Papers › Spatial-Temporal Transformer for Dynamic Scene Graph Generation

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

26 Jul 2021ICCV 2021 10arXiv:2107.12309archive 2025-07-28

Yuren Cong, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn, Michael Ying Yang

Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2107.12309")

Code

Syntology Ran 7 of 14 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 2 ran; community (archive-listed): 5 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yrcong/sttran officialmentioned in papermentioned on GitHubpytorchMIT report
lunaproject22/aar mentioned on GitHubpytorch 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

14 samples harvested; 7 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

7ran
7unverified

Licence: 5 of the 14 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.

get_ranking yrcong/STTran/lib/pytorch_misc.py official repository ran MIT (permissive) · a1e587129dd2dfaf · report
pairwise yrcong/STTran/lib/pytorch_misc.py official repository ran MIT (permissive) · fef49730c9e9a2b8 · report
cuda_collate_fn yrcong/STTran/dataloader/action_genome.py official repository unverified MIT (permissive) · 3b53b8b24f740103 · report
im_list_to_blob yrcong/STTran/lib/funcs.py official repository unverified MIT (permissive) · d614ca29b05d68ec · report
load_word_vectors yrcong/STTran/lib/word_vectors.py official repository unverified MIT (permissive) · 7fee693dfb2f64b5 · report
obj_edge_vectors yrcong/STTran/lib/word_vectors.py official repository unverified MIT (permissive) · 3b52f8f6c24ea8da · report
optimistic_restore yrcong/STTran/lib/pytorch_misc.py official repository unverified MIT (permissive) · 6d0daf87a6ec7e39 · report
reporthook yrcong/STTran/lib/word_vectors.py official repository unverified MIT (permissive) · e31361e8a2fbb396 · report
transpose_packed_sequence_inds yrcong/STTran/lib/funcs.py official repository unverified MIT (permissive) · bbdc9c82250ba50d · report
TransformerDecoder lunaproject22/aar/lib/transformer.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 22fd84f6ef1eaa10 · report
TransformerDecoderLayer lunaproject22/aar/lib/transformer.py community (archive-listed) ran no licence file found · pointer only · 65aa79798bcd2990 · report
TransformerEncoder lunaproject22/aar/lib/transformer.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 040179c6bd8eb32f · report
TransformerEncoderLayer lunaproject22/aar/lib/transformer.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · cf0d96423bcfe244 · report
transformer lunaproject22/aar/lib/transformer.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 1e8a7993eb1f6599 · report

Tasks

DecoderScene Graph GenerationVideo UnderstandingVideo Visual Relation DetectionVisual Relationship Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionTransformer

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