SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.00579 · 2022

Video + CLIP Baseline for Ego4D Long-term Action Anticipation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 3 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
srijandas07/clip_baseline_lta_ego4d canonical 3 of 9
FunctionStatusWhere it lives
round_width Ran srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py
code served (permissive licence) · get_code("b07e3607b90c1e7c")
topk_errors Ran srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py
code served (permissive licence) · get_code("10e9b4ea0c092f82")
topks_correct Ran srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py
code served (permissive licence) · get_code("eea7a73a4935fff4")
distributed_topk_errors Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/evaluation/lta_metrics.py
code served (permissive licence) · get_code("b6dd75b900cecbb8")
drop_path Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py
code served (permissive licence) · get_code("bcc1cdae3bb3212c")
get_loss_func Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/models/losses.py
code served (permissive licence) · get_code("dd72775d1ea00db7")
get_norm Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/models/batchnorm_helper.py
code served (permissive licence) · get_code("952f23f7aff7ce7d")
get_trans_func Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/models/resnet_helper.py
code served (permissive licence) · get_code("4d6991202a8d6097")
is_detection_enabled Not yet run srijandas07/clip_baseline_lta_ego4d/ego4d/models/video_model_builder.py
code served (permissive licence) · get_code("a99430fceaa1dc2d")

Repositories linked to this paper

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

Abstract

In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action anticipation. Our code is available at github.com/srijandas07/clip_baseline_LTA_Ego4d.

For agents

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

get_harvested_code_for_paper("2207.00579")
get_code_for_paper("2207.00579")
have("2207.00579")

Connect an agent — have() is free.