From f02931c0899d25b15b3bf3e87cbc1f5ed3a59f35 Mon Sep 17 00:00:00 2001
From: Dmitry Ryumin <neweraairesearch@gmail.com>
Date: Thu, 21 Mar 2024 16:56:11 +0300
Subject: [PATCH] Update files

---
 json_data/2024/main/IVMSP.json | 644 +++++++++++++++++++++++++++++++++
 1 file changed, 644 insertions(+)

diff --git a/json_data/2024/main/IVMSP.json b/json_data/2024/main/IVMSP.json
index 89e0ae3..6eec477 100644
--- a/json_data/2024/main/IVMSP.json
+++ b/json_data/2024/main/IVMSP.json
@@ -166,5 +166,649 @@
     "onedrive": null,
     "loom": null,
     "section": "Vision and Language"
+  },
+  {
+    "title": "Human Guided Cross-Modal Reasoning with Semantic Attention Learning for Visual Question Answering",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10448302",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Semanticmapper: Region-Specific Domain Adaptation for 3D Shapes Through Lexical Delineation",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446758",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Self-Distilled Dynamic Fusion Network for Language-based Fashion Retrieval",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10445903",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Implicit-Knowledge-Guided Align Before Understanding for KB-VQA",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10448108",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Imitating the Human Visual System for Scanpath Predicting",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447354",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Read, Spell and Repeat: Scene Text Recognition with Vision-Language Circular Refinement",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446176",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "End-to-End Spatially-Constrained Multi-Perspective Fine-Grained Image Captioning",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10445846",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Improved Image Captioning via Knowledge Graph-Augmented Models",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447637",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Think as People: Context-Driven Multi-Image News Captioning with Adaptive Dual Attention",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446024",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "MGRL: Mutual-Guidance Representation Learning for Text-to-Image Person Retrieval",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447260",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Fine-Grained Features Alignment and Fusion for Text-Video Cross-Modal Retrieval",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446511",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Label Correction for Sketch-based 3d Shape Retrieval",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447927",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Glocal Cascading Network for Topic Enhanced Visual Storytelling",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447361",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "CROCFUN: Cross-Modal Conditional Fusion Network for Pansharpening",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446470",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Domain-Wise Invariant Learning for Panoptic Scene Graph Generation",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447193",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": "2310.05867",
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "CReStyler: Text-Guided Single Image Style Transfer Method based on CNN and Restormer",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446192",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Maskstr: Guide Scene Text Recognition Models with Masking",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446874",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Supplementing Missing Visions via Dialog for Scene Graph Generations",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446239",
+    "github": "L-YeZhu/SI-Dial",
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": "2204.11143",
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "CKT-RCM: Clip-based Knowledge Transfer and Relational Context Mining for Unbiased Panoptic Scene Graph Generation",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446810",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Memory Self-Calibrated Network for Visual Grounding",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447732",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Text-Video Completion Networks with Motion Compensation and Attention Aggregation",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10447901",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "M2SUM: Multi-Granularity Scale-Adaptive Video Summarizer towards Informative Context Representation Learning",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10446527",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
+  },
+  {
+    "title": "Template-Guided Data Augmentation for Unbiased Scene Graph Generation",
+    "base_url": null,
+    "title_page": null,
+    "ieee_id": "10448033",
+    "github": null,
+    "web_page": null,
+    "github_page": null,
+    "colab": null,
+    "modelscope": null,
+    "gitee": null,
+    "gitlab": null,
+    "zenodo": null,
+    "kaggle": null,
+    "demo_page": null,
+    "paper_thecvf": null,
+    "paper_arxiv_id": null,
+    "paper_pdf": null,
+    "paper_hal_science": null,
+    "paper_researchgate": null,
+    "paper_amazon": null,
+    "youtube_id": null,
+    "drive_google": null,
+    "dropbox": null,
+    "onedrive": null,
+    "loom": null,
+    "section": "Vision and Language"
   }
 ]
\ No newline at end of file