Image de couverture de livre

Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Peng, Bo, Lyu, YuanJie, Qin, PengGang, Xu, Tong
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Event-oriented Long Video Understanding
par: Du, Yifan, et autres
Publié: (2024)

Fostering Video Reasoning via Next-Event Prediction
par: Wang, Haonan, et autres
Publié: (2025)

Generating Event-oriented Attribution for Movies via Two-Stage Prefix-Enhanced Multimodal LLM
par: Lyu, Yuanjie, et autres
Publié: (2024)

LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
par: Geng, Tiantian, et autres
Publié: (2024)

MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval
par: Kriz, Reno, et autres
Publié: (2024)

MLVU: Benchmarking Multi-task Long Video Understanding
par: Zhou, Junjie, et autres
Publié: (2024)

Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs
par: Plötzky, Florian, et autres
Publié: (2024)

Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction
par: Liu, Wanlong, et autres
Publié: (2024)

A Video-grounded Dialogue Dataset and Metric for Event-driven Activities
par: Imrattanatrai, Wiradee, et autres
Publié: (2025)

Towards Zero-Shot & Explainable Video Description by Reasoning over Graphs of Events in Space and Time
par: Masala, Mihai, et autres
Publié: (2025)

Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space
par: Yu, Xiaoyan, et autres
Publié: (2024)

Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation
par: Wang, Yiping, et autres
Publié: (2024)

ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
par: Ma, David, et autres
Publié: (2025)

LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning
par: Tang, Yolo Yunlong, et autres
Publié: (2023)

Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models
par: Chew, Oscar, et autres
Publié: (2026)

Event-Anchored Frame Selection for Effective Long-Video Understanding
par: Chen, Wang, et autres
Publié: (2026)

Bilateral Event Mining and Complementary for Event Stream Super-Resolution
par: Huang, Zhilin, et autres
Publié: (2024)

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach
par: Li, Hebei, et autres
Publié: (2025)

Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval
par: Dipta, Shubhashis Roy, et autres
Publié: (2025)

MultiClimate: Multimodal Stance Detection on Climate Change Videos
par: Wang, Jiawen, et autres
Publié: (2024)

EventLens: Leveraging Event-Aware Pretraining and Cross-modal Linking Enhances Visual Commonsense Reasoning
par: Ma, Mingjie, et autres
Publié: (2024)

Towards Better Multi-head Attention via Channel-wise Sample Permutation
par: Yuan, Shen, et autres
Publié: (2024)

Spatial Semantic Recurrent Mining for Referring Image Segmentation
par: Yang, Jiaxing, et autres
Publié: (2024)

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding
par: Wang, Xiangfeng, et autres
Publié: (2025)

Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets
par: Wu, Peng, et autres
Publié: (2026)

EFSA: Towards Event-Level Financial Sentiment Analysis
par: Chen, Tianyu, et autres
Publié: (2024)

Grounding Partially-Defined Events in Multimodal Data
par: Sanders, Kate, et autres
Publié: (2024)

OpenEP: Open-Ended Future Event Prediction
par: Guan, Yong, et autres
Publié: (2024)

Semantic Event Graphs for Long-Form Video Question Answering
par: Dixit, Aradhya, et autres
Publié: (2026)

OmChat: A Recipe to Train Multimodal Language Models with Strong Long Context and Video Understanding
par: Zhao, Tiancheng, et autres
Publié: (2024)

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding
par: Luo, Fuwen, et autres
Publié: (2025)

RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction
par: Jin, Yongkang, et autres
Publié: (2026)

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation
par: Zhang, Hongyu, et autres
Publié: (2026)

Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors
par: Luo, Fuwen, et autres
Publié: (2026)

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
par: Qi, Ji, et autres
Publié: (2025)

RefereeBench: Are Video MLLMs Ready to be Multi-Sport Referees
par: Xu, Yichen, et autres
Publié: (2026)

Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams
par: Guo, Zhenghui, et autres
Publié: (2026)

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
par: Zhao, Yilun, et autres
Publié: (2025)

Enhancing Long Video Understanding via Hierarchical Event-Based Memory
par: Cheng, Dingxin, et autres
Publié: (2024)

VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models
par: Cheng, Ming, et autres
Publié: (2025)