Search Results for author:
Found 17 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.
CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
To this end, we study low-resource generative conversational query rewrite that is robust to both noise and language style shift.
AACP: Aesthetics assessment of children's paintings based on self-supervised learning
To solve this problem, we construct an aesthetics assessment dataset of children's paintings and a model based on self-supervised learning.
DreaMoving: A Human Video Generation Framework based on Diffusion Models
In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos.
An APT Event Extraction Method Based on BERT-BiGRU-CRF for APT Attack Detection
To enhance the understanding of APT attacks, in this paper, a novel approach for extracting APT attack events from web texts is proposed.
DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets
However, due to the sparse characteristics of point clouds, it is non-trivial to apply a standard transformer on sparse points.
Ranked #1 on
3D Object Detection
on nuScenes LiDAR only
McQueen: a Benchmark for Multimodal Conversational Query Rewrite
In this paper, we propose the task of multimodal conversational query rewrite (McQR), which performs query rewrite under the multimodal visual conversation setting.
Boosting 3D Object Detection via Object-Focused Image Fusion
Given a set of point features and image feature maps, DeMF adaptively aggregates image features by taking the projected 2D location of the 3D point as reference.
Ranked #5 on
3D Object Detection
on SUN-RGBD val
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP).
NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains.
BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling
However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the development of robust end-to-end ToD systems for multilingual countries and regions.
Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation
Representation of semantic context and local details is the essential issue for building modern semantic segmentation models.
Fast and Accurate Scene Parsing via Bi-direction Alignment Networks
Motivated by this, we propose a novel network by aligning two-path information into each other through a learned flow field.
Alfvénic versus non-Alfvénic turbulence in the inner heliosphere as observed by Parker Solar Probe
We make use of the Parker Solar Probe (PSP) data to explore the nature of solar wind turbulence focusing on the Alfv\'enic character and power spectra of the fluctuations and their dependence on distance and context (i. e. large scale solar wind properties), aiming to understand the role that different effects such as source properties, solar wind expansion, stream interaction might play in determining the turbulent state.
Solar and Stellar Astrophysics Space Physics
Deep RNN Framework for Visual Sequential Applications
There are mainly two novel designs in our deep RNN framework: one is a new RNN module called Context Bridge Module (CBM) which splits the information flowing along the sequence (temporal direction) and along depth (spatial representation direction), making it easier to train when building deep by balancing these two directions; the other is the Overlap Coherence Training Scheme that reduces the training complexity for long visual sequential tasks on account of the limitation of computing resources.
Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning
The lack of labeled data is one of the main challenges when building a task-oriented dialogue system.
