Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks73 from public data
- CCNet: Criss-Cross Attention for Semantic Segmentation3,111
For each pixel, a novel criss-cross attention module in CCNet harvests the contextual information of all the pixels on its criss-cross path by taking a further recurrent operation, each pixel can finally capture the full-image dependencies from all pixels.
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data2,221
This work designs a data engine to collect and automatically annotate large-scale unlabeled data and develops an auxiliary supervision to enforce the model to inherit rich semantic priors from pre-trained encoders, which results in a better depth-conditioned ControlNet.
- Executing your Commands via Motion Diffusion in Latent Space766
The proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages.
- 595
- TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation338
Experimental results demonstrate that the proposed TopFormer method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency.
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos277
Video Depth Anything is proposed for high-quality, consistent depth estimation in super-long videos (over several minutes) without sacrificing efficiency, and sets a new state-of-the-art in zero-shot video depth estimation.
- Devil in the Details: Towards Accurate Single and Multiple Human Parsing268
This paper identifies several useful properties, including feature resolution, global context information and edge details, and performs rigorous analyses to reveal how to leverage them to benefit the human parsing task, resulting in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing.
- Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis237
This work presents Agriculture-Vision: a large-scale aerial farmland image dataset for semantic segmentation of agricultural patterns, and proposes an effective model designed for aerial agricultural pattern recognition.
- AlignSeg: Feature-Aligned Segmentation Networks199
This paper proposes Feature-Aligned Segmentation Networks (AlignSeg), a feature aggregation network that adopts a simple learnable interpolation strategy to learn transformation offsets of pixels that can effectively relieve the feature misalignment issue caused by multi-resolution feature aggregation.
- Sa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos168
Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications.
- BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs137
BozoGPT is a multi-modal LLM with visual grounding that can perform cross-modAL interaction between vision, audio and language, providing fine-grained understanding of visual objects and other given modalities and performs consistently well when provided by arbitrary modalities.
- SPGNet: Semantic Prediction Guidance for Scene Parsing134
By carefully re-weighting features across stages, a two-stage encoder-decoder network coupled with the proposed Semantic Prediction Guidance (SPG) module can significantly outperform its one-stage counterpart with similar parameters and computations.
- SeaFormer++: Squeeze-Enhanced Axial Transformer for Mobile Visual Recognition132
A new method squeeze-enhanced Axial Transformer (SeaFormer) for mobile visual recognition, designed a generic attention block characterized by the formulation of squeeze Axial and detail enhancement, which can be further used to create a family of backbone architectures with superior cost-effectiveness.
- SeMask: Semantically Masked Transformers for Semantic Segmentation132
This paper argues that incorporating semantic information of the image into pretrained hierarchical transformer-based backbones while finetuning improves the performance considerably and proposes SeMask, a simple and effective framework that incorporates semantic information into the encoder with the help of a semantic attention operation.
- Deep learning-based automated image segmentation for concrete petrographic analysis120
The experimental results showed that CNN outperforms the color-based segmentation by a considerable margin, and has comparable accuracy to human experts, and the segmentation time is reduced to mere seconds.
- 119
- 99
- GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation78
A classification-model-based approach is proposed to investigate the underlying architecture of GPT-4o, where empirical results suggest the model consists of an auto-regressive (AR) combined with a diffusion-based head for image decoding, rather than the VAR-like architectures.
- Deep patch learning for weakly supervised object classification and discovery76
The results show that the proposed weakly supervised patch features via weak supervisions method can obtain state-of-the-art performance on object classification, and very competitive results on object discovery, with faster testing speed than competitors.
- High-Resolution Deep Image Matting64
The proposed HDMatt approach runs matting in a patch-based crop-and-stitch manner for high-resolution inputs with a novel module design to address the contextual dependency and consistency issues between different patches.
- LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models58
This work introduces LOKI, a novel benchmark designed to evaluate the ability of LMMs to detect synthetic data across multiple modalities, and evaluated 22 open-source LMMs and 6 closed-source models on it, highlighting their potential as synthetic data detectors and also revealing some limitations in the development of LMM capabilities.
- 52
- Human De-occlusion: Invisible Perception and Recovery for Humans48
A two-stage framework is proposed to estimate the invisible portions and recover the content inside of human deocclusion and a stacked network structure is devised to refine inaccurate masks from a general instance segmentation model and predict integrated masks simultaneously.
- Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report39
This paper introduces the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly realtime performance on smartphones and IoT platforms.
- The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer34
Sail is introduced, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture that eliminates the need for a separate vision encoder, presenting a more minimalist architecture design.
