MultiVENT-Raw is released, a multilingual collection of nearly 120,000 primarily raw videos paired with 130 events and 222 event-centric queries, along with human-annotated video relevance judgments and human-extracted key facts for relevant videos.
Abstract
Online information is increasingly consumed in video format. Much of this comes in the form of *raw video*: continuous footage taken on a cell phone, with a hand-held camera, or via CCTV, which is then directly uploaded to social media platforms and content sharing services. Whereas professional or even amateur-edited footage tends to feature scripted speech, chyrons, graphics, and metadata that help contextualize its subject matter, raw video typically contains none of these things, making it a much more challenging medium for information retrieval and machine understanding. To facilitate progress in this domain, we release MultiVENT-Raw, a multilingual collection of nearly 120,000 primarily raw videos (over 5,300 total hours), paired with 130 events and 222 event-centric queries, along with human-annotated video relevance judgments and human-extracted key facts for relevant videos. MultiVENT-Raw supports both a retrieval task---to identify videos in the collection relevant to a query event---and a generation task---to summarize event-related videos into a coherent report for a target user. We benchmark strong baselines on MultiVENT-Raw, showing both tasks to be challenging even for some of the latest multimodal models.
VideoVIBE is introduced, a video-grounded benchmark that transforms human-operated webpage recordings into fine-grained diagnostic tasks and V2Lens is proposed, a training-free, evidence-grounded multi-agent system that challenges and selectively refines initial video-based diagnoses through targeted visual and source-...
Jia-Jun Xu, Yang-Hao Zhou, Jing Liao et al.· 1 citation
VideoEvent is a lightweight and efficient training-free framework that segments an input video into question-relevant temporal events and selectively supplements them with low-level visual cues such as background and object layout, making it highly suitable for practical deployment.
Chen-Chen Lin, Ming-Han Lee, Kun-Ru Wu et al.· International Conference on...· 0 citations
This work introduces a frame-selection method designed specifically for multiple-choice questions, and is the first to directly utilize answer choices as inference-time cues for selecting frames relevant to answering a question.
Video Relational Algebra (VRA), a nested algebra over videos, transcripts, frames, and object tracks that captures common semantic video operations is introduced, and a set of approximate optimizations that rewrite VRA queries to reduce MLLM usage while improving result quality are derived.
Sultan Muratbek, Charisse Ivana Yeung, Chanwut Kittivorawong et al.· 0 citations
STITCH is presented, a training-free method that divides a video into semantically meaningful temporal chunks that are computed once per video and reused across tasks, suggesting that reusable temporal abstraction is a promising direction for general video understanding.
Etienne Casanova, S. Brodjian, Pietro Perona· 0 citations
Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one frame per second requires millions of tokens. To reduce costs, researchers rely on heuristics such as sampling a subset of frames, compressing videos into image grids, or...
Zhi-Xiu Zhu, Kristina Gligoric· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.