Cover Image

Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yan, Zeng, Gangyan, Wu, Daiqing, Shen, Huawen, Li, Binbin, Zhou, Yu, Ma, Can, Bi, Xiaojun
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding
by: Zhang, Yan, et al.
Published: (2026)

VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
by: He, Haibin, et al.
Published: (2026)

Resolving Sentiment Discrepancy for Multimodal Sentiment Detection via Semantics Completion and Decomposition
by: Wu, Daiqing, et al.
Published: (2024)

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

Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts
by: Xie, Enze, et al.
Published: (2024)

Bridging Visual Affective Gap: Borrowing Textual Knowledge by Learning from Noisy Image-Text Pairs
by: Wu, Daiqing, et al.
Published: (2025)

Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training
by: Li, Gengluo, et al.
Published: (2026)

MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation
by: Li, Gengluo, et al.
Published: (2026)

EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration
by: Wu, Daiqing, et al.
Published: (2025)

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

VidText: Towards Comprehensive Evaluation for Video Text Understanding
by: Yang, Zhoufaran, et al.
Published: (2025)

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
by: Li, Gengluo, et al.
Published: (2025)

Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach
by: Wu, Daiqing, et al.
Published: (2025)

An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
by: Wu, Daiqing, et al.
Published: (2025)

TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
by: Lyu, Jiahao, et al.
Published: (2024)

Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion
by: Wu, Daiqing, et al.
Published: (2025)

Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
by: Yu, Chenmin, et al.
Published: (2026)

Towards Training-Free Scene Text Editing
by: Li, Yubo, et al.
Published: (2026)

Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation
by: Huang, Binyuan, et al.
Published: (2026)

Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion
by: Zhao, Fangmin, et al.
Published: (2025)

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
by: Shu, Yan, et al.
Published: (2025)

DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment
by: Yu, Li, et al.
Published: (2025)

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

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
by: Zeng, Gangyan, et al.
Published: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
by: Yang, Lehan, et al.
Published: (2025)

LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining
by: Shen, Huawen, et al.
Published: (2024)

Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
by: Cheng, Zesen, et al.
Published: (2024)

IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation
by: Wu, Yinwei, et al.
Published: (2024)

InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
by: Fan, Tiehan, et al.
Published: (2024)

Text-Guided Multi-Instance Learning for Scoliosis Screening via Gait Video Analysis
by: Li, Haiqing, et al.
Published: (2025)

TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
by: Zhang, Zijian, et al.
Published: (2025)

Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing
by: Shen, Hongyu, et al.
Published: (2025)

InstanceV: Instance-Level Video Generation
by: Chen, Yuheng, et al.
Published: (2025)

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality
by: Zhang, Tianle, et al.
Published: (2024)

When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
by: Sun, Zhengyang, et al.
Published: (2026)

Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
by: Liang, Chen, et al.
Published: (2021)

R^3-VQA: "Read the Room" by Video Social Reasoning
by: Niu, Lixing, et al.
Published: (2025)

M$^{3}$T2IBench: A Large-Scale Multi-Category, Multi-Instance, Multi-Relation Text-to-Image Benchmark
by: Zhang, Huixuan, et al.
Published: (2025)