SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.12309 · ICCV · 2021

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 7 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
yrcong/STTran canonical 2 of 9
lunaproject22/aar — 5 of 5
FunctionStatusWhere it lives
TransformerDecoder Ran lunaproject22/aar/lib/transformer.py
pointer only (licence: NONE) · get_code("22fd84f6ef1eaa10")
TransformerDecoderLayer Ran lunaproject22/aar/lib/transformer.py
pointer only (licence: NONE) · get_code("65aa79798bcd2990")
TransformerEncoder Ran lunaproject22/aar/lib/transformer.py
pointer only (licence: NONE) · get_code("040179c6bd8eb32f")
TransformerEncoderLayer Ran lunaproject22/aar/lib/transformer.py
pointer only (licence: NONE) · get_code("cf0d96423bcfe244")
get_ranking Ran yrcong/STTran/lib/pytorch_misc.py
code served (permissive licence) · get_code("a1e587129dd2dfaf")
pairwise Ran yrcong/STTran/lib/pytorch_misc.py
code served (permissive licence) · get_code("fef49730c9e9a2b8")
transformer Ran lunaproject22/aar/lib/transformer.py
pointer only (licence: NONE) · get_code("1e8a7993eb1f6599")
cuda_collate_fn Not yet run yrcong/STTran/dataloader/action_genome.py
code served (permissive licence) · get_code("3b53b8b24f740103")
im_list_to_blob Not yet run yrcong/STTran/lib/funcs.py
code served (permissive licence) · get_code("d614ca29b05d68ec")
load_word_vectors Not yet run yrcong/STTran/lib/word_vectors.py
code served (permissive licence) · get_code("7fee693dfb2f64b5")
obj_edge_vectors Not yet run yrcong/STTran/lib/word_vectors.py
code served (permissive licence) · get_code("3b52f8f6c24ea8da")
optimistic_restore Not yet run yrcong/STTran/lib/pytorch_misc.py
code served (permissive licence) · get_code("6d0daf87a6ec7e39")
reporthook Not yet run yrcong/STTran/lib/word_vectors.py
code served (permissive licence) · get_code("e31361e8a2fbb396")
transpose_packed_sequence_inds Not yet run yrcong/STTran/lib/funcs.py
code served (permissive licence) · get_code("bbdc9c82250ba50d")

Repositories linked to this paper

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

Abstract

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.

For agents

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

get_harvested_code_for_paper("2107.12309")
get_code_for_paper("2107.12309")
have("2107.12309")

Connect an agent — have() is free.