Video Relationship Detection Using Mixture of Experts
نویسندگان
چکیده
Machine comprehension of visual information from images and videos by neural networks suffers two limitations: (1) the computational inference gap in vision language to accurately determine which object a given agent acts on then represent it language, (2) shortcoming stability generalization classifier trained single, monolithic network. To address these limitations, we propose MoE-VRD, novel approach relationship detection via mixture experts. MoE-VRD recognizes triplets form < subject,predicate,object > tuple extract between subject, predicate, processing. Since detecting subject (acting) object(s) (being acted upon) requires that action be recognized, base our network recent work detection. limitations associated with single networks, experts is based multiple small models, whose outputs are aggregated. That is, each expert learner capable tagging objects. employs an ensemble while preserving complexity cost original underlying model applying sparsely-gated experts, allows for conditional computation significant gain capacity. We show capabilities massive ability scale mixture-of-experts leads problem outperforms state-of-the-art.
منابع مشابه
Mixture of Experts Classication Using a Hierarchical Mixture Model
A three-level hierarchical mixture model for classication is presented that models the following data generation process: (1) the data are generated by a nite number of sources (clusters), and (2) the generation mechanism of each source assumes the existence of individual internal class-labeled sources (subclusters of the external cluster). The model estimates the posterior probability of cla...
متن کاملMotion Compensated Video Shot Detection using Multiple Feature Experts
In this fast developing technical era of digital technology, there is an explosion of video data especially on the internet. Organizing video and locating required information effectively and accurately presents a great challenge to the researchers. This demands a tool which would break down the video into smaller and manageable units called shots. A wide range of approaches have been investiga...
متن کاملMixture of Experts Classification Using a Hierarchical Mixture Model
A three-level hierarchical mixture model for classification is presented that models the following data generation process: (1) the data are generated by a finite number of sources (clusters), and (2) the generation mechanism of each source assumes the existence of individual internal class-labeled sources (subclusters of the external cluster). The model estimates the posterior probability of c...
متن کاملMixture of Vector Experts
We describe and analyze an algorithm for predicting a sequence of n-dimensional binary vectors based on a set of experts making vector predictions in [0, 1]. We measure the loss of individual predictions by the 2-norm between the actual outcome vector and the prediction. The loss of an expert is then the sum of the losses experienced on individual trials. We obtain bounds for the loss of our ex...
متن کاملModeling Wisdom of Crowds Using Latent Mixture of Discriminative Experts
In many computational linguistic scenarios, training labels are subjectives making it necessary to acquire the opinions of multiple annotators/experts, which is referred to as ”wisdom of crowds”. In this paper, we propose a new approach for modeling wisdom of crowds based on the Latent Mixture of Discriminative Experts (LMDE) model that can automatically learn the prototypical patterns and hidd...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2023
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2023.3257280