Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks61 from public data
- Path Aggregation Network for Instance Segmentation9,321
Path Aggregation Network (PANet) is proposed aiming at boosting information flow in proposal-based instance segmentation framework by enhancing the entire feature hierarchy with accurate localization signals in lower layers by bottom-up path augmentation.
- MAT: Mask-Aware Transformer for Large Hole Image Inpainting539
A novel transformer-based model for large hole inpainting is presented, which unifies the merits of transformers and convolutions to efficiently process high-resolution images.
- 248
- Faster R-CNN for marine organisms detection and recognition using data augmentation194
Three data augmentation methods dedicated to underwater-imaging are proposed, the inverse process of underwater image restoration is used to simulate different marine turbulence environments, and perspective transformation and Illumination synthesis are proposed to simulateDifferent marine uneven illuminating environments.
- MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution185
This work proposes a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-cor correspondence aggregation scheme to explore self-similarity of images across scales.
- BigDL154
This paper presents BigDL (adistributeddeeplearning framework for Apache Spark), which allows deep learning applications to run on the Apache Hadoop/Spark cluster so as to directly process the production data, and as a part of the end-to-end data analysis pipeline for deployment and management.
- 132
- High Quality Entity Segmentation115
CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop.
- Identifying Pine Wood Nematode Disease Using UAV Images and Deep Learning Algorithms106
A new network, SCANet (spatial-context-attention network), to identify pine nematode disease based on unmanned aerial vehicle (UAV) multi-spectral remote sensing images and a spatial information retention module is designed to reduce the loss of spatial information.
- Open World Entity Segmentation103
This work proposes a CondInst-like fully-convolutional architecture with two novel modules specifically designed to exploit the class-agnostic and non-overlapping requirements of ES, and investigates the feasibility of convolutional center-based representation to segment things and stuffs in a unified manner.
- Best-Buddy GANs for Highly Detailed Image Super-resolution95
This work considers the single image super-resolution (SISR) problem, and proposes best-buddy GANs (Beby-GAN) for rich-detail SISR, a region-aware adversarial learning strategy that directs the model to focus on generating details for textured areas adaptively.
- Image Synthesis via Semantic Composition75
A novel approach to synthesize realistic images based on their semantic layouts hypothesizes that for objects with similar appearance, they share similar representation, and proposes a dynamic weighted network constructed by spatially conditional computation.
- Multi-Scale Aligned Distillation for Low-Resolution Detection74
The idea of spatially aligning feature maps between models of varying input resolutions by shifting feature pyramid position is explored and crossed feature-level fusion is proposed to dynamically fuse teacher’s multi-resolution features to guide the student better.
- 66
- Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision65
A conceptually simple, strong, and efficient framework for fully- and weakly-supervised panoptic segmentation, called Panoptic FCN, which encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
- RGB-D Co-attention Network for Semantic Segmentation47
The extensive experiments validate the effectiveness of CANet in fusing RGB and D features, achieving the state-of-the-art performance on two challenging RGB-D semantic segmentation datasets, i.e., NYUDv2, SUN-RGBD.
- Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model36
Reason3D is introduced, a novel LLM designed for comprehensive 3D understanding that processes point cloud data and text prompts to produce textual responses and segmentation masks, enabling advanced tasks such as 3D reasoning segmentation, hierarchical searching, express referring, and question answering with detailed mask outputs.
- Dual Associated Encoder for Face Restoration36
This work proposes a novel dual-branch framework named DAEFR, which introduces an auxiliary LQ branch that extracts crucial information from the LQ inputs and incorporates association training to promote effective synergy between the two branches, enhancing code prediction and output quality.
- PointINS: Point-Based Instance Segmentation34
This paper proposes an instance-aware convolution that decomposes this mask representation learning task into two tractable modules as instance- aware weights and instance-agnostic features, improving mask learning efficiency by avoiding employing several independent convolutions.
- 34
- UniGS: Unified Representation for Image Generation and Segmentation33
A novel unified representation of diffusion models for image generation and segmentation using a colormap to represent entity-level masks is introduced, addressing the challenge of varying entity numbers while aligning the representation closely with the image RGB domain.
- 32
- ICM-3D: Instantiated Category Modeling for 3D Instance Segmentation29
This paper proposes ICM-3D, a single-step method to segment 3D instances via instantiated categorization and shows that it obtains inspiring performance across multiple frameworks, backbones and benchmarks.
- Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation28
A unified framework, Reference Twice (RefT), is introduced to exploit the relationship between support and query features for FSIS and related tasks, demonstrating that support object queries encode key factors after base training, allowing query features to be enhanced twice at both feature and query levels.
- 27
- Faster R-CNN for Marine Organism Detection and Recognition Using Data Augmentation27
Three data augmentation methods are proposed dedicated to underwater-imaging, where the inverse process of underwater image restoration is used to simulate different marine turbulence environments, and Perspective transformation and Illumination synthesis are proposed.
- 25
- Dual Degradation Representation for Joint Deraining and Low-Light Enhancement in the Dark21
A novel two-stage model called L2RIRNet is introduced, which innovatively integrates low-light enhancement and deraining into a single framework in real-world settings and contributes a dataset containing both synthetic and real-world low-light-rainy images.
- 17
- Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer16
This work proposes DeT, a method that adapts DiT models to improve motion transfer ability and introduces a simple yet effective temporal kernel to smooth DiT features along the temporal dimension, facilitating the decoupling of foreground motion from background appearance.
- 16
- Rethinking Evaluation Metrics of Open-Vocabulary Segmentaion16
Novel evaluation metrics, namely Open mIoU, Open AP, and Open PQ, tailored for three open-vocabulary segmentation tasks are designed, which demonstrate that the relative subjectivity of similarity distance can still well evaluate the open ability of the existing open- vocabulary segmentation methods.
- 16
- CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation14
A novel Class-Agnostic Semi-Supervised Learning (CA-SSL) framework is proposed to achieve a more favorable task-specificity balance in extracting training signals from unlabeled data and introduces a warmup training stage to avoid underfitting/overfitting when fine-tuned on the ground-truth labels in detection and segmentation tasks.
- Controllable 3D Outdoor Scene Generation via Scene Graphs13
An interactive system that transforms a sparse scene graph into a dense Bird's Eye View Embedding Map, which guides a conditional diffusion model to generate 3D scenes that match the scene graph description.
- Automatically Discovering Novel Visual Categories With Adaptive Prototype Learning13
A novel adaptive prototype learning method is proposed that leverages prototypes to emphasize category discrimination and alleviate the issue of missing annotations for novel classes to discover unknown categories when a certain number of classes are already known.
- 12
- 9
- 7
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation5
This work addresses the problem of efficient and stable video semantic segmentation using a novel yet simple Temporal Feature Correlation (TFC) module that selectively reuse label-consistent features across frames through linear interpolation and update others through sparse multi-scale deformable attention.
- CFCI-Net: Cross-Modality Feature Calibration and Integration Network for RGB-D Semantic Segmentation5
- 5
- Application of improved deep learning algorithm in obstacle avoidance of UAV4
A refined version of the You Only Look Once (YOLO) algorithm is introduced, termed Improved YOLO (I-YOLO), which not only maintains the swift detection speed inherent in the original YOLO but also augments its feature enhancement network.
- 4
- 2
- 2
- 2
- An Intelligent Design Model for the Thin-Walled Steel Perforated Member2
This paper describes work that aims to use neural network technology to establish an intelligent design model for prediction of the ultimate load of thin-walled steel perforated sections.
- 2
- 1
- 1
- Attribution Analysis-based Concept Alignment: A Human-in-the-loop Data Debugging Framework–
Inspired by human-AI alignment, AACA (Attribution Analysis-based Concept Alignment), a human-in-the-loop framework that mitigates bias in the training set by aligning the concepts used by humans and AI during the decision-making process is introduced.
- Uncertainty-guided classification-regression framework for hyperspectral underwater depth estimation–
- –
- A topological reconstruction method for building point clouds integrating deep semantic segmentation and adjacency constraints–
A topological reconstruction method integrating deep semantic segmentation and adjacency constraints is proposed, achieving high-precision component identification via joint network optimization and confirming the effectiveness of boundary regularization in enhancing consistency.
- –
- –
- Research on the influence of artificial intelligence technology based on big data analysis on modern art creation–
This paper explores the characteristics of intelligent visual art in the context of deep learning, finds its advantages that can be combined with artistic expression, and creates a new form of visual art creation expression based on deep learning.
- –
- –
- Combination of multiple observation videos based on face angle estimation–
A combination method of multiple observation videos based on face angle estimation is proposed to solve the problem of storage of abundant useless data and difficulty for searching and analyzing of observation videos.
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 2026-10-15. 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.