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
- Heng-Chao LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works43 from public data
- PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images99
This work proposes a negative prompt calibration (NPC) method based on the nonoverlapping nature of instance masks, where overlapping masks are used as negative signals to refine segmentation, and presents a novel pointly-supervised SAM (PointSAM).
- 70
- Transformation-Invariant Network for Few-Shot Object Detection in Remote-Sensing Images48
This work proposes integrating a feature pyramid network (FPN) and utilizing prototype features to enhance query features, thereby improving existing FSOD methods and tackling the issue of spatial misalignment caused by orientation variations between the query and support images by introducing a transformation-invariant network (TINet).
- 28
- AFDet: Toward More Accurate and Faster Object Detection in Remote Sensing Images28
This article proposes a more accurate and faster detector named AFDet, which is composed of a backbone pretrained on ImageNet and a head that includes a center prediction branch (CPB), semantic supervision branch (SSB), and boundary estimation branch (BEB).
- 27
- SSLChange: A Self-Supervised Change Detection Framework Based on Domain Adaptation26
A novel self-supervised contrastive framework applicable to the RSCD task, which promotes the model to accurately capture spatial, structural, and semantic information through the domain adapter (DA) and the hierarchical contrastive head.
- 24
- Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs23
Patch-as-Decodable Token (PaDT), a unified paradigm that enables MLLMs to directly generate both textual and diverse visual outputs, is introduced, suggesting PaDT consistently achieving state-of-the-art performance, even compared with significantly larger MLLM models.
- 23
- 22
- 22
- PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection18
A Prototype-based Soft-labels (PS) strategy through assessing similarities between low-confidence pseudo-labels and category prototypes as soft-labels to unleash their potential, which substantially mitigates the constraints posed by few-shot samples.
- Clip-Guided Source-Free Object Detection in Aerial Images16
This work utilizes Contrastive Language-Image Pre-training (CLIP) to guide the generation of pseudo-labels, termed CLIP-guided Aggregation (CGA), and leverages CLIP’s zero-shot classification capability to aggregate its scores with the original predicted bounding boxes, enabling us to obtain refined scores for the pseudo-labels.
- 16
- 14
- COUD: Continual Urbanization Detector for Time Series Building Change Detection12
A two-stage continual urbanization detector (COUD) for time series urban building change detection task that employs self-supervised pretraining for feature refinement, and performs optimization through temporal distillation approach is proposed.
- 8
- MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation7
This work introduces MuSS, a large-scale, dual-track dataset tailored for multi-shot video and S2V generation, and proposes the Cinematic Narrative Benchmark, featuring a visual-logic-driven paradigm and a novel Anti-Copy-Paste Variance (ACP-Var) metric to rigorously assess continuous storytelling and 3D structural consistency.
- 7
- 7
- 6
- 6
- Toward Distortion-Aware Change Detection in Realistic Scenarios6
Experimental results in 2 large-scale realistic scenarios demonstrate that the proposed reusable self-supervised framework for bitemporal geometric distortion can alleviate the bitemporal geometric distortion in CD tasks.
- On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning6
An effective and realistic attack method is proposed that better produces poisoned samples without access to benign samples, and an effective in-distribution attack objective is derived, and two TTA-aware attack objectives are designed.
- RCCFormer: A Robust Crowd Counting Network Based on Transformer4
This paper proposes a robust Transformer-based crowd counting network, termed RCCFormer, specifically designed for background suppression and scale awareness, and incorporates a Multi-level Feature Fusion Module (MFFM), which meticulously integrates features extracted at diverse stages of the backbone architecture.
- Exploring Generalizable Pretraining for Real-World Change Detection via Geometric Estimation4
This article proposes a self-supervision motivated CD framework with geometric estimation, called “MatchCD,” which utilizes the zero-shot capability to optimize the encoder with self-supervised contrastive representation and CD to simultaneously handle the bitemporal unalignment and object change issues.
- Few-Shot Object Detection With Contrastive Enhancement Loss Guided by Object Association Graph in Remote Sensing Images3
A few-shot object detection with contrastive enhancement loss guided by object association graph (OAG-FSOD), which effectively strengthens the feature representation of objects, thereby improving the performance of few-shot object detection in remote sensing images.
- 3
- Prompt-Calibrated SAM 3 for Open-Vocabulary Remote-Sensing Semantic Segmentation2
ProC-SAM3 is proposed, which calibrates SAM3’s prompt interface for remote-sensing OVSS from three complementary aspects and achieves an average mIoU of 56.1%, outperforming the previous best training-free method by 3.9 percentage points.
- 2
- 2
- Piecewise Self-Adaption Weighted attention for the detection of concentrated distributions of ships in SAR images2
A novel parameter-free Piecewise Self-Adaptation Weighted (PSAW) attention module is introduced, which is designed to mitigate semantic ambiguities and enhance the clarity of feature boundaries within feature maps.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
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 2026-10-12. 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.