Search Results for author:
Found 23 papers, 7 papers with code
Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Masking
Human pose estimation is a fundamental and challenging task in computer vision.
Coordinated Sparse Recovery of Label Noise
Based on CSR, this study designs a joint sample selection strategy and constructs a comprehensive and powerful learning framework called CSR+.
IterAlign: Iterative Constitutional Alignment of Large Language Models
Such a constitution discovery pipeline can be run iteratively and automatically to discover new constitutions that specifically target the alignment gaps in the current LLM.
Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration.
Language Models As Semantic Indexers
Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs.
Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation.
Tucker Bilinear Attention Network for Multi-scale Remote Sensing Object Detection
However, for small targets, there still be seriously missed detections due to the loss of key detail features.
Recent Progress in Conversational AI
Conversational artificial intelligence (AI) is becoming an increasingly popular topic among industry and academia.
Agreement or Disagreement in Noise-tolerant Mutual Learning?
The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information between dual-network.
Contrastive-mixup learning for improved speaker verification
In this work, we propose contrastive-mixup, a novel augmentation strategy that learns distinguishing representations based on a distance metric.
Self-supervised Speaker Recognition Training Using Human-Machine Dialogues
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication.
Swin Transformer coupling CNNs Makes Strong Contextual Encoders for VHR Image Road Extraction
While CNN excels at extracting local detail features, the Transformer naturally perceives global contextual information.
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction
With the development of deep learning, medical image classification has been significantly improved.
Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition
Based on whether the speech content is constrained or not, both text-dependent (TD) and text-independent (TI) speaker recognition models may be used.
Fast Single-shot Ship Instance Segmentation Based on Polar Template Mask in Remote Sensing Images
Object detection and instance segmentation in remote sensing images is a fundamental and challenging task, due to the complexity of scenes and targets.
Automated Relational Meta-learning
In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones.
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR).
Connection Sensitive Attention U-NET for Accurate Retinal Vessel Segmentation
We develop a connection sensitive attention U-Net(CSAU) for accurate retinal vessel segmentation.
Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images
Robust semantic segmentation of VHR remote sensing images from UAV sensors is critical for earth observation, land use, land cover or mapping applications.
Feature Fusion through Multitask CNN for Large-scale Remote Sensing Image Segmentation
In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery.
TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
SeqFace: Make full use of sequence information for face recognition
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.
Ranked #1 on
Face Verification
on YouTube Faces DB
DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
Semantic segmentation is a fundamental research in remote sensing image processing.
