paper-with-me

홈 › Papers

Exploring Self- and Cross-Triplet Correlations for Human-Object Interaction Detection

2024-01-11 · Weibo Jiang, Weihong Ren, Jiandong Tian, Liangqiong Qu, Zhiyong Wang, Honghai Liu

Human-Object Interaction (HOI) detection plays a vital role in scene understanding, which aims to predict the HOI triplet in the form of <human, object, action>. Existing methods mainly extract multi-modal features (e.g., appearance, object semantics, human pose) and then fuse them together to directly predict HOI triplets. However, most of these methods focus on seeking for self-triplet aggregation, but ignore the potential cross-triplet dependencies, resulting in ambiguity of action prediction. In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection. Specifically, we regard each triplet proposal as a graph where Human, Object represent nodes and Action indicates edge, to aggregate self-triplet correlation. Also, we try to explore cross-triplet dependencies by jointly considering instance-level, semantic-level, and layout-level relations. Besides, we leverage the CLIP model to assist our SCTC obtain interaction-aware feature by knowledge distillation, which provides useful action clues for HOI detection. Extensive experiments on HICO-DET and V-COCO datasets verify the effectiveness of our proposed SCTC.

📄 PDF Abstract BibTeX arXiv:2401.05676

Code (0)

등록된 구현이 없습니다.

Tasks

Human-Object Interaction DetectionKnowledge DistillationObjectScene UnderstandingTriplet

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Exploring Correlations of Self-Supervised Tasks for Graphs

2024-05-07 · Taoran Fang, Wei Zhou, Yifei Sun, Kaiqiao Han 외

Graph self-supervised learning has sparked a research surge in training informative representations without accessing any labeled data. However, our understanding of graph self-supervised learning remains limited, and th…

Multi-Task LearningSelf-Supervised Learning

Triplet Attention Transformer for Spatiotemporal Predictive Learning

2023-10-28 · Xuesong Nie, Xi Chen, Haoyuan Jin, Zhihang Zhu 외

Spatiotemporal predictive learning offers a self-supervised learning paradigm that enables models to learn both spatial and temporal patterns by predicting future sequences based on historical sequences. Mainstream metho…

Computational EfficiencyPredictionSelf-Supervised LearningTrajectory Prediction+1

Deep Comprehensive Correlation Mining for Image Clustering

2019-04-15 · ICCV 2019 10 · Jianlong Wu, Keyu Long, Fei Wang, Chen Qian 외

Recent developed deep unsupervised methods allow us to jointly learn representation and cluster unlabelled data. These deep clustering methods mainly focus on the correlation among samples, e.g., selecting high precision…

ClusteringDeep ClusteringImage ClusteringPseudo Label+1

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

2023-07-25 · ICCV 2023 1 · Yichao Cao, Qingfei Tang, Feng Yang, Xiu Su 외

Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the …

Human-Object Interaction DetectionSentenceTransfer Learning

Cross-Modal Subspace Learning with Scheduled Adaptive Margin Constraints

2019-09-30 · David Semedo, João Magalhães

Cross-modal embeddings, between textual and visual modalities, aim to organise multimodal instances by their semantic correlations. State-of-the-art approaches use maximum-margin methods, based on the hinge-loss, to enfo…

Incremental LearningTriplet