Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks76 from public data
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions5,324
The Pyramid Vision Transformer (PVT) is introduced, which overcomes the difficulties of porting Transformer to various dense prediction tasks and is validated through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation.
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks3,476
A large-scale vision-language foun-dation model (Intern VL), which scales up the vision foun-dation model to 6 billion parameters and progressively aligns it with the LLM, using web-scale image-text data from various sources is designed.
- Selective Kernel Networks3,132
Detailed analyses show that the neurons in SKNet can capture target objects with different scales, which verifies the capability of neurons for adaptively adjusting their receptive field sizes according to the input.
- PVT v2: Improved baselines with pyramid vision transformer2,673
This work improves the original Pyramid Vision Transformer (PVT v1) by adding three designs: a linear complexity attention layer, an overlapping patch embedding, and a convolutional feed-forward network to reduce the computational complexity of PVT v1 to linearity and provide significant improvements on fundamental vision tasks.
- 1,348
- InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions1,217
This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs, and reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large- scale parameters from massive datalike ViTs.
- 918
- PolarMask: Single Shot Instance Segmentation With Polar Representation641
This paper introduces an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods.
- Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers626
The proposed model, named Polyp-PVT, effectively suppresses noises in the features and significantly improves their expressive capabilities, and is more robust to various challenging situations than existing representative methods.
- BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers593
This work presents a new framework termed BEVFormer, which learns unified BEV representations from multi-modality data with spatiotemporal transformers to support multiple autonomous driving perception tasks, achieving outstanding results across these tasks.
- Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection450
This paper explores a completely novel and different perspective to perform LQE – based on the learned distributions of the four parameters of the bounding box – and develops a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LqE based on GFLV1, thus producing GFLv2.
- DetCo: Unsupervised Contrastive Learning for Object Detection379
Extensive experiments demonstrate that DetCo not only outperforms recent methods on a series of 2D and 3D instance-level detection tasks, but also competitive on image classification.
- DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving319
DriveMLM is introduced, an LLM-based AD framework that can perform close-loop autonomous driving in realistic simulators and can plug-and-play in existing AD systems such as Autopilot and Apollo for close-loop driving.
- 294
- Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection271
- Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications267
The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.
- Delving Into the Devils of Bird’s-Eye-View Perception: A Review, Evaluation and Recipe252
A full suite of practical guidebook to improve the performance of BEV perception tasks, including camera, LiDAR and fusion inputs is introduced, and the future research directions in this area are pointed out.
- Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers199
This work presents Panoptic SegFormer, a general framework for panoptic segmentation with transformers, which contains three innovative components: an efficient deeply-supervised mask decoder, a query decoupling strategy, and an improved postprocessing method.
- PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text177
An end-to-end text spotting framework, termed PAN++, which can efficiently detect and recognize text of arbitrary shapes in natural scenes, based on the kernel representation that reformulates a text line as a text kernel surrounded by peripheral pixels.
- FB-BEV: BEV Representation from Forward-Backward View Transformations171
This work proposes a novel forward-backward view transformation module that compensates for the deficiencies in both existing methods, allowing them to enhance each other to obtain higher quality BEV representations mutually.
- Differentiable Hierarchical Graph Grouping for Multi-person Pose Estimation147
This paper proposes a novel differentiable Hierarchical Graph Grouping (HGG) method, which takes human keypoint candidates as graph nodes and clusters keypoints in a multi-layer graph neural network model and improves the performance of bottom-up pose estimation methods.
- A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook142
This article introduces seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks, and delves into the potential future directions behind the emergence of reasoning abilities within foundation models.
- 140
- Mini-InternVL: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance139
This work introduces Mini-InternVL, a series of MLLMs with parameters ranging from 1 billion to 4 billion, which achieves 90% of the performance with only 5% of the parameters, which makes these models more accessible and applicable in various real-world scenarios.
- VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition109
A visual-linguistic long-tailed recognition framework that can not only learn visual representation from images but also learn corresponding linguistic representation from noisy class-level text descriptions collected from the Internet, and is close to the prevailing performance training on the full ImageNet.
- Segmenting Transparent Objects in the Wild with Transformer109
A novel Transformer-based segmentation pipeline termed Trans2Seg is proposed, which significantly outperforms all the CNN-based methods, showing the proposed algorithm's potential ability to solve transparent object segmentation.
- Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding100
Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models and fostering further advancements in multi-modal and discrete diffusion model research.
- 97
- PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond85
The proposed polar representation can provide a new perspective for designing algorithms to solve single-shot instance segmentation, and is fully convolutional and can be easily embedded into most off-the-shelf detection methods.
- Mixed Link Networks57
This work presents a highly efficient and modularized Mixed Link Network (MixNet) which is equipped with flexible inner link and outer link modules and demonstrates that MixNets can achieve superior efficiency in parameter over the state-of-the-art architectures on many competitive datasets like CIFAR-10/100, SVHN and ImageNet.
- Low-Light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion55
This work proposes a novel and robust low-light image enhancement method via CLIP-Fourier guided wavelet diffusion, abbreviated as CFWD, which outperforms existing state-of-the-art methods, achieving significant progress in image quality and noise suppression.
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces39
The Visual Embodied Brain (VeBrain), a unified framework for perception, reasoning, and control in real world, is presented and a novel robotic adapter is proposed to convert textual control signals from MLLMs to motion policies of real robots.
