Search Results for author:
Found 15 papers, 6 papers with code
When are Foundation Models Effective? Understanding the Suitability for Pixel-Level Classification Using Multispectral Imagery
This work aims to enhance the understanding of the status and suitability of foundation models for pixel-level classification using multispectral imagery at moderate resolution, through comparisons with traditional machine learning (ML) and regular-size deep learning models.
Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration
We believe our work could provide a novel perspective to consider the uncertainty quality for the general motion prediction task and encourage the studies in this field.
SimFair: Physics-Guided Fairness-Aware Learning with Simulation Models
Fairness-awareness has emerged as an essential building block for the responsible use of artificial intelligence in real applications.
The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Pooling
In addition, our method reduces more than 60% memory costs of the subsequent pixel-level CD processing stage.
A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Specifically, in addition to a text encoder encoding the input text, our model is equipped with a table header generator to first output a table header, i. e., the first row of the table, in the manner of sequence generation.
Revisiting Non-Autoregressive Translation at Scale
Experimental results on the large-scale WMT20 En-De show that the asymmetric architecture (e. g. bigger encoder and smaller decoder) can achieve comparable performance with the scaling model, while maintaining the superiority of decoding speed with standard NAT models.
Learning to Detect Noisy Labels Using Model-Based Features
Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation.
TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts
In TCNL, the shallow feature extractor gets preliminary features first.
Temporal Saliency Query Network for Efficient Video Recognition
For each category, the common pattern of it is employed as a query and the most salient frames are responded to it.
Ranked #5 on
Action Recognition
on ActivityNet
A fully differentiable ligand pose optimization framework guided by deep learning and traditional scoring functions
In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF.
Utterance Rewriting with Contrastive Learning in Multi-turn Dialogue
Context modeling plays a significant role in building multi-turn dialogue systems.
Multi-Attention Generative Adversarial Network for Remote Sensing Image Super-Resolution
The main body of the generator contains two blocks; one is the pyramidal convolution in the residual-dense block (PCRDB), and the other is the attention-based upsample (AUP) block.
Robust End-to-End Offline Chinese Handwriting Text Page Spotter with Text Kernel
Offline Chinese handwriting text recognition is a long-standing research topic in the field of pattern recognition.
Adaptive Task Sampling for Meta-Learning
Meta-learning methods have been extensively studied and applied in computer vision, especially for few-shot classification tasks.
Deep Learning for Image Super-resolution: A Survey
Image Super-Resolution (SR) is an important class of image processing techniques to enhance the resolution of images and videos in computer vision.
