Imagen de Portada

Adept: Annotation-Denoising Auxiliary Tasks with Discrete Cosine Transform Map and Keypoint for Human-Centric Pretraining

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Weizhen, Yan, Yunfeng, Tang, Shixiang, Deng, Yiheng, Zhong, Yangyang, Luo, Pengxin, Qi, Donglian
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
por: He, Weizhen, et al.
Publicado: (2023)

Instruct-ReID++: Towards Universal Purpose Instruction-Guided Person Re-identification
por: He, Weizhen, et al.
Publicado: (2024)

TextVidBench: A Benchmark for Long Video Scene Text Understanding
por: Zhong, Yangyang, et al.
Publicado: (2025)

Hulk: A Universal Knowledge Translator for Human-Centric Tasks
por: Wang, Yizhou, et al.
Publicado: (2023)

Enhancing Recommendation with Denoising Auxiliary Task
por: Liu, Pengsheng, et al.
Publicado: (2024)

Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers
por: Pan, Hongyi, et al.
Publicado: (2024)

Efficient Neural Networks with Discrete Cosine Transform Activations
por: Martinez-Gost, Marc, et al.
Publicado: (2025)

TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
por: Li, Ao, et al.
Publicado: (2026)

Adaptive function approximation based on the Discrete Cosine Transform (DCT)
por: Pérez-Neira, Ana I., et al.
Publicado: (2023)

Combining Discrete Wavelet and Cosine Transforms for Efficient Sentence Embedding
por: Salama, Rana, et al.
Publicado: (2025)

On Securing Berrut Approximated Coded Computing Through Discrete Cosine Transforms
por: Borah, Rimpi, et al.
Publicado: (2025)

Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform
por: Huang, Chenyu, et al.
Publicado: (2025)

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
por: Zhong, Yangyang, et al.
Publicado: (2026)

Human-Centric Foundation Models: Perception, Generation and Agentic Modeling
por: Tang, Shixiang, et al.
Publicado: (2025)

Unsupervised Keypoints from Pretrained Diffusion Models
por: Hedlin, Eric, et al.
Publicado: (2023)

The Fourier Cosine Method for Discrete Probability Distributions
por: Shen, Xiaoyu, et al.
Publicado: (2024)

Cosine Annealing Optimized Denoising Diffusion Error Correction Codes
por: Ou, Congyang, et al.
Publicado: (2024)

Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models
por: Wang, Xuanhan, et al.
Publicado: (2025)

DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms
por: Zhouzhi, Xiong, et al.
Publicado: (2026)

Annotator-Centric Active Learning for Subjective NLP Tasks
por: van der Meer, Michiel, et al.
Publicado: (2024)

Maps for Autonomous Driving: Full-process Survey and Frontiers
por: Chen, Pengxin, et al.
Publicado: (2025)

Exudates and Blood Vessel Segmentation in Eye Fundus Images Using the Fourier and Cosine Discrete Transforms
por: Luis David Lara Rodríguez
Publicado: (2016)

P‐5.6: A Coverless Image Steganography Technique Based on Discrete Cosine Transform
por: Xiaoxuan Zhang, et al.
Publicado: (2025)

Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance
por: Luong, Diep, et al.
Publicado: (2025)

A Partial Characterization of Cosine Thurston Maps
por: D'Souza, Schinella
Publicado: (2025)

Training Transformers in Cosine Coefficient Space
por: Bergach, Mohamed Amine
Publicado: (2026)

Cottention: Linear Transformers With Cosine Attention
por: Mongaras, Gabriel, et al.
Publicado: (2024)

Towards Human-AI Accessibility Mapping in India: VLM-Guided Annotations and POI-Centric Analysis in Chandigarh
por: Lalwani, Varchita, et al.
Publicado: (2026)

DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
por: Wang, Kun, et al.
Publicado: (2024)

A Vision-Centric Approach for Static Map Element Annotation
por: Zhang, Jiaxin, et al.
Publicado: (2023)

Denoising Vision Transformers
por: Yang, Jiawei, et al.
Publicado: (2024)

Pretrained Mobility Transformer: A Foundation Model for Human Mobility
por: Wu, Xinhua, et al.
Publicado: (2024)

Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP
por: Zhong, Jinzuomu, et al.
Publicado: (2023)

Edge-Fog Computing-Enabled EEG Data Compression via Asymmetrical Variational Discrete Cosine Transform Network
por: Zhu, Xin, et al.
Publicado: (2025)

Relation-Aware LNN-Transformer for Intersection-Centric Next-Step Prediction
por: Ren, Zhehong, et al.
Publicado: (2025)

Smooth SCAD: A Raised Cosine SCAD Type Thresholding Rule for Wavelet Denoising
por: Kulkarni, Radhika, et al.
Publicado: (2026)

The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
por: Zhang, Leo, et al.
Publicado: (2025)

CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints
por: Deng, Yuhong, et al.
Publicado: (2025)

Ankh3: Multi-Task Pretraining with Sequence Denoising and Completion Enhances Protein Representations
por: Alsamkary, Hazem, et al.
Publicado: (2025)

Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor
por: Saini, Saurabh, et al.
Publicado: (2025)