- Docopilot: Improving Multimodal Models for Document-Level Understanding38
This work presents a high-quality document-level dataset, Doc-750K, designed to support in-depth understanding of multimodal documents, and develops a native multimodal model, Docopilot, which can accurately handle document-level dependencies without relying on RAG.
- ZeroGUI: Automating Online GUI Learning at Zero Human Cost38
ZeroGUI is proposed, a scalable, online learning framework for automating GUI Agent training at Zero human cost that integrates VLM-based automatic task generation to produce diverse training goals from the current environment state, and two-stage online reinforcement learning to continuously interact with and learn from GUI environments.
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models31
This work extends each image into a "static" video and introduces a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames.
- Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization31
An extremely simple Ultra-Resolution Style Transfer framework, termed URST, to flexibly process arbitrary high-resolution images (e.g., 10000x10000 pixels) style transfer for the first time and surpasses existing SOTA methods on ultra-high resolution images benefiting from the effectiveness of the proposed stroke perceptual loss in enlarging the stroke size.
- 31
- AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting28
This work proposes a novel text spotter, named Ambiguity Eliminating Text Spotter (AE TextSpotter), which learns both visual and linguistic features to significantly reduce ambiguity in text detection, and is the first time to improve text detection by using a language model.
- 24
- Detection of SARS-CoV-2 using machine learning-enabled paper-assisted ratiometric fluorescent sensors based on target-induced magnetic DNAzyme19
The integration of intelligent artificial vision with the paper-assisted ratiometric fluorescent sensor presents a novel approach for the on-site detection of COVID-19 and holds potential for broader use in disease diagnostics in the future.
- 14
- One-Pot Rlock-Mediated CRISPR/Cas12a-Driven RCA Cycle for Rapid and High-Sensitive APE1 Detection13
A versatile Rlock-Lock (Rlock) conversion platform is introduced that enables the transformation of RCA-based nucleic acid detection technologies into APE1-responsive assays and develops a novel POCT method for APE1 detection that integrates CRISPR/Cas12a with RCA into a one-pot APE1 detection system.
- HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding11
This paper presents a novel high-performance monolithic VLM named HoVLE, which introduces a holistic embedding module that converts visual and textual inputs into a shared space, allowing LLMs to process images in the same way as texts.
- 10
- 9
- EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models7
EvoMoE introduces a meticulously designed expert initialization strategy that progressively evolves multiple robust experts from a single trainable expert, a process termed expert evolution that specifically targets severe expert homogenization.
- Ultra-fast one-pot isothermal detection of respiratory virus: ADNA-initiated CRISPR/Cas12a-mediated RCA cycle6
An ultra-rapid, one-pot isothermal assay called "ADNA-initiated CRISPR-Cas12a-mediated RCA cycle" (ACRE), which can detect targets with concentrations above 10 pM within 2.5 min, without the reverse transcription step or specialized instrumentation.
- 6
- 6
- VLG: General Video Recognition with Web Textual Knowledge5
A unified visual-linguistic framework (VLG) to solve the problem of GVR with an effective two-stage training paradigm is presented, and extensive results show that the VLG obtains the state-of-the-art performance under four settings.
- WegFormer: Transformers for Weakly Supervised Semantic Segmentation5
This work for the first time introduces Transformer to build a simple and effective WSSS framework, termed WegFormer, that achieves state-of-the-art results on the PASCAL VOC dataset, significantly outperforming the previous best method.
- Polygon-Free: Unconstrained Scene Text Detection with Box Annotations5
An unconstrained text detection system termed Polygon-free (PF), in which most existing polygon-based text detectors are trained with only upright bounding box annotations, to transfer knowledge from synthetic data to real data to enhance the supervision information of upright bounded boxes.
- 4
- SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training.4
A novel text detection system termed SelfText Beyond Polygon (SBP) with Bounding Box Supervision (BBS) and Dynamic Self Training (DST), where training a polygon-based text detector with only a limited set of upright bounding box annotations is proposed.
- Androfim: few-shot android malware family detection based on image representation3
A novel few-shot learning approach based on the image representation of an Android application which utilizes self-supervised learning to obtain the pre-trained backbone from the unlabeled auxiliary data and employs a metric-based few-shot learning method for Android malware classification.
- A survey of historical learning: learning models with learning history3
This survey is the first survey that systematically studies the methodologies which make use of various historical statistics when training deep neural networks and encourages the community to pay attention to the think of historical learning principles when designing algorithms.
- 3
- 2
- 2
- Optimizing 4D Lookup Table for Low-light Video Enhancement via Wavelet Priori2
Wavelet-priori for 4D Lookup Table (WaveLUT) is proposed, which effectively enhances the color coherence between video frames and the accuracy of color mapping while maintaining low latency and achieves metric-favorable and perceptually oriented real-time enhancement while maintaining high efficiency.
- 2
- 1
- –
- –
- When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI–
CamHarmTI is introduced, a benchmark for evaluating LVLM ability to perceive and interpret camouflaged harmful content within text-image compositions and fine-tuning experiments demonstrate thatbench serves as an effective resource for improving model perception, promoting a more integrated scene understanding.
- –
- –
- –
- –
- –
- Guided Refine-Head for Object Detection–
Abundant ablation studies and comparative experiments on MS-COCO 2017 validate the superiority of the proposed Guided Refin-Head, which is made up of a newly proposed detection network called Refine-Head and a knowledge-distillation-like loss function.
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. 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.