-
Notifications
You must be signed in to change notification settings - Fork 17
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
c78d897
commit 5cd9de6
Showing
1 changed file
with
170 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,170 @@ | ||
| [ | ||
| { | ||
| "title": "JM-CLIP: A Joint Modal Similarity Contrastive Learning Model for Video-Text Retrieval", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10446490", | ||
| "github": "DannielGe/JM-CLIP", | ||
| "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": "Language-Free Compositional Action Generation via Decoupling Refinement", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10448207", | ||
| "github": "XLiu443/Language-free-Compositional-Action-Generation-via-Decoupling-Refinement", | ||
| "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": "2307.03538", | ||
| "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": "DAP: Domain-Aware Prompt Learning for Vision-and-Language Navigation", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10446504", | ||
| "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": "2311.17812", | ||
| "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": "M3sum: A Novel Unsupervised Language-Guided Video Summarization", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10447504", | ||
| "github": "ZovanZhou/M3Sum", | ||
| "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": "WAVER: Writing-Style Agnostic Text-Video Retrieval via Distilling Vision-Language Models through Open-Vocabulary Knowledge", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10446193", | ||
| "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": "2312.09507", | ||
| "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": "MTIDNet: A Multimodal Temporal Interest Detection Network for Video Summarization", | ||
| "base_url": null, | ||
| "title_page": null, | ||
| "ieee_id": "10448236", | ||
| "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" | ||
| } | ||
| ] |