Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works159 from public data
- Pyramid Scene Parsing Network15,291
This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task.
- Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers3,852
This paper deploys a pure transformer to encode an image as a sequence of patches, termed SEgmentation TRansformer (SETR), and shows that SETR achieves new state of the art on ADE20K, Pascal Context, and competitive results on Cityscapes.
- Point Transformer2,467
The Point Transformer design improves upon prior work across domains and tasks and crosses the 70% mIoU threshold for the first time on the challenging S3DIS dataset.
- 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.
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images1,627
An image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address the challenging task of real-time semantic segmentation is proposed and in-depth analysis of the framework is provided.
- PSANet: Point-wise Spatial Attention Network for Scene Parsing1,191
The point-wise spatial attention network (PSANet) is proposed to relax the local neighborhood constraint and achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality.
- Point Transformer V3: Simpler, Faster, Stronger1,171
This paper presents Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the over-all performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns.
- Exploring Self-Attention for Image Recognition946
This work considers two forms of self-attention, pairwise and patchwise, which generalizes standard dot-product attention and is fundamentally a set operator and strictly more powerful than convolution.
- 840
- DriveGPT4: Interpretable End-to-End Autonomous Driving Via Large Language Model795
DriveGPT4 is introduced, a novel interpretable end-to-end autonomous driving system based on LLMs capable of processing multi-frame video inputs and textual queries that facilitates the interpretation of vehicle actions, offers pertinent reasoning, and effectively addresses a diverse range of questions posed by users.
- Prior Guided Feature Enrichment Network for Few-Shot Segmentation764
The PFENet consists of novel designs of a training-free prior mask generation method that not only retains generalization power but also improves model performance and Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks.
- Distilling Knowledge via Knowledge Review717
For the first time in knowledge distillation, cross-stage connection paths are proposed and a new review mechanism is proposed that requires negligible computation overhead, and outperforms other methods on a variety of tasks.
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation610
This paper designs a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid, and presents PointGroup, a new end-to-end bottom-up architecture specifically focused on better grouping the points by exploring the void space between objects.
- PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds591
Different from the existing point convolution operators whose network architectures are often heavily engineered, the PAConv integrates into classical MLP-based point cloud pipelines without changing network configurations and significantly improves baseline performance on both classification and segmentation tasks, yet with decent efficiency.
- 583
- LAVT: Language-Aware Vision Transformer for Referring Image Segmentation569
This work shows that significantly better cross-modal alignments can be achieved through the early fusion of linguistic and visual features in intermediate layers of a vision Transformer encoder network.
- Stratified Transformer for 3D Point Cloud Segmentation564
Stratified Transformer is proposed that is able to capture long-range contexts and demonstrates strong generalization ability and high performance and first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance.
- AnyDoor: Zero-shot Object-level Image Customization539
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations with desired shapes, and proposes to borrow knowledge from video datasets, which can observe various forms of a single object, leading to stronger model generalizability and robustness.
- UPSNet: A Unified Panoptic Segmentation Network469
A parameter-free panoptic head is introduced which solves thepanoptic segmentation via pixel-wise classification and first leverages the logits from the previous two heads and then innovatively expands the representation for enabling prediction of an extra unknown class which helps better resolving the conflicts between semantic and instance segmentation.
- SegStereo: Exploiting Semantic Information for Disparity Estimation383
This paper suggests that appropriate incorporation of semantic cues can greatly rectify prediction in commonly-used disparity estimation frameworks and proposes a unified model SegStereo, which employs semantic features from segmentation and introduces semantic softmax loss, which helps improve the prediction accuracy of disparity maps.
- PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer343
This paper proposes the PhysFormer, an end-to-end video transformer based architecture, to adaptively aggregate both local and global spatio-temporal features for rPPG representation enhancement, and proposes the label distribution learning and a curriculum learning inspired dynamic constraint in frequency domain.
- Semi-supervised Semantic Segmentation with Directional Context-aware Consistency261
This paper proposes to maintain the context-aware consistency between features of the same identity but with different contexts, making the representations robust to the varying environments, and presents the Directional Contrastive Loss (DC Loss) to accomplish the consistency in a pixel-to-pixel manner.
