Papers › Hyperbolic Audio-visual Zero-shot Learning

Hyperbolic Audio-visual Zero-shot Learning

24 Aug 2023ICCV 2023 1arXiv:2308.12558archive 2025-07-28

Jie Hong, Zeeshan Hayder, Junlin Han, Pengfei Fang, Mehrtash Harandi, Lars Petersson

Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analysis of the audio-visual data reveals a large degree of hyperbolicity, indicating the potential benefit of using a hyperbolic transformation to achieve curvature-aware geometric learning, with the aim of exploring more complex hierarchical data structures for this task. The proposed approach employs a novel loss function that incorporates cross-modality alignment between video and audio features in the hyperbolic space. Additionally, we explore the use of multiple adaptive curvatures for hyperbolic projections. The experimental results on this very challenging task demonstrate that our proposed hyperbolic approach for zero-shot learning outperforms the SOTA method on three datasets: VGGSound-GZSL, UCF-GZSL, and ActivityNet-GZSL achieving a harmonic mean (HM) improvement of around 3.0%, 7.0%, and 5.3%, respectively.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

GZSL Video ClassificationZero-Shot Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
GZSL Video Classification ActivityNet-GZSL (cls) Hyper-multiple HM 15.25 #2 of 4 Archive leaderboard report
GZSL Video Classification ActivityNet-GZSL (cls) Hyper-multiple ZSL 10.39 #2 of 4 Archive leaderboard report
GZSL Video Classification ActivityNet-GZSL(main) Hyper-multiple HM 12.65 #2 of 7 Archive leaderboard report
GZSL Video Classification ActivityNet-GZSL(main) Hyper-multiple ZSL 9.50 #2 of 7 Archive leaderboard report
GZSL Video Classification UCF-GZSL (cls) Hyper-multiple HM 48.30 #3 of 4 Archive leaderboard report
GZSL Video Classification UCF-GZSL (cls) Hyper-multiple ZSL 52.11 #3 of 4 Archive leaderboard report
GZSL Video Classification UCF-GZSL(main) Hyper-multiple HM 29.32 #3 of 7 Archive leaderboard report
GZSL Video Classification UCF-GZSL(main) Hyper-multiple ZSL 22.24 #3 of 7 Archive leaderboard report
GZSL Video Classification VGGSound-GZSL (cls) Hyper-multiple HM 8.67 #3 of 4 Archive leaderboard report
GZSL Video Classification VGGSound-GZSL (cls) Hyper-multiple ZSL 7.31 #3 of 4 Archive leaderboard report
GZSL Video Classification VGGSound-GZSL(main) Hyper-multiple HM 9.32 #2 of 7 Archive leaderboard report
GZSL Video Classification VGGSound-GZSL(main) Hyper-multiple ZSL 7.97 #2 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