Search Results for author:
Found 27 papers, 7 papers with code
Noise Learning for Text Classification: A Benchmark
However, we find that noise learning in text classification is relatively underdeveloped: 1. many methods that have been proven effective in the image domain are not explored in text classification, 2. it is difficult to conduct a fair comparison between previous studies as they do experiments in different noise settings.
One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
Advanced image fusion methods mostly prioritise high-level missions, where task interaction struggles with semantic gaps, requiring complex bridging mechanisms.
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition
Drawing inspiration from this cognitive process, we propose a novel trunk-branch contrastive network (TBCNet) for RGB-based multi-view action recognition.
Subpixel Edge Localization Based on Converted Intensity Summation under Stable Edge Region
We take an innovative perspective by assuming that the intensity at the pixel level can be interpreted as a local integral mapping in the intensity model for subpixel localization.
MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention
By aligning brushstroke styles with the texture and contours of colored images, particularly in late decoder layers handling local textures, MixSA addresses the common issue of color averaging by adjusting initial outlines.
Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections
The shared topology of human skeletons motivated the recent investigation of graph convolutional network (GCN) solutions for action recognition.
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models
As large language models become increasingly prevalent in the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance.
Capture Artifacts via Progressive Disentangling and Purifying Blended Identities for Deepfake Detection
To address these issues, a Deepfake detection method based on progressive disentangling and purifying blended identities is innovatively proposed in this paper.
QuadBEV: An Efficient Quadruple-Task Perception Framework via Bird's-Eye-View Representation
Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstream tasks.
Learning Content-Aware Multi-Modal Joint Input Pruning via Bird's-Eye-View Representation
In the landscape of autonomous driving, Bird's-Eye-View (BEV) representation has recently garnered substantial academic attention, serving as a transformative framework for the fusion of multi-modal sensor inputs.
RMLR: Extending Multinomial Logistic Regression into General Geometries
Specifically, we showcase our framework on the Symmetric Positive Definite (SPD) manifold and special orthogonal group, i. e., the set of rotation matrices.
Dynamic Subframe Splitting and Spatio-Temporal Motion Entangled Sparse Attention for RGB-E Tracking
Based on this, we design an event-based sparse attention mechanism to enhance the interaction of event features in temporal and spatial dimensions.
CoMoFusion: Fast and High-quality Fusion of Infrared and Visible Image with Consistency Model
Generative models are widely utilized to model the distribution of fused images in the field of infrared and visible image fusion.
S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusion
However, in image fusion, current methods underestimate the potential of SSSM in capturing the global spatial information of both modalities.
Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support
Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support.
BusReF: Infrared-Visible images registration and fusion focus on reconstructible area using one set of features
We focus on Infrared-Visible image registration and fusion task (IVRF).
iDesigner: A High-Resolution and Complex-Prompt Following Text-to-Image Diffusion Model for Interior Design
However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution.
Towards Efficient 3D Object Detection in Bird's-Eye-View Space for Autonomous Driving: A Convolutional-Only Approach
3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving.
Ziya2: Data-centric Learning is All LLMs Need
Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings.
Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs.
Edge Based Oriented Object Detection
In the field of remote sensing, we often utilize oriented bounding boxes (OBB) to bound the objects.
Riemannian Multinomial Logistics Regression for SPD Neural Networks
Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks.
LabelPrompt: Effective Prompt-based Learning for Relation Classification
Specifically, associating natural language words that fill the masked token with semantic relation labels (\textit{e. g.} \textit{``org:founded\_by}'') is difficult.
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning
We design Semantic Attention (SA) and generative Knowledge Disentanglement (KD) to learn the dependence of feasibility and contextuality, respectively.
Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence
We hope that this project will be the foundation of Chinese cognitive intelligence.
PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion
In this paper, we propose a Patch Pyramid Transformer(PPT) to effectively address the above issues. Specifically, we first design a Patch Transformer to transform the image into a sequence of patches, where transformer encoding is performed for each patch to extract local representations.
a high efficiency fully convolutional networks for pixel wise surface defect detection
Our method is composed of a segmentation stage (stage 1), a detection stage (stage 2), and a matting stage (stage 3).
