SOTAVerified

TextVQA

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–47 of 47 papers

TitleStatusHype
FlexAttention for Efficient High-Resolution Vision-Language Models—0
Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture—0
HyViLM: Enhancing Fine-Grained Recognition with a Hybrid Encoder for Vision-Language Models—0
Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA—0
Making the V in Text-VQA Matter—0
Multiple-Question Multiple-Answer Text-VQA—0
SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering—0
Sentence Attention Blocks for Answer Grounding—0
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text—0
TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance—0
Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering—0
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering—0
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal CluesCode0
VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction OptimizationCode0
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language ModelsCode0
Towards a Unified Multimodal Reasoning FrameworkCode0
Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question AnsweringCode0
InstructOCR: Instruction Boosting Scene Text SpottingCode0
Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCapsCode0
Separate and Locate: Rethink the Text in Text-based Visual Question AnsweringCode0
OmniFusion Technical ReportCode0
Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQACode0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.