Imagen de Portada

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Haibin, Ye, Maoyuan, Zhang, Jing, Liu, Juhua, Du, Bo
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA
por: He, Haibin, et al.
Publicado: (2025)

GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
por: He, Haibin, et al.
Publicado: (2025)

GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
por: He, Haibin, et al.
Publicado: (2024)

LogicOCR: Do Your Large Multimodal Models Excel at Logical Reasoning on Text-Rich Images?
por: Ye, Maoyuan, et al.
Publicado: (2025)

ET-SAM: Efficient Point Prompt Prediction in SAM for Unified Scene Text Detection and Layout Analysis
por: Zhang, Xike, et al.
Publicado: (2026)

Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
por: He, Haibin, et al.
Publicado: (2025)

Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation
por: Chen, Hang, et al.
Publicado: (2025)

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues
por: Zhang, Yan, et al.
Publicado: (2024)

Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective
por: Zhang, Yan, et al.
Publicado: (2025)

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
por: Ye, Maoyuan, et al.
Publicado: (2023)

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
por: Ye, Maoyuan, et al.
Publicado: (2024)

Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model
por: Qiao, Yixuan, et al.
Publicado: (2021)

Rethink Sparse Signals for Pose-guided Text-to-image Generation
por: Xuan, Wenjie, et al.
Publicado: (2025)

Agentic Keyframe Search for Video Question Answering
por: Fan, Sunqi, et al.
Publicado: (2025)

Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
por: Liu, Lin, et al.
Publicado: (2026)

KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation
por: Wang, Xingrui, et al.
Publicado: (2025)

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
por: Zhou, Sheng, et al.
Publicado: (2025)

Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
por: Fang, Bo, et al.
Publicado: (2025)

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
por: Nie, Ming, et al.
Publicado: (2025)

Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training
por: Zhong, Qihuang, et al.
Publicado: (2026)

GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization
por: Song, Zixuan, et al.
Publicado: (2025)

Large Model based Sequential Keyframe Extraction for Video Summarization
por: Tan, Kailong, et al.
Publicado: (2024)

KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes
por: Wu, Jingchao, et al.
Publicado: (2025)

KeyVideoLLM: Towards Large-scale Video Keyframe Selection
por: Liang, Hao, et al.
Publicado: (2024)

QTG-VQA: Question-Type-Guided Architectural for VideoQA Systems
por: He, Zhixian, et al.
Publicado: (2024)

The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
por: He, Qingdong, et al.
Publicado: (2025)

RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering
por: Zhang, Chengyi, et al.
Publicado: (2026)

Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA Challenge
por: Xu, Yinsong, et al.
Publicado: (2026)

PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking
por: Lv, Meng, et al.
Publicado: (2026)

Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering
por: Kwon, Minchan, et al.
Publicado: (2026)

RFL-CDNet: Towards Accurate Change Detection via Richer Feature Learning
por: Gan, Yuhang, et al.
Publicado: (2024)

EduVQA: Towards Concept-Aware Assessment of Educational AI-Generated Videos
por: Chen, Baoliang, et al.
Publicado: (2026)

Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation
por: Wang, Xiaojuan, et al.
Publicado: (2024)

Adaptive Keyframe Sampling for Long Video Understanding
por: Tang, Xi, et al.
Publicado: (2025)

MUJICA: Reforming SISR Models for PBR Material Super-Resolution via Cross-Map Attention
por: Du, Xin, et al.
Publicado: (2025)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
por: Song, Baiyang, et al.
Publicado: (2026)

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
por: Zhang, Chi, et al.
Publicado: (2025)

WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation
por: Wang, Jing, et al.
Publicado: (2025)

AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
por: Zhang, Shuheng, et al.
Publicado: (2025)

SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models
por: Liu, Bo, et al.
Publicado: (2025)