- 226
- 221
- Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation219
This work establishes a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process, and predicts a label to indicate the semantic consistency of the two connected points to enhance point prediction.
- Fully Convolutional Networks for Panoptic Segmentation202
This approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline and outperforms previous box-based and -free models with high efficiency on COCO, Cityscapes, and Mapillary Vistas datasets with single scale input.
- FocalClick: Towards Practical Interactive Image Segmentation183
FocalClick achieves competitive results against SOTA methods with significantly smaller FLOPs and shows significant superiority when making corrections on preexisting masks.
- 167
- PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer160
This paper proposes two end-to-end video transformer based architectures, namely PhysFormer and PhysFormer++, to adaptively aggregate both local and global spatio-temporal features for rPPG representation enhancement, and proposes the label distribution learning and a curriculum learning inspired dynamic constraint in frequency domain.
- Bidirectional Projection Network for Cross Dimension Scene Understanding159
This paper presents a bidirectional projection network (BPNet) for joint 2D and 3D reasoning in an end-to-end manner that achieves top performance on the ScanNetV2 benchmark for both 1D and 2D semantic segmentation.
- UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation143
This work argues that, it is necessary to switch the baseline of SSS from ResNet-based encoders to more capable ViT-based encoders that are pre-trained on massive data, and presents UniMatch V2, inheriting the core spirit of weak-to-strong consistency from V1, but requiring less training cost and providing consistently better results.
- Augmented Feedback in Semantic Segmentation Under Image Level Supervision139
This paper proposes a framework with only image-level supervision that unifies semantic segmentation and object localization with important proposal aggregation and selection modules that greatly reduce the notorious error accumulation problem that commonly arises in weakly supervised learning.
- Dual-Cross Central Difference Network for Face Anti-Spoofing137
Two Cross Central Difference Convolutions are proposed, which exploit the difference of the center and surround sparse local features from the horizontal/vertical and diagonal directions, respectively, and a novel Patch Exchange (PE) augmentation strategy for FAS is proposed via simply exchanging the face patches as well as their dense labels from random samples.
- Detecting Everything in the Open World: Towards Universal Object Detection128
UniDetector is proposed, a universal object detector that has the ability to recognize enormous categories in the open world, and surpasses the traditional supervised baselines by more than 4% on average without seeing any corresponding images.
- Generalized Few-shot Semantic Segmentation123
This paper introduces a new benchmark, called Generalized Few-Shot Semantic Segmentation (GFS- Seg), and proposes the Context-Aware Prototype Learning (CAPL) that significantly improves performance by leveraging the co-occurrence prior knowledge from support samples and dynamically enriching contextual information to the classifier, conditioned on the content of each query image.
- Towards Large-Scale 3D Representation Learning with Multi-Dataset Point Prompt Training117
PPT is introduced, a novel framework for multi-dataset synergistic learning in the context of 3D representation learning that supports multiple pre-training paradigms and achieves state-of-the-art performance on each dataset using a single weight-shared model with supervised multi-dataset training.
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation103
The creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost, is proposed.
- 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.
- Visual Programming for Zero-Shot Open-Vocabulary 3D Visual Grounding97
This work proposes a novel visual programming approach for zero-shot open-vocabulary 3DVG, leveraging the capabilities of large language models (LLMs) and develops an innovative language-object correlation module to extend the scope of existing 3D object detectors into open-vocabulary scenarios.
- GPT4Point: A Unified Framework for Point-Language Understanding and Generation96
GPT4Point, an innovative, groundbreaking point-language multimodal model explicitly designed for unified 3D object understanding and generation within the MLLMframework, is introduced and Pyramid-XL, a point-language dataset annotation engine, is developed to support the expansive needs of 3D object-text pairs.
- MTFormer: Multi-task Learning via Transformer and Cross-Task Reasoning95
It is demonstrated that models with transformer structures are more appropriate for MTL than convolutional neural networks (CNNs), and a novel transformer-based architecture named MTFormer is proposed, which achieves state-of-the-art results with limited network parameters and computations.
