Papers › Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

14 Jun 2020CVPR 2021 1arXiv:2006.07976archive 2025-07-28

Junting Pan, Siyu Chen, Mike Zheng Shou, Yu Liu, Jing Shao, Hongsheng Li

Localizing persons and recognizing their actions from videos is a challenging task towards high-level video understanding. Recent advances have been achieved by modeling direct pairwise relations between entities. In this paper, we take one step further, not only model direct relations between pairs but also take into account indirect higher-order relations established upon multiple elements. We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context. To this end, we design an Actor-Context-Actor Relation Network (ACAR-Net) which builds upon a novel High-order Relation Reasoning Operator and an Actor-Context Feature Bank to enable indirect relation reasoning for spatio-temporal action localization. Experiments on AVA and UCF101-24 datasets show the advantages of modeling actor-context-actor relations, and visualization of attention maps further verifies that our model is capable of finding relevant higher-order relations to support action detection. Notably, our method ranks first in the AVA-Kineticsaction localization task of ActivityNet Challenge 2020, out-performing other entries by a significant margin (+6.71mAP). Training code and models will be available at https://github.com/Siyu-C/ACAR-Net.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.07976")

Code

Syntology Ran 1 of 27 code samples harvested from 2 repositories linked to this paper; 26 have no recorded run. Of those that ran: 1 ran · violated contract.

By repository: official repository: 21 samples from 1 repository, 0 ran; community (archive-listed): 6 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Siyu-C/ACAR-Net officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
salmank255/ROADSlowFast mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

27 samples harvested; 1 ran; 0 honoured the contract we drafted; 26 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
26unverified

Licence: 0 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

area Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py official repository unverified Apache-2.0 (permissive) · ae6e56e979816086 · report
ava_criterion Siyu-C/ACAR-Net/losses.py official repository unverified Apache-2.0 (permissive) · 2751c2cbb8d17356 · report
ava_pose_softmax_criterion Siyu-C/ACAR-Net/losses.py official repository unverified Apache-2.0 (permissive) · 3b570b6730c1319f · report
ava_pose_softmax_func Siyu-C/ACAR-Net/losses.py official repository unverified Apache-2.0 (permissive) · b93cca48f0e47db7 · report
box_list_to_box_mask_list Siyu-C/ACAR-Net/ava_evaluation/np_box_mask_list_ops.py official repository unverified Apache-2.0 (permissive) · 3a972d2a2de3e7f6 · report
compute_average_precision Siyu-C/ACAR-Net/ava_evaluation/metrics.py official repository unverified Apache-2.0 (permissive) · 029d0444c2c321d4 · report
compute_cor_loc Siyu-C/ACAR-Net/ava_evaluation/metrics.py official repository unverified Apache-2.0 (permissive) · c0b97624f9249399 · report
compute_precision_recall Siyu-C/ACAR-Net/ava_evaluation/metrics.py official repository unverified Apache-2.0 (permissive) · 9faafd74ff0068a0 · report
convert_label_map_to_categories Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py official repository unverified Apache-2.0 (permissive) · a5a7cde0ddc2ebbc · report
create_category_index Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py official repository unverified Apache-2.0 (permissive) · dc6b3dd700e4eea1 · report
create_logger Siyu-C/ACAR-Net/utils.py official repository unverified Apache-2.0 (permissive) · abf34766c2f1571a · report
get_env_variable Siyu-C/ACAR-Net/distributed_utils.py official repository unverified Apache-2.0 (permissive) · 452dcb1b9317d2d9 · report
get_max_label_map_index Siyu-C/ACAR-Net/ava_evaluation/label_map_util.py official repository unverified Apache-2.0 (permissive) · d3367980903ee2a9 · report
get_scheduler Siyu-C/ACAR-Net/scheduler.py official repository unverified Apache-2.0 (permissive) · 6ecced1e66623371 · report
init_distributed Siyu-C/ACAR-Net/distributed_utils.py official repository unverified Apache-2.0 (permissive) · bae310a052f21971 · report
intersection Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py official repository unverified Apache-2.0 (permissive) · 9563a9a954385a6d · report
iou Siyu-C/ACAR-Net/ava_evaluation/np_box_list_ops.py official repository unverified Apache-2.0 (permissive) · a7428b0e09d7a2d5 · report
make_image_key Siyu-C/ACAR-Net/calc_mAP.py official repository unverified Apache-2.0 (permissive) · 15e577f3614f1586 · report
parameters_string Siyu-C/ACAR-Net/utils.py official repository unverified Apache-2.0 (permissive) · 45a26c192ff99933 · report
read_csv Siyu-C/ACAR-Net/calc_mAP.py official repository unverified Apache-2.0 (permissive) · 897e38093ca7f101 · report
read_exclusions Siyu-C/ACAR-Net/calc_mAP.py official repository unverified Apache-2.0 (permissive) · b49799a287ea9eec · report
str2bool salmank255/ROADSlowFast/inference_vis.py community (archive-listed) ran · violated contract Apache-2.0 (permissive) · 25c7475539e39da4 · report
backbone_models salmank255/ROADSlowFast/models/backbone_models.py community (archive-listed) unverified Apache-2.0 (permissive) · 5fd8c2cc3399ab75 · report
get_area salmank255/ROADSlowFast/kmean_anchors.py community (archive-listed) unverified Apache-2.0 (permissive) · 70645db2047d82ec · report
get_center salmank255/ROADSlowFast/kmean_anchors.py community (archive-listed) unverified Apache-2.0 (permissive) · bf09436830878aaa · report
set_out_video salmank255/ROADSlowFast/inference_vis.py community (archive-listed) unverified Apache-2.0 (permissive) · 5040afe356ddac29 · report
set_video salmank255/ROADSlowFast/inference_vis.py community (archive-listed) unverified Apache-2.0 (permissive) · 21947d8387b20363 · report

Tasks

Action DetectionAction LocalizationAction RecognitionRelation NetworkSpatio-Temporal Action LocalizationTemporal Action LocalizationVideo Understanding

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition AVA v2.1 ACAR-Net, SlowFast R-101 (Kinetics-400 pretraining) mAP (Val) 30.0 #2 of 15 Archive leaderboard report
Action Recognition AVA v2.2 ACAR-Net, SlowFast R-101 (Kinetics-700 pretraining) mAP 31.72 #24 of 38 Archive leaderboard report
Spatio-Temporal Action Localization AVA-Kinetics ACAR (multi-scale, ensemble) test mAP 39.62 #5 of 7 Archive leaderboard report
Spatio-Temporal Action Localization AVA-Kinetics ACAR (multi-scale, ensemble) val mAP 40.49 #5 of 7 Archive leaderboard report
Spatio-Temporal Action Localization AVA-Kinetics ACAR (multi-scale, R-101, 8 × 8) val mAP 36.36 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections