AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding

Abstract

Significant progress has been achieved in Computer Vision by leveraging large-scale image datasets. However, large-scale datasets for complex Computer Vision tasks beyond classification are still limited. This paper proposed a large-scale dataset named AIC (AI Challenger) with three sub-datasets, human keypoint detection (HKD), large-scale attribute dataset (LAD) and image Chinese captioning (ICC). In this dataset, we annotate class labels (LAD), keypoint coordinate (HKD), bounding box (HKD and LAD), attribute (LAD) and caption (ICC). These rich annotations bridge the semantic gap between low-level images and high-level concepts. The proposed dataset is an effective benchmark to evaluate and improve different computational methods. In addition, for related tasks, others can also use our dataset as a new resource to pre-train their models.

References in corpus (19)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Microsoft COCO Captions: Data Collection and Evaluation Server
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Evaluation of Output Embeddings for Fine-Grained Image Classification
• Human pose estimation via Convolutional Part Heatmap Regression
• Stacked Hourglass Networks for Human Pose Estimation
• Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
• Convolutional Pose Machines
• Image Captioning with Semantic Attention
• Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
• Language Models for Image Captioning: The Quirks and What Works
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward
• Recent Advances in Zero-shot Recognition
• Boosting Image Captioning with Attributes
• Zero-Shot Learning posed as a Missing Data Problem
• Multi-Person Pose Estimation with Local Joint-to-Person Associations

Cited by in corpus (34)

• Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
• Deep High-Resolution Representation Learning for Visual Recognition
• Deep Learning-Based Human Pose Estimation: A Survey
• WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training
• WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose
• Deep High-Resolution Representation Learning for Human Pose Estimation
• Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
• ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
• CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
• Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese
• When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration
• Towards Zero-shot Cross-lingual Image Retrieval
• Pose-Guided Multi-Granularity Attention Network for Text-Based Person Search
• COCO-CN for Cross-Lingual Image Tagging, Captioning and Retrieval
• A Review on Human Pose Estimation
• Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representation
• AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
• Double Anchor R-CNN for Human Detection in a Crowd
• Unpaired Image Captioning by Language Pivoting
• Monocular, One-stage, Regression of Multiple 3D People
• Hulk: A Universal Knowledge Translator for Human-Centric Tasks
• EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
• TAN: Temporal Affine Network for Real-Time Left Ventricle Anatomical Structure Analysis Based on 2D Ultrasound Videos
• Generalizing Monocular 3D Human Pose Estimation in the Wild
• Unpaired Cross-lingual Image Caption Generation with Self-Supervised Rewards
• Towards Zero-shot Cross-lingual Image Retrieval and Tagging
• Whole-Body Human Pose Estimation in the Wild
• ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation
• Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation
• Synthetic Training for Monocular Human Mesh Recovery
• Detector-in-Detector: Multi-Level Analysis for Human-Parts
• TransAug: Translate as Augmentation for Sentence Embeddings
• Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
• Coherent Loss: A Generic Framework for Stable Video Segmentation