- 94
- UniPAD: A Universal Pre-Training Paradigm for Autonomous Driving90
UniPAD is presented, a novel self-supervised learning paradigm applying 3D volumetric differentiable rendering that implicitly encodes 3D space, facilitating the reconstruction of continuous 3D shape structures and the intricate appear-ance characteristics of their 2D projections.
- Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning82
An efficient and effective contrastive learning framework, which generates contrastive views directly on scene-level point clouds by a well-curated data augmentation pipeline and a practical view mixing strategy, and an exquisite design of contrastive cross masks, which targets the reconstruction of point color and surfel normal.
- LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields76
The extensive experiments on the scene-level KITTI-360 dataset, and on the object-level NeRF-MVL show that the LiDAR-NeRF surpasses the model-based algorithms significantly, and a structural regularization method to preserve local structural details is introduced.
- 71
- 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.
- EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions64
This work proposes the EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech abilities while maintaining the leading vision-language performance and surprisingly notices that omni-modal alignment can further enhance vision-language and speech abilities compared with the bi-modal aligned counterparts.
- 59
- Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models57
Orient Anything is introduced, the first expert and foundational model designed to estimate object orientation in a single- and free-view image and achieves state-of-the-art orientation estimation accuracy in both rendered and real images and exhibits impressive zero-shot ability in various scenarios.
- 55
- 50
- 49
- Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation49
A dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect, by set-ting additional branches in the target model during training, and dealing with pixels with diverse properties to-wards adversarial perturbation.
- OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces47
This work proposes remapping and binding the spaces of various pre-trained specialist models together, and presents OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters, which support 3D, audio, image, and language inputs.
- 45
- 38
- 36
- 32
- 31
- 27
- 27
- 24
- 24
- 23
- 22
- 22
- 22
- DreamComposer: Controllable 3D Object Generation via Multi-View Conditions22
Experiments show that DreamComposer is compatible with state-of-the-art diffusion models for zero-shot novel view synthesis, further enhancing them to generate high-fidelity novel view images with multi-view conditions, ready for controllable 3D object reconstruction and various other applications.
- 20
- Hierarchical Interaction Network for Video Object Segmentation from Referring Expressions20
This paper presents an end-to-end hierarchical interaction network (HINet) for the VOSRE problem, which leverages the feature pyramid produced by the visual encoder to generate multiple levels of multi-modal features and extracts signals of moving objects from optical input.
- HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models19
HiRes-LLaVA is proposed, a novel framework designed to efficiently process high-resolution inputs of any size without altering the original contextual and geometric information, and demonstrates the superiority of HiRes-LLaVA on both existing public benchmarks and EntityGrid-QA.
- 19
- 19
- 18
- 18
- 18
- 16
- 16
- 15
- 15
- HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding13
This work proposes a new early-fusion LMM that can fuse multi-modal inputs in the early stage and respond to visual instructions in an auto-regressive manner and devise an efficient training recipe for the proposed model, which harnesses the prior knowledge of the pre-trained models, addressing both the performance limitations and the challenge of resource consumption.
- 13
- 12
- 12
- Influencer Backdoor Attack on Semantic Segmentation11
This work explores backdoor attacks on segmentation models to misclassify all pixels of a victim class by injecting a specific trigger on non-victim pixels during inferences, which is dubbed Influencer Backdoor Attack (IBA).
- 6
- General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments6
This paper uses Deep Generative Networks with a novel training mechanism to eliminate the distribution gap between adversarial and clean samples in feature space of the target DNNs, and proposes a more effective pixel level training constraint to make this achievable, thus enhancing robustness on adversarial samples.
- 5
- 5
- 5
- 5
- 4
- LiT: Unifying LiDAR "Languages" with LiDAR Translator4
The LiDAR Translator (LiT) is introduced, a framework that directly translates LiDAR data across domains, enabling both cross-domain adaptation and multi-domain joint learning.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.