- 31
- The 1st Agriculture-Vision Challenge: Methods and Results27
The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with the challenge dataset.
- Harnessing Diffusion Models for Visual Perception with Meta Prompts23
This paper proposes a simple yet effective scheme to harness a diffusion model for visual perception tasks, and designs a recurrent refinement training strategy that fully leverages the property of diffusion models, thereby yielding stronger visual features.
- 22
- 20
- 19
- Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs18
This work introduces Grasp Any Region (GAR) for region-level visual understanding, and constructs GAR-Bench, which not only provides a more accurate evaluation of single-region comprehension, but also, more importantly, measures interactions and complex reasoning across multiple regions.
- Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration15
A novel layered 3D scene reconstruction framework from panoramic image, named Scene4U, which outperforms state-of-the-art method, improving by 24.24% in LPIPS and 24.40% in BRISQUE, while also achieving the fastest training speed.
- Dynamic text prompt joint multimodal features for accurate plant disease image captioning14
This study proposes BLIP-DP, a novel approach that dynamically generates prompts to enhance multimodal feature fusion for plant disease image captioning, and developed a model that incorporates a ViT, BERT, and a visual question-answering module.
- MM-NodeFormer: Node Transformer Multimodal Fusion for Emotion Recognition in Conversation13
A multimodal network called MM-NodeFormer for ERC is proposed, which leverages the characteristics of different Transformer encoding stages to fuse the emotional features from the text, audio, and visual modalities according to their emotional richness.
- 13
- 10
- 10
- 9
- 9
- Mesh Simplification Using Vertex Clustering Based on Principal Curvature9
This paper improves the defect of error accumulation which consisted in the previous algorithms, not only ensuring the display effect for the model, but also raising the efficiency of algorithm.
- 8
- 8
- 6
- Knowledge domain and trend of disease-modifying therapies for multiple sclerosis: A study based on CiteSpace5
Current research hotspots and trends in DMTs in multiple sclerosis focus on the effectiveness of different DMTs drugs in treating patients with MS and how to optimise treatment strategies.
- 4
- IDIR: Identifying and Distilling Informative Relations for Speaker Verification4
This work proposes dentifying and D istilling I dentifying and D istilling I nformative R elations (IDIR), enabling the student network to acquire speakers’ relationships from the teacher, demonstrating its merits and effectiveness.
- Disentangled Pre-training for Image Matting4
Extensive experimental evaluations show that the proposed approach outperforms both the state-of-the-art matting methods and other alternative self-supervised initialisation approaches by a large margin, and shows the robustness of the proposed approach over different backbone architectures.
- Lightweight Model Pre-Training via Language Guided Knowledge Distillation4
This paper introduces language guidance to the distillation process and proposes a new method named Language-Guided Distillation (LGD) system, which uses category names of the target downstream task to help refine the knowledge transferred between the teacher and student.
- 4
- 3
- 3
- 3
- 3
- 2
- Revisiting Evolutionary Program Repair via Code Language Model2
A novel approach, ARJA-CLM, is introduced, which integrates the multiobjective evolutionary algorithm with CLM to fix multilocation bugs in Java projects and proposes a context-aware prompt construction stratege, which enriches the prompt with additional information about accessible fields and methods for the CLM generating candidate statements.
- 2
- DL-propargylglycine reverses beta-lactam resistance in Streptococcus agalactiae1
DL-Propargylglycine (PAG), an inhibitor of cystathionine-γ-lyase inhibitor, exclusively synergizes with β-lactams to reverse resistance in ampicillin-resistant GBS and other streptococci, overcoming tolerance in persisters and biofilms.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- Targeted shortwave diathermy combined with perceptual training for patients with severe traumatic optic neuropathy–
This study provides the first evidence of visual function recovery occurring 73 days after complete vision loss in child with TON when combined rehabilitation was implemented, and demonstrated beneficial effects in patients with severe TON after EOND surgery.
- Fully Automated Segmentation of Brain and Scalp Blood Vessels on Multi-Parametric Magnetic Resonance Imaging Using Multi-view Cascaded Network–
A cascaded DL network (MVPC-Net) that combines three refinements: multi-view learning, multi-parameter input, and a multi-view ensemble module-based strategy can provide better segmentation of the brain, and scalp blood vessels and has potential for clinical application.
- Targeted shortwave diathermy with perceptual training for severe traumatic optic neuropathy patients–
- Wavelet Domain Double Fragile Watermarking Algorithm for Image Authentication–
Experimental results show that the wavelet domain double fragile watermarking algorithm not only resists well the vector quantization attack, but also has lower FAP and MAP, and does well in image authentication.
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.