captioning framework that uses a vision‑language model to generate frame‑level narratives for gaps between events and detect transitions based on semantic changes. SBS refines temporal masks by aligning transition points with vision‑language cues, rather than relying on rigidly placed synthetic captions. Experiments on ActivityNet Captions and YouCook2 show that SBS achieves state‑of‑the‑art results in both captioning and localization tasks.

By Ye-Chan Kim, Seunghee Choi, SeungJu Cha, Si-Woo Kim, Hwiseon Kim, Hyungee Kim, Dong-Jin Kim
arXiv Computer Vision
Aug 31

Training-Free Temporal Abstraction for General Video Understanding

The paper introduces STITCH, a training‑free method that partitions videos into semantically meaningful temporal chunks using a frozen video‑text backbone. By detecting changes in the embedding sequence of short video windows, STITCH produces reusable temporal abstractions that can be applied to multiple tasks such as event boundary detection, language‑based moment retrieval, and frame selection for vision‑language models. Experiments show that STITCH performs competitively with specialized methods while requiring no task‑specific training, especially when processing is limited to a few frames or tokens.

By Etienne Casanova, Sevan Brodjian, Pietro Perona
arXiv Computer Vision
4d ago

EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use

EventMemAgent is an active online video agent that uses a hierarchical memory module to handle continuous perception and long‑range reasoning in streaming video. The framework employs a short‑term memory layer to detect event boundaries and sample frames within a fixed buffer, while a long‑term memory layer archives observations event‑by‑event. It also incorporates a multi‑granular perception toolkit and Agentic Reinforcement Learning to internalize reasoning and tool‑use strategies, achieving competitive results on online video benchmarks.

By Siwei Wen, Zhangcheng Wang, Xingjian Zhang, Lei Huang, Wenjun Wu