Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288334673> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4288334673 abstract "Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal models of the users states (e.g., engagement) are therefore needed. Most of the existing works that try to build classifiers for the users states assume that the data to train the models are fully labeled. Nevertheless, data labeling is costly and tedious, and also prone to subjective interpretations by the human coders. This is even more pronounced when the data are multi-modal (e.g., some users are more expressive with their facial expressions, some with their voice). Thus, building models that can accurately estimate the users states during an interaction is challenging. To tackle this, we propose a novel multi-modal active learning (AL) approach that uses the notion of deep reinforcement learning (RL) to find an optimal policy for active selection of the users data, needed to train the target (modality-specific) models. We investigate different strategies for multi-modal data fusion, and show that the proposed model-level fusion coupled with RL outperforms the feature-level and modality-specific models, and the naive AL strategies such as random sampling, and the standard heuristics such as uncertainty sampling. We show the benefits of this approach on the task of engagement estimation from real-world child-robot interactions during an autism therapy. Importantly, we show that the proposed multi-modal AL approach can be used to efficiently personalize the engagement classifiers to the target user using a small amount of actively selected users data." @default.
- W4288334673 created "2022-07-28" @default.
- W4288334673 creator A5006602426 @default.
- W4288334673 creator A5038571306 @default.
- W4288334673 creator A5043060302 @default.
- W4288334673 creator A5087366916 @default.
- W4288334673 date "2019-06-07" @default.
- W4288334673 modified "2023-09-26" @default.
- W4288334673 title "Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach" @default.
- W4288334673 doi "https://doi.org/10.48550/arxiv.1906.03098" @default.
- W4288334673 hasPublicationYear "2019" @default.
- W4288334673 type Work @default.
- W4288334673 citedByCount "0" @default.
- W4288334673 crossrefType "posted-content" @default.
- W4288334673 hasAuthorship W4288334673A5006602426 @default.
- W4288334673 hasAuthorship W4288334673A5038571306 @default.
- W4288334673 hasAuthorship W4288334673A5043060302 @default.
- W4288334673 hasAuthorship W4288334673A5087366916 @default.
- W4288334673 hasBestOaLocation W42883346731 @default.
- W4288334673 hasConcept C106131492 @default.
- W4288334673 hasConcept C111919701 @default.
- W4288334673 hasConcept C119857082 @default.
- W4288334673 hasConcept C127705205 @default.
- W4288334673 hasConcept C138885662 @default.
- W4288334673 hasConcept C140779682 @default.
- W4288334673 hasConcept C154945302 @default.
- W4288334673 hasConcept C185592680 @default.
- W4288334673 hasConcept C188027245 @default.
- W4288334673 hasConcept C199360897 @default.
- W4288334673 hasConcept C2776401178 @default.
- W4288334673 hasConcept C2780226545 @default.
- W4288334673 hasConcept C31972630 @default.
- W4288334673 hasConcept C41008148 @default.
- W4288334673 hasConcept C41895202 @default.
- W4288334673 hasConcept C71139939 @default.
- W4288334673 hasConcept C90559484 @default.
- W4288334673 hasConcept C97541855 @default.
- W4288334673 hasConceptScore W4288334673C106131492 @default.
- W4288334673 hasConceptScore W4288334673C111919701 @default.
- W4288334673 hasConceptScore W4288334673C119857082 @default.
- W4288334673 hasConceptScore W4288334673C127705205 @default.
- W4288334673 hasConceptScore W4288334673C138885662 @default.
- W4288334673 hasConceptScore W4288334673C140779682 @default.
- W4288334673 hasConceptScore W4288334673C154945302 @default.
- W4288334673 hasConceptScore W4288334673C185592680 @default.
- W4288334673 hasConceptScore W4288334673C188027245 @default.
- W4288334673 hasConceptScore W4288334673C199360897 @default.
- W4288334673 hasConceptScore W4288334673C2776401178 @default.
- W4288334673 hasConceptScore W4288334673C2780226545 @default.
- W4288334673 hasConceptScore W4288334673C31972630 @default.
- W4288334673 hasConceptScore W4288334673C41008148 @default.
- W4288334673 hasConceptScore W4288334673C41895202 @default.
- W4288334673 hasConceptScore W4288334673C71139939 @default.
- W4288334673 hasConceptScore W4288334673C90559484 @default.
- W4288334673 hasConceptScore W4288334673C97541855 @default.
- W4288334673 hasLocation W42883346731 @default.
- W4288334673 hasOpenAccess W4288334673 @default.
- W4288334673 hasPrimaryLocation W42883346731 @default.
- W4288334673 hasRelatedWork W2179579997 @default.
- W4288334673 hasRelatedWork W2231070293 @default.
- W4288334673 hasRelatedWork W2936900244 @default.
- W4288334673 hasRelatedWork W3022038857 @default.
- W4288334673 hasRelatedWork W3093691203 @default.
- W4288334673 hasRelatedWork W3198037411 @default.
- W4288334673 hasRelatedWork W4226120250 @default.
- W4288334673 hasRelatedWork W4301366326 @default.
- W4288334673 hasRelatedWork W4307007972 @default.
- W4288334673 hasRelatedWork W4319083788 @default.
- W4288334673 isParatext "false" @default.
- W4288334673 isRetracted "false" @default.
- W4288334673 workType "article" @default.