{"url":"/method/visual-parsing","slug":"visual-parsing","name":"Visual Parsing","full_name":"Visual Parsing","full_name_withheld":false,"description_markdown":"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. \r\nIt 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.\r\nThree 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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","paper":"/paper/probing-inter-modality-visual-parsing-with-1","first_author":"Hongwei Xue","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/probing-inter-modality-visual-parsing-with-1"},"source":{"url":"https://openreview.net/forum?id=e0nZIFEpmYh","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":"/paper/omnigenbench-a-benchmark-for-omnipotent","title":"OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks","date":"2025-05-24","arxiv_id":"2505.18775","n_code_links":1,"syntology":null},{"paper":null,"title":"The Contemporary Art of Image Search: Iterative User Intent Expansion via Vision-Language Model","date":"2023-12-04","arxiv_id":"2312.01656","n_code_links":0,"syntology":null},{"paper":"/paper/sphinx-the-joint-mixing-of-weights-tasks-and","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","date":"2023-11-13","arxiv_id":"2311.07575","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":null,"title":"Parsing Objects at a Finer Granularity: A Survey","date":"2022-12-28","arxiv_id":"2212.13693","n_code_links":0,"syntology":null},{"paper":"/paper/rlip-relational-language-image-pre-training","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","date":"2022-09-05","arxiv_id":"2209.01814","n_code_links":3,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/probing-inter-modality-visual-parsing-with-1","title":"Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training","date":"2021-05-21","arxiv_id":null,"n_code_links":0,"syntology":null}],"papers_shown":6,"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":null,"name":"Relation","papers":2},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":2},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":2},{"task":"/task/described-object-detection","name":"Described Object Detection","papers":1},{"task":"/task/fine-grained-visual-recognition","name":"Fine-Grained Visual Recognition","papers":1},{"task":"/task/human-part-segmentation","name":"Human Part Segmentation","papers":1},{"task":"/task/human-object-interaction-detection","name":"Human-Object Interaction Detection","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":1},{"task":"/task/instruction-following","name":"Instruction Following","papers":1},{"task":"/task/interactive-segmentation","name":"Interactive Segmentation","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/object-recognition","name":"Object Recognition","papers":1},{"task":"/task/pose-estimation","name":"Pose Estimation","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/survey","name":"Survey","papers":1},{"task":"/task/synthetic-data-generation","name":"Synthetic Data Generation","papers":1}],"tasks_shown":20,"n_tasks":24,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/visual-parsing"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}