Papers › 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

26 Feb 2018CVPR 2018 6arXiv:1802.09232archive 2025-07-28

Diogo C. Luvizon, David Picard, Hedi Tabia

Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and human action recognition from video sequences. We show that a single architecture can be used to solve the two problems in an efficient way and still achieves state-of-the-art results. Additionally, we demonstrate that optimization from end-to-end leads to significantly higher accuracy than separated learning. The proposed architecture can be trained with data from different categories simultaneously in a seamlessly way. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU) demonstrate the effectiveness of our method on the targeted tasks.

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="1802.09232")

Code

Syntology Ran 0 of 25 code samples harvested from 1 repository linked to this paper; 25 have no recorded run.

By repository: community (archive-listed): 25 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dluvizon/deephar mentioned on GitHubMIT 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

25 samples harvested; 0 ran; 0 honoured the contract we drafted; 25 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.

25unverified

Licence: 0 of the 25 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 dluvizon/deephar. “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.

action_prediction_early_fusion dluvizon/deephar/deephar/models/spnet.py community (archive-listed) unverified MIT (permissive) · 2b23b3aa62c445cb · report
action_top dluvizon/deephar/deephar/models/action.py community (archive-listed) unverified MIT (permissive) · d103639c80df1e4f · report
add_tensorlist dluvizon/deephar/deephar/models/common.py community (archive-listed) unverified MIT (permissive) · 0cf7210017234f9c · report
build_act_pred_block dluvizon/deephar/deephar/models/action.py community (archive-listed) unverified MIT (permissive) · fe05101a124ed6e5 · report
build_pose_model dluvizon/deephar/deephar/models/action.py community (archive-listed) unverified MIT (permissive) · a7634fec4f5ad0a3 · report
build_reception_block dluvizon/deephar/deephar/models/reception.py community (archive-listed) unverified MIT (permissive) · 6b2a3d9fe907a974 · report
build_regmap_block dluvizon/deephar/deephar/models/reception.py community (archive-listed) unverified MIT (permissive) · 63e1b7fec39396c5 · report
build_sconv_block dluvizon/deephar/deephar/models/reception.py community (archive-listed) unverified MIT (permissive) · d50b506eab82722e · report
channel_softmax_2d dluvizon/deephar/deephar/activations.py community (archive-listed) unverified MIT (permissive) · 3736dce1115c2cd2 · report
concat_tensorlist dluvizon/deephar/deephar/models/common.py community (archive-listed) unverified MIT (permissive) · bdfe57e9d50bfd4f · report
conv2d dluvizon/deephar/deephar/layers.py community (archive-listed) unverified MIT (permissive) · 7bbc7651f4df590a · report
conv_block dluvizon/deephar/deephar/models/blocks.py community (archive-listed) unverified MIT (permissive) · dd1d092a82873639 · report
elasticnet_bincross_loss_on_valid_joints dluvizon/deephar/deephar/losses.py community (archive-listed) unverified MIT (permissive) · 33bbcc52a7b5557f · report
elasticnet_loss_on_valid_joints dluvizon/deephar/deephar/losses.py community (archive-listed) unverified MIT (permissive) · 187971aca9ed7375 · report
elasticnet_loss_on_valid_joints dluvizon/deephar/deephar/objectives.py community (archive-listed) unverified MIT (permissive) · e828ec5077b00a62 · report
identity_block dluvizon/deephar/deephar/models/blocks.py community (archive-listed) unverified MIT (permissive) · 4310717bca3c3fee · report
l1_loss_on_valid_joints dluvizon/deephar/deephar/losses.py community (archive-listed) unverified MIT (permissive) · 5cd044b993eb22d7 · report
mean_distance_error dluvizon/deephar/deephar/measures.py community (archive-listed) unverified MIT (permissive) · 6addcfc360155a19 · report
pck3d dluvizon/deephar/deephar/measures.py community (archive-listed) unverified MIT (permissive) · 365c7a3c29e72751 · report
pckh dluvizon/deephar/deephar/measures.py community (archive-listed) unverified MIT (permissive) · 14edab500394ebe9 · report
prediction_block dluvizon/deephar/deephar/models/spnet.py community (archive-listed) unverified MIT (permissive) · fc7597186a5bf1a3 · report
prediction_branch dluvizon/deephar/deephar/models/spnet.py community (archive-listed) unverified MIT (permissive) · da27fcfda5118da4 · report
relu dluvizon/deephar/deephar/layers.py community (archive-listed) unverified MIT (permissive) · 401ff7831c3db2d1 · report
residual_unit dluvizon/deephar/deephar/models/common.py community (archive-listed) unverified MIT (permissive) · 56b0283b329ccb24 · report
stem_inception_v4 dluvizon/deephar/deephar/models/blocks.py community (archive-listed) unverified MIT (permissive) · 0861e93b7e6d2418 · report

Tasks

3D Human Pose Estimation3D Pose EstimationAction RecognitionAction Recognition In VideosPose EstimationTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition In Videos NTU RGB+D 2D-3D-Softargmax (RGB only) Accuracy (CS) 85.5 #1 of 1 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