VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text

• URL: http://arxiv.org/abs/2406.06462v4
• Date: Fri, 18 Apr 2025 16:42:48 GMT
• Title: VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
• Authors: Tianyu Zhang, Suyuchen Wang, Lu Li, Ge Zhang, Perouz Taslakian, Sai Rajeswar, Jie Fu, Bang Liu, Yoshua Bengio,
• Abstract summary: We introduce Visual Caption Restoration (VCR), a vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images.<n>This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images.
• Score: 80.24176572093512
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.

Related papers

• Visual Lexicon: Rich Image Features in Language Space [99.94214846451347]
  ViLex simultaneously captures rich semantic content and fine visual details. ViLex generates tokens optimized for reconstructing input images using a frozen text-to-image (T2I) diffusion model. As an image embedding in the language space, ViLex tokens leverage the compositionality of natural languages.
  arXiv  Detail & Related papers  (2024-12-09T18:57:24Z)
• Learning text-to-video retrieval from image captioning [59.81537951811595]
  We describe a protocol to study text-to-video retrieval training with unlabeled videos. We assume (i) no access to labels for any videos, and (ii) access to labeled images in the form of text. We show that automatically labeling video frames with image captioning allows text-to-video retrieval training.
  arXiv  Detail & Related papers  (2024-04-26T15:56:08Z)
• Text encoders bottleneck compositionality in contrastive vision-language models [76.2406963762722]
  We train text-only recovery probes that aim to reconstruct captions from single-vector text representations. We find that CLIP's text encoder falls short on more compositional inputs. Results suggest text-only recoverability is a necessary (but not sufficient) condition for modeling compositional factors.
  arXiv  Detail & Related papers  (2023-05-24T08:48:44Z)
• Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training [70.83385449872495]
  The correlation between the vision and text is essential for video moment retrieval (VMR) Existing methods rely on separate pre-training feature extractors for visual and textual understanding. We propose a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments.
  arXiv  Detail & Related papers  (2023-02-28T19:29:05Z)
• MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval [43.2299969152561]
  Methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols. Our method outperforms state-of-the-art methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols.
  arXiv  Detail & Related papers  (2022-04-26T16:06:31Z)
• Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting [69.77701325270047]
  This paper presents a weakly supervised pre-training method that can acquire effective scene text representations. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features. Experiments show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks.
  arXiv  Detail & Related papers  (2022-03-08T08:10:45Z)
• Primitive Representation Learning for Scene Text Recognition [7.818765015637802]
  We propose a primitive representation learning method that aims to exploit intrinsic representations of scene text images. A Primitive REpresentation learning Network (PREN) is constructed to use the visual text representations for parallel decoding. We also propose a framework called PREN2D to alleviate the misalignment problem in attention-based methods.
  arXiv  Detail & Related papers  (2021-05-10T11:54:49Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.