SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.10816 · NeurIPS · 2024

LVD-2M: A Long-take Video Dataset with Temporally Dense Captions

Jiashi Feng, Yuqing Wang, Zhijie Lin, Xihui Liu, Daquan Zhou, Tianwei Xiong

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
silentview/lvd-2m canonical 5 of 5
SilentView/LVD-2M canonical 2 of 2
FunctionStatusWhere it lives
cache Ran silentview/lvd-2m/pytube/helpers.py
pointer only (licence: NONE) · get_code("fd8738bf3f18e932")
cal_span_time Ran SilentView/LVD-2M/download_videos_release.py
pointer only (licence: NONE) · get_code("ed810f1befb0a75c")
get_format_profile Ran silentview/lvd-2m/pytube/itags.py
pointer only (licence: NONE) · get_code("288cd7ed350c4225")
is_private Ran silentview/lvd-2m/pytube/extract.py
pointer only (licence: NONE) · get_code("bbc530b455c98aa3")
parse_time Ran SilentView/LVD-2M/download_videos_release.py
pointer only (licence: NONE) · get_code("177afae9e319dff7")
recording_available Ran silentview/lvd-2m/pytube/extract.py
pointer only (licence: NONE) · get_code("90dfd7518fe80b47")
safe_filename Ran silentview/lvd-2m/pytube/helpers.py
pointer only (licence: NONE) · get_code("65bcff147b37d623")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Others: Videos with small motion Ours: Long-take Videos longer than 10s Ours: Large-motion Videos Others: Videos with Scene Cut A man in a yellow jacket walking through a restaurant. The video appears to depict a man in a bright yellow jacket who is the central figure. The setting seems to be an indoor, professional or educational environment, such as a conference room or office, with high ceilings, large windows, and furnishings like tables and chairs. The man is shown walking into the room, engaging in a conversation with another person, and then interacting with a group of people seated around a table, suggesting a meeting or discussion. The man's actions and prominent attire suggest he is the main subject of the video.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.10816")
get_code_for_paper("2410.10816")
have("2410.10816")

Connect an agent — have() is free.