Methods › Computer Vision › Vision and Language Pre-Trained Models › Visual Parsing
Visual Parsing
Introduced by Hongwei Xue et al. in Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Visual Parsing is a vision and language pretrained model that adopts self-attention for visual feature learning where each visual token is an approximate weighted mixture of all tokens. Thus, visual parsing provides the dependencies of each visual token pair. It helps better learning of visual relation with the language and promote inter modal alignment. The model is composed of a vision Transformer that takes an image as input and outputs the visual tokens and a multimodal Transformer. It applies a linear layer and a Layer Normalization to embed the vision tokens. It follows BERT to get word embeddings. Vision and language tokens are concatenated to form the input sequences. A multi-modal Transformer is used to fuse the vision and language modality. A metric named Inter-Modality Flow (IMF) is used to quantify the interactions between two modalities. Three pretraining tasks are adopted: Masked Language Modeling (MLM), Image-Text Matching (ITM), and Masked Feature Regression (MFR). MFR is a novel task that is included to mask visual tokens with similar or correlated semantics in this framework.
Papers archive 2025-07-28
6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks 24 May 2025 · 1 repository · arXiv:2505.18775
-
The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model 4 Dec 2023 · 0 repositories · arXiv:2312.01656
-
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models 13 Nov 2023 · 1 repository · arXiv:2311.07575Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
Parsing Objects at a Finer Granularity: A Survey 28 Dec 2022 · 0 repositories · arXiv:2212.13693
-
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection 5 Sep 2022 · 3 repositories · arXiv:2209.01814Syntology ran 0 of 1 samples · 1 unverified
-
Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training 21 May 2021 · 0 repositories
Tasks archive 2025-07-28
20 shown of 24 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections