Search Results for author:
Found 11 papers, 4 papers with code
ARS-DETR: Aspect Ratio Sensitive Oriented Object Detection with Transformer
Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model.
Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations
To this end, we introduce the multimodal information bottleneck (MIB), aiming to learn a powerful and sufficient multimodal representation that is free of redundancy and to filter out noisy information in unimodal representations.
Multimodal Emotion Recognition
Multimodal Sentiment Analysis
Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis
On the other hand, noisy information hidden in each modality interferes the learning of correct cross-modal dynamics.
Hybrid Contrastive Learning of Tri-Modal Representation for Multimodal Sentiment Analysis
Specifically, we simultaneously perform intra-/inter-modal contrastive learning and semi-contrastive learning (that is why we call it hybrid contrastive learning), with which the model can fully explore cross-modal interactions, preserve inter-class relationships and reduce the modality gap.
Efficient Peer Effects Estimators with Group Effects
We show that these moment conditions can be cast in terms of a linear random group effects model and lead to a class of GMM estimators that are generally identified as long as there is sufficient variation in group size.
Taxonomy Completion via Triplet Matching Network
Previous approaches focus on the taxonomy expansion, i. e. finding an appropriate hypernym concept from the taxonomy for a new query concept.
Analyzing Unaligned Multimodal Sequence via Graph Convolution and Graph Pooling Fusion
A majority of existing works generally focus on aligned fusion, mostly at word level, of the three modalities to accomplish this task, which is impractical in real-world scenarios.
Xiaomingbot: A Multilingual Robot News Reporter
This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four integral capabilities: news generation, news translation, news reading and avatar animation.
Importance-Aware Learning for Neural Headline Editing
We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers.
Constraint-free Natural Image Reconstruction from fMRI Signals Based on Convolutional Neural Network
Without semantic prior information, we present a novel method to reconstruct nature images from fMRI signals of human visual cortex based on the computation model of convolutional neural network (CNN).
Scale Up Event Extraction Learning via Automatic Training Data Generation
We show that this large volume of training data not only leads to a better event extractor, but also allows us to detect multiple typed events.
