Image de couverture de livre

Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fei, Jiajun, Li, Dian, Deng, Zhidong, Wang, Zekun, Liu, Gang, Wang, Hui
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

HourVideo: 1-Hour Video-Language Understanding
par: Chandrasegaran, Keshigeyan, et autres
Publié: (2024)

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues
par: Pan, Yaning, et autres
Publié: (2025)

Video Panels for Long Video Understanding
par: Doorenbos, Lars, et autres
Publié: (2025)

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation
par: Yan, Xin, et autres
Publié: (2024)

Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
par: Liu, Jiajun, et autres
Publié: (2024)

Linear Scaling Video VLMs for Long Video Understanding
par: Eyzaguirre, Cristobal, et autres
Publié: (2026)

VCA: Video Curious Agent for Long Video Understanding
par: Yang, Zeyuan, et autres
Publié: (2024)

TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
par: Chen, Shimin, et autres
Publié: (2024)

VideoExplorer: Think With Videos For Agentic Long-Video Understanding
par: Yuan, Huaying, et autres
Publié: (2025)

Video-Infinity: Distributed Long Video Generation
par: Tan, Zhenxiong, et autres
Publié: (2024)

FAME: Fairness-aware Attention-modulated Video Editing
par: Wu, Zhangkai, et autres
Publié: (2025)

Long Story Short: Story-level Video Understanding from 20K Short Films
par: Ghermi, Ridouane, et autres
Publié: (2024)

Causality Model for Semantic Understanding on Videos
par: Yicong, Li
Publié: (2025)

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
par: Fu, Honghao, et autres
Publié: (2026)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
par: Chen, Houlun, et autres
Publié: (2026)

PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
par: Mao, Xiaofeng, et autres
Publié: (2026)

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

IPFormer-VideoLLM: Enhancing Multi-modal Video Understanding for Multi-shot Scenes
par: Liang, Yujia, et autres
Publié: (2025)

USV: Towards Understanding the User-generated Short-form Videos
par: Cheng, Haoyue, et autres
Publié: (2026)

Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding
par: Wang, Yun, et autres
Publié: (2025)

VideoAgent: Long-form Video Understanding with Large Language Model as Agent
par: Wang, Xiaohan, et autres
Publié: (2024)

LVBench: An Extreme Long Video Understanding Benchmark
par: Wang, Weihan, et autres
Publié: (2024)

HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding
par: Zou, Heqing, et autres
Publié: (2025)

Enhancing Long Video Question Answering with Scene-Localized Frame Grouping
par: Yang, Xuyi, et autres
Publié: (2025)

CausalVE: Face Video Privacy Encryption via Causal Video Prediction
par: Huang, Yubo, et autres
Publié: (2024)

VideoWeave: A Data-Centric Approach for Efficient Video Understanding
par: Durante, Zane, et autres
Publié: (2026)

Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
par: Wang, Ziyang, et autres
Publié: (2025)

Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
par: Li, Chengzhi, et autres
Publié: (2025)

VideoNSA: Native Sparse Attention Scales Video Understanding
par: Song, Enxin, et autres
Publié: (2025)

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
par: Lin, Kuanwei, et autres
Publié: (2026)

VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
par: Qiu, Chenhao, et autres
Publié: (2026)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
par: Jin, Hongbo, et autres
Publié: (2025)

ReWind: Understanding Long Videos with Instructed Learnable Memory
par: Diko, Anxhelo, et autres
Publié: (2024)

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
par: Peng, Tianhao, et autres
Publié: (2025)

VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
par: Wang, Shihao, et autres
Publié: (2025)

MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
par: Deng, Yufan, et autres
Publié: (2025)

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
par: Qin, Minghao, et autres
Publié: (2025)

VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
par: Liu, Wenqi, et autres
Publié: (2026)

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
par: Lu, Hao, et autres
Publié: (2025)

QuickVideo: Real-Time Long Video Understanding with System Algorithm Co-Design
par: Schneider, Benjamin, et autres
Publié: (2025)