Search Results for author:
Found 10 papers, 8 papers with code
AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework
The task of financial analysis primarily encompasses two key areas: stock trend prediction and the corresponding financial question answering.
Imbalance-Agnostic Source-Free Domain Adaptation via Avatar Prototype Alignment
To address this issue, we study a more practical SF-UDA task, termed imbalance-agnostic SF-UDA, where the class distributions of both the unseen source domain and unlabeled target domain are unknown and could be arbitrarily skewed.
Disentangling Writer and Character Styles for Handwriting Generation
In light of this, we propose to disentangle the style representations at both writer and character levels from individual handwritings to synthesize realistic stylized online handwritten characters.
Beyond Fixation: Dynamic Window Visual Transformer
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window.
Co-attention network with label embedding for text classification
To alleviate this issue, label embedding frameworks are proposed to adopt the label-to-text attention that directly uses label information to construct the text representation for more efficient text classification.
Ranked #2 on
Multi-Label Text Classification
on AAPD
(Micro F1 metric)
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
(2) prototype adaptation: based on the generated source prototypes and target pseudo labels, we develop a new robust contrastive prototype adaptation strategy to align each pseudo-labeled target data to the corresponding source prototypes.
Ranked #12 on
Domain Adaptation
on VisDA2017
Towards Accurate Text-based Image Captioning with Content Diversity Exploration
This task, however, is very challenging because an image often contains complex texts and visual information that is hard to be described comprehensively.
Location-aware Graph Convolutional Networks for Video Question Answering
In this work, we propose to represent the contents in the video as a location-aware graph by incorporating the location information of an object into the graph construction.
Joint Wasserstein Distribution Matching
However, the resultant optimization problem is still intractable.
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs
As a result, the representation power of intermediate layers can be very weak and the model becomes very redundant with limited performance.
