SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.07058 · 2021

Ego4D: Around the World in 3,000 Hours of Egocentric Video

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 9 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
ego4d/hands-and-objects canonical 1 of 1
ego4d/episodic-memory pwc_unofficial 5 of 6
copy not recorded — 2 of 2
ego4d/forecasting pwc_unofficial 1 of 6
FunctionStatusWhere it lives
bi_loss Ran ego4d/episodic-memory/MQ/Models/Loss.py
code served (permissive licence) · get_code("7ec8e5ea9abf1846")
convert_annotations_to_clipwise_list Ran ego4d/episodic-memory/VQ2D/extract_vq_detection_scores.py
code served (permissive licence) · get_code("ca522943b8eb15aa")
get_loss_supplement Ran ego4d/episodic-memory/MQ/Models/Loss.py
code served (permissive licence) · get_code("05a34cc547463ca5")
get_neigh_idx_semantic Ran ego4d/episodic-memory/MQ/Models/GCNs.py
code served (permissive licence) · get_code("b00a3a1790c6e560")
interpolated_prec_rec Ran this paper's copy was not recorded; identical code first harvested from Ontheway361/BSN_pytorch
pointer only · get_code("81aab88321de62c2")
nms Ran ego4d/episodic-memory/MQ/Infer.py
code served (permissive licence) · get_code("2ab50acb3969a597")
round_width Ran ego4d/forecasting/ego4d_forecasting/models/video_model_builder.py
code served (permissive licence) · get_code("b07e3607b90c1e7c")
segment_iou Ran this paper's copy was not recorded; identical code first harvested from Ontheway361/BSN_pytorch
pointer only · get_code("d0744a2fe3151508")
wrapper_segment_iou Ran ego4d/hands-and-objects/state-change-localization-classification/bmn/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py
code served (permissive licence) · get_code("265572629e36af77")
drop_path Not yet run ego4d/forecasting/ego4d_forecasting/models/video_model_builder.py
code served (permissive licence) · get_code("bcc1cdae3bb3212c")
get_loss_func Not yet run ego4d/forecasting/ego4d_forecasting/models/losses.py
code served (permissive licence) · get_code("dd72775d1ea00db7")
get_norm Not yet run ego4d/forecasting/ego4d_forecasting/models/batchnorm_helper.py
code served (permissive licence) · get_code("952f23f7aff7ce7d")
get_trans_func Not yet run ego4d/forecasting/ego4d_forecasting/models/resnet_helper.py
code served (permissive licence) · get_code("4d6991202a8d6097")
is_detection_enabled Not yet run ego4d/forecasting/ego4d_forecasting/models/video_model_builder.py
code served (permissive licence) · get_code("a99430fceaa1dc2d")
knn Not yet run ego4d/episodic-memory/MQ/Models/GCNs.py
code served (permissive licence) · get_code("9a2621658570ef96")

Repositories linked to this paper

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

Abstract

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

For agents

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

get_harvested_code_for_paper("2110.07058")
get_code_for_paper("2110.07058")
have("2110.07058")

Connect an agent — have() is free.