Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks74 from public data
- Deep High-Resolution Representation Learning for Human Pose Estimation5,649
This paper proposes a network that maintains high-resolution representations through the whole process of human pose estimation and empirically demonstrates the effectiveness of the network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.
- Deep High-Resolution Representation Learning for Visual Recognition5,145
The superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, is shown, suggesting that the HRNet is a stronger backbone for computer vision problems.
- CvT: Introducing Convolutions to Vision Transformers2,569
A new architecture is presented that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both de-signs, and the positional encoding, a crucial component in existing Vision Transformers, can be safely re-moved in this model.
- Simple Baselines for Human Pose Estimation and Tracking2,149
This work provides simple and effective baseline methods for pose estimation that are helpful for inspiring and evaluating new ideas for the field and achieved on challenging benchmarks.
- Dynamic Head: Unifying Object Detection Heads with Attentions1,044
This paper presents a novel dynamic head framework to unify object detection heads with attentions by coherently combining multiple self-attention mechanisms between feature levels for scale- awareness, among spatial locations for spatial-awareness, and within output channels for task-awareness that significantly improves the representation ability of object detection Heads without any computational overhead.
- Integral Human Pose Regression963
This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues and is differentiable, efficient, and compatible with any heat map based methods.
- HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation954
HigherHRNet is presented, a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids that surpasses all top-down methods on CrowdPose test and achieves new state-of-the-art result on COCO test-dev, suggesting its robustness in crowded scene.
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks657
Florence-2, a novel vision foundation model with a unified, prompt-based representation for various computer vision and vision-language tasks, is introduced and demonstrated to be a strong vision foundation model contender with un-precedented zero-shot and fine-tuning capabilities.
- 614
- Lite-HRNet: A Lightweight High-Resolution Network507
An efficient high-resolution network, Lite-HRNet, is presented, which demonstrates superior results on human pose estimation over popular lightweight networks and can be easily applied to semantic segmentation task in the same lightweight manner.
- 428
- Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding405
A comprehensive empirical study shows that the new ViT significantly outperforms several strong baselines, including the existing ViT models and their ResNet counterparts, and the Pyramid Vision Transformer from a concurrent work, on a range of vision tasks, including image classification, object detection, and segmentation.
- Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression401
It is empirically show that the proposed direct regression method outperforms keypoint detection and grouping methods and achieves superior bottom-up pose estimation results on two benchmark datasets, COCO and CrowdPose.
- 382
- 326
- 309
- Unified Contrastive Learning in Image-Text-Label Space301
This work intro-duce a new formulation of Unified Con-trastive Learning (UniCL) with a single learning objective to seamlessly prompt the synergy of two data types, universally for image recognition in zero-shot, linear-probing, fully finetuning and transfer learning sce-narios.
- 256
- MiniViT: Compressing Vision Transformers with Weight Multiplexing186
MiniViT, a new compression framework, which achieves parameter reduction in vision transformers while retaining the same performance, and makes the weights shared across layers, while imposing a transformation on the weights to increase diversity.
- 82
- 74
- 73
- Mariana56
Mariana, the Tencent deep learning platform, which utilizes GPU and CPU cluster to train models parallelly with three frameworks, achieves state-of-the-art acceleration performance, and plays a key role in training models and improving quality for automatic speech recognition and image recognition in Tencent WeChat, a mobile social platform.
- 51
- Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation41
Higher-Resolution Network (HigherHRNet) is proposed, which is a simple extension of the High-Res resolution Network (HRNet), which generates higher-resolution feature maps by deconvolving the high- resolution feature maps outputted by HRNet, which are spatially more accurate for small and medium persons.
- Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion30
Florence-VL is presented, a new family of multimodal large language models (MLLMs) with enriched visual representations produced by Florence-2, a generative vision foundation model, with significant improvements over existing state-of-the-art MLLMs across various multi-modal and vision-centric benchmarks.
- 27
- 3D Human Pose Estimation via Explicit Compositional Depth Maps25
This work proposes to use densely-generated limb depth maps to ease the learning of body joints depth, and designs a lifting module from 2D pixel coordinates to 3D camera coordinates which explicitly takes the depth values as inputs, and is aligned with camera perspective projection model.
- Anatomical Prior Guided Spatial Contrastive Learning for Few-Shot Medical Image Segmentation19
An anatomical prior guided spatial contrastive learning, called APSCL, is proposed, which exploits anatomical prior knowledge derived from medical images to construct contrastive learning from a spatial perspective for few-shot medical image segmentation.
- 17
- 16
- 15
- TableStrRec: framework for table structure recognition in data sheet images13
It is shown that utilizing TableStrRec to detect four classes of objects improves the table structure recognition performance on three public test sets, and the proposed method under the FinTabNet dataset using the structure-only TEDS score, achieving 98.34%, can outperform most state-of-the-art benchmark models.
- HyCTAS: Multi-objective hybrid convolution-transformer architecture search for real-time image segmentation12
A series of models via the Hybrid Convolutional-Transformer Architecture Search (HyCTAS) method that searches for the best hybrid combination of lightweight convolution layers and memory-efficient self-attention layers between branches from different resolutions and fuses them at high resolution for both efficiency and effectiveness are presented.
- 12
- 8
- 8
- Insulation property of wire-plane gap under fire condition: Effects of vegetation flame conductivity8
- 8
- Semi-Supervised FMCW Radar Hand Gesture Recognition via Pseudo-Label Consistency Learning7
This work proposes a semi-supervised learning framework guided by pseudo-label consistency, which utilizes a dual-branch structure with a mean-teacher network to alleviate accuracy degradation resulting from individual differences and interference from other body parts, thereby bolstering the network’s robustness.
- 7
- 6
- 6
- 6
- 4
- 4
- 3
- 3
- 3
- 3
- Focus Stacking with High Fidelity and Superior Visual Effects2
The results show that the proposed method can generate high-quality all-in-focus images by achieving two goals simultaneously, especially can successfully solve the TR problem and eliminate the visual effect degradation of synthesized images caused by the TR problem.
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- PriFU: Capturing Task-Relevant Information Without Adversarial Learning1
A method for privacy preservation in the inference phase by removing task-irrelevant information, which requires no knowledge of the privacy attacks nor introduction of adversarial learning, and introduces a metric to distinguish task-irrelevant information from task-relevant information.
- 1
- 1
- Primal-Dual Group Convolutions for Deep Neural Networks1
This paper presents a simple and modularized neural network architecture, named primal-dual group convolutional neural networks (PDGCNets), and demonstrates that these networks are more efficient in using parameters and computation complexity with similar or higher accuracy.
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.