paper-with-me

Papers

Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition

2021-07-26 · ICCV 2021 10 · Ayan Kumar Bhunia, Aneeshan Sain, Amandeep Kumar, Shuvozit Ghose, Pinaki Nath Chowdhury, Yi-Zhe Song

Although text recognition has significantly evolved over the years, state-of-the-art (SOTA) models still struggle in the wild scenarios due to complex backgrounds, varying fonts, uncontrolled illuminations, distortions and other artefacts. This is because such models solely depend on visual information for text recognition, thus lacking semantic reasoning capabilities. In this paper, we argue that semantic information offers a complementary role in addition to visual only. More specifically, we additionally utilize semantic information by proposing a multi-stage multi-scale attentional decoder that performs joint visual-semantic reasoning. Our novelty lies in the intuition that for text recognition, the prediction should be refined in a stage-wise manner. Therefore our key contribution is in designing a stage-wise unrolling attentional decoder where non-differentiability, invoked by discretely predicted character labels, needs to be bypassed for end-to-end training. While the first stage predicts using visual features, subsequent stages refine on top of it using joint visual-semantic information. Additionally, we introduce multi-scale 2D attention along with dense and residual connections between different stages to deal with varying scales of character sizes, for better performance and faster convergence during training. Experimental results show our approach to outperform existing SOTA methods by a considerable margin.

📄 PDF Abstract BibTeX arXiv:2107.12090

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderRolling Shutter Correction

Similar Papers 제목 키워드 기반

Semantic-Enriched Latent Visual Reasoning

2026-05-19 · Tianrun Xu, Yue Sun, Qixun Wang, Jingyi Lu 외 arxiv

Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produ…

Question AnsweringVisual Reasoning

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

2026-01-05 · Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu 외 arxiv

Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reas…

Information ExtractionMathematical Reasoning

MedVL-SAM2: A unified 3D medical vision-language model for multimodal reasoning and prompt-driven segmentation

2026-01-14 · Yang Xing, Jiong Wu, Savas Ozdemir, Ying Zhang 외 arxiv

Recent progress in medical vision-language models (VLMs) has achieved strong performance on image-level text-centric tasks such as report generation and visual question answering (VQA). However, achieving fine-grained vi…

Visual Question AnsweringInteractive SegmentationMultimodal ReasoningSpatial Reasoning

Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation

2025-11-21 · Shuo Wang, Yucheng Wang, Guoxin Lian, Yongcai Wang 외 arxiv

Vision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they have advanced within a multi-step instruction. However, recent Vision-L…

Vision-Language Navigation

Chatting with Images for Introspective Visual Thinking

2026-02-11 · Junfei Wu, Jian Guan, Qiang Liu, Shu Wu 외 arxiv

Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual information. Recently the proposal of ''thinking…

Reinforcement LearningSpatial ReasoningVisual Reasoning