paper-with-me

홈 › Papers

Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection

2024-09-28 · Jiaxu Leng, Zhanjie Wu, Mingpi Tan, Yiran Liu, Ji Gan, Haosheng Chen, Xinbo Gao

While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leading to weaknesses in recognizing normal events that are visually similar to violent events (\emph{i.e.}, ambiguous violence). In contrast, hyperbolic representation learning, renowned for its ability to model hierarchical and complex relationships between events, has the potential to amplify the discrimination between visually similar events. Inspired by these, we develop a novel Dual-Space Representation Learning (DSRL) method for weakly supervised VVD to utilize the strength of both Euclidean and hyperbolic geometries, capturing the visual features of events while also exploring the intrinsic relations between events, thereby enhancing the discriminative capacity of the features. DSRL employs a novel information aggregation strategy to progressively learn event context in hyperbolic spaces, which selects aggregation nodes through layer-sensitive hyperbolic association degrees constrained by hyperbolic Dirichlet energy. Furthermore, DSRL attempts to break the cyber-balkanization of different spaces, utilizing cross-space attention to facilitate information interactions between Euclidean and hyperbolic space to capture better discriminative features for final violence detection. Comprehensive experiments demonstrate the effectiveness of our proposed DSRL.

📄 PDF Abstract BibTeX arXiv:2409.19252

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Quaternion Graph Neural Networks

2020-08-12 · Dai Quoc Nguyen, Tu Dinh Nguyen, Dinh Phung

Recently, graph neural networks (GNNs) have become an important and active research direction in deep learning. It is worth noting that most of the existing GNN-based methods learn graph representations within the Euclid…

General ClassificationGraph ClassificationGraph EmbeddingKnowledge Graph Completion+4

Quotient-Based Posterior Analysis for Euclidean Latent Space Models

2026-04-03 · Kisung You, Mauro Giuffrè arxiv

Latent space models are widely used in statistical network analysis and are often fit by Markov chain Monte Carlo. However, posterior summaries of latent coordinates are not canonical because the likelihood depends only …

Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation

2026-06-28 · Jongoh Jeong, Sun-Kyung Lee, Kuk-Jin Yoon hf

Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute bud…

Cross-Modal Retrieval

Neural Fields as Distributions: Signal Processing Beyond Euclidean Space

2024-01-01 · CVPR 2024 1 · Daniel Rebain, Soroosh Yazdani, Kwang Moo Yi, Andrea Tagliasacchi

Neural fields have emerged as a powerful and broadly applicable method for representing signals. However in contrast to classical discrete digital signal processing the portfolio of tools to process such representati…

The Bregman Variational Dual-Tree Framework

2013-09-26 · Saeed Amizadeh, Bo Thiesson, Milos Hauskrecht

Graph-based methods provide a powerful tool set for many non-parametric frameworks in Machine Learning. In general, the memory and computational complexity of these methods is quadratic in the number of examples in the d…

Text Categorization