Papers › Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through...

Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness

19 May 2023arXiv:2305.11468archive 2025-07-28

Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie

Graph Convolutional Networks (GCNs) have long defined the state-of-the-art in skeleton-based action recognition, leveraging their ability to unravel the complex dynamics of human joint topology through the graph's adjacency matrix. However, an inherent flaw has come to light in these cutting-edge models: they tend to optimize the adjacency matrix jointly with the model weights. This process, while seemingly efficient, causes a gradual decay of bone connectivity data, culminating in a model indifferent to the very topology it sought to map. As a remedy, we propose a threefold strategy: (1) We forge an innovative pathway that encodes bone connectivity by harnessing the power of graph distances. This approach preserves the vital topological nuances often lost in conventional GCNs. (2) We highlight an oft-overlooked feature - the temporal mean of a skeletal sequence, which, despite its modest guise, carries highly action-specific information. (3) Our investigation revealed strong variations in joint-to-joint relationships across different actions. This finding exposes the limitations of a single adjacency matrix in capturing the variations of relational configurations emblematic of human movement, which we remedy by proposing an efficient refinement to Graph Convolutions (GC) - the BlockGC. This evolution slashes parameters by a substantial margin (above 40%), while elevating performance beyond original GCNs. Our full model, the BlockGCN, establishes new standards in skeleton-based action recognition for small model sizes. Its high accuracy, notably on the large-scale NTU RGB+D 120 dataset, stand as compelling proof of the efficacy of BlockGCN.

PaperPDFCodeCode 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="2305.11468")

Code

Syntology Ran 10 of 12 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhouyuxuanyx/blockgcn officialmentioned in papermentioned 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

12 samples harvested; 10 ran; 0 honoured the contract we drafted; 2 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
3ran · our draft was wrong
6ran
2unverified

Licence: 0 of the 12 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 zhouyuxuanyx/blockgcn. “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.

downsample zhouyuxuanyx/blockgcn/feeders/tools.py official repository ran Apache-2.0 (permissive) · 8b14974e8aa7320f · report
edge2mat zhouyuxuanyx/blockgcn/graph/tools.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 5f5ae82020ac7ec2 · report
get_k_scale_graph zhouyuxuanyx/blockgcn/graph/tools.py official repository ran Apache-2.0 (permissive) · d3e8dd52d4a2755a · report
get_sgp_mat zhouyuxuanyx/blockgcn/graph/tools.py official repository ran Apache-2.0 (permissive) · 5940d00ced3d0637 · report
import_class zhouyuxuanyx/blockgcn/model/BlockGCN.py official repository ran · our draft was wrong Apache-2.0 (permissive) · ffed4f85d50832c9 · report
import_class zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 4e946d7c92be9d41 · report
ngpu zhouyuxuanyx/blockgcn/torchlight/torchlight/gpu.py official repository ran fingerprinted Apache-2.0 (permissive) · 83ed4b272b1e38d0 · report
str2bool zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py official repository ran · violated contract Apache-2.0 (permissive) · f017532fc389cbfe · report
valid_crop_resize zhouyuxuanyx/blockgcn/feeders/tools.py official repository ran Apache-2.0 (permissive) · 37939bae213ecfd4 · report
visible_gpu zhouyuxuanyx/blockgcn/torchlight/torchlight/gpu.py official repository ran fingerprinted Apache-2.0 (permissive) · 621e08e84928c5c3 · report
str2dict zhouyuxuanyx/blockgcn/torchlight/torchlight/util.py official repository unverified Apache-2.0 (permissive) · 1e89b2b546737164 · report
temporal_slice zhouyuxuanyx/blockgcn/feeders/tools.py official repository unverified Apache-2.0 (permissive) · 2f7f389f0584c97e · report

Tasks

Action RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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