Search Results for author:
Found 7 papers, 3 papers with code
VidText: Towards Comprehensive Evaluation for Video Text Understanding
We hope VidText will fill the current gap in video understanding benchmarks and serve as a foundation for future research on multimodal reasoning with video text in dynamic environments.
CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
Scene Text Retrieval (STR) seeks to identify all images containing a given query string.
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
To bridge this gap, we introduce a new Natural Language-based Document Image Retrieval (NL-DIR) benchmark with corresponding evaluation metrics.
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues
Video text-based visual question answering (Video TextVQA) is a practical task that aims to answer questions by jointly reasoning textual and visual information in a given video.
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
Scene text retrieval aims to find all images containing the query text from an image gallery.
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks.
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
Texts in scene images convey critical information for scene understanding and reasoning.
Optical Character Recognition
Optical Character Recognition (OCR)
+4
