paper-with-me

홈 › Papers

Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition

2017-03-24 · Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen

This work deviates from easy-to-define class boundaries for object interactions. For the task of object interaction recognition, often captured using an egocentric view, we show that semantic ambiguities in verbs and recognising sub-interactions along with concurrent interactions result in legitimate class overlaps (Figure 1). We thus aim to model the mapping between observations and interaction classes, as well as class overlaps, towards a probabilistic multi-label classifier that emulates human annotators. Given a video segment containing an object interaction, we model the probability for a verb, out of a list of possible verbs, to be used to annotate that interaction. The proba- bility is learnt from crowdsourced annotations, and is tested on two public datasets, comprising 1405 video sequences for which we provide annotations on 90 verbs. We outper- form conventional single-label classification by 11% and 6% on the two datasets respectively, and show that learning from annotation probabilities outperforms majority voting and enables discovery of co-occurring labels.

📄 PDF Abstract BibTeX arXiv:1703.08338

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationObject

Similar Papers 제목 키워드 기반

Probabilistic Decoupling of Labels in Classification

2019-05-29 · Jeppe Nørregaard, Lars Kai Hansen

We investigate probabilistic decoupling of labels supplied for training, from the underlying classes for prediction. Decoupling enables an inference scheme general enough to implement many classification problems, includ…

ClassificationGeneral Classification

From Articles to Canopies: Knowledge-Driven Pseudo-Labelling for Tree Species Classification using LLM Experts

2026-04-17 · Michał Romaszewski, Dominik Kopeć, Michał Cholewa, Katarzyna Kołodziej 외 arxiv

Hyperspectral tree species classification is challenging due to limited and imbalanced class labels, spectral mixing (overlapping light signatures from multiple species), and ecological heterogeneity (variability among e…

Enhance Robustness of Sequence Labelling with Masked Adversarial Training

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Luoxin Chen, Xinyue Liu, Weitong Ruan, Jianhua Lu

Adversarial training (AT) has shown strong regularization effects on deep learning algorithms by introducing small input perturbations to improve model robustness. In language tasks, adversarial training brings word-leve…

Chunkingnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+4

Weakly supervised localisation of prostate cancer using reinforcement learning for bi-parametric MR images

2024-02-21 · Martynas Pocius, Wen Yan, Dean C. Barratt, Mark Emberton 외

In this paper we propose a reinforcement learning based weakly supervised system for localisation. We train a controller function to localise regions of interest within an image by introducing a novel reward definition t…

Multiple Instance LearningObject

ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification

2021-11-25 · CVPR 2022 1 · Fengbei Liu, Yu Tian, Yuanhong Chen, Yuyuan Liu 외

Effective semi-supervised learning (SSL) in medical image analysis (MIA) must address two challenges: 1) work effectively on both multi-class (e.g., lesion classification) and multi-label (e.g., multiple-disease diagnosi…

image-classificationImage ClassificationMedical Image AnalysisMedical Image Classification+3