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.
Works36 from public data
- CLIP-guided Prototype Modulating for Few-shot Action Recognition106
This work presents a CLIP-guided prototype modulating framework called CLIP-FSAR, which consists of two key components: a video-text contrastive objective and a prototype modulation that bridges the task discrepancy between CLIP and the few-shot video task by contrasting videos and corresponding class text descriptions.
- Deep Metric Learning for Open World Semantic Segmentation106
This paper adopts the Deep Metric Learning Network (DMLNet) with contrastive clustering to implement open-set semantic segmentation, which behaves like a human being, which is able to identify OOD objects and gradually learn them with corresponding supervision.
- Consistent Prompting for Rehearsal-Free Continual Learning74
A novel prompt-based method, Consistent Prompting (CPrompt), is proposed to enhance prediction robustness and boost prompt selection accuracy and achieves state-of-the-art performance on multiple continual learning benchmarks.
- Open-set 3D Object Detection46
An open-set 3D object detector is proposed, which aims to identify known objects, like the closed-set detection, and (2) identify unknown objects and give their accurate bounding boxes, and the proposed method combining metric learning and unsupervised clustering is called the MLUC network.
- A lightweight multi-scale context network for salient object detection in optical remote sensing images41
This paper proposes a multi-scale context network, namely MSCNet, for SOD in optical RSIs, and designs an attention-based pyramid feature aggregation mechanism for gradually aggregating and refining the salient regions from the multi- scale context extraction module.
- 32
- SAD: Segment Any RGBD25
The Segment Any RGBD (SAD) model is proposed, which is specifically designed to extract geometry information directly from images, inspired by the natural ability of humans to identify objects through the visualization of depth maps, thus providing cues with enhanced geometry information and mitigating the issue of over-segmentation.
- CMDFusion: Bidirectional Fusion Network With Cross-Modality Knowledge Distillation for LiDAR Semantic Segmentation25
This work proposes a Bidirectional Fusion Network with Cross-Modality Knowledge Distillation (CMDFusion) and shows that this scheme achieves the best performance among all fusion-based methods on SemanticKITTI and nuScenes datasets.
- 24
- 24
- LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving19
LargeAD, a versatile and scalable framework designed for large-scale 3D pretraining across diverse real-world driving datasets, leverages VFMs to extract semantically rich superpixels from 2D images, which are aligned with LiDAR point clouds to generate high-quality contrastive samples, and introduces several key innovations.
- 19
- 17
- 13
- Enlarging Instance-specific and Class-specific Information for Open-set Action Recognition12
A novel Prototypical Similarity Learning (PSL) framework is proposed to keep the instance variance within the same class to retain more IS information and to enlarge the instance-specific and classspecific information contained in the feature for better performance.
- 11
- Data Pyramid for Embodied Manipulation: A Survey8
This work organizes the embodied data ecosystem as a pyramidspanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity.
- Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations8
The feasibility of self-supervised motion prediction with only unlabeled Li-DAR point clouds is explored and the significant superiority of this approach over the state-of-the-art self-supervised methods is demonstrated.
- iControl3D: An Interactive System for Controllable 3D Scene Generation5
iControl3D is presented, a novel interactive system that empowers users to generate and render customizable 3D scenes with precise control and enables users to build a radiance field of their scene online and navigate the entire scene.
- 5
- 4
- 4
- 2
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- SimMAT: Exploring Transferability from Vision Foundation Models to Any Image Modality–
SimMAT can improve the segmentation performance (mIoU) from 22.15% to 53.88% on average for evaluated modalities and consistently outperforms other baselines and can raise awareness of cross-modal transfer learning and benefit various fields for better results with vision foundation models.
- SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality–
In SimCMF, a simple and effective framework to study cross-modal fine-tuning from vision foundation models trained on natural RGB images to other imaging modalities of different physical properties, a novel cross-modal alignment module is proposed to address the modality misalignment problem.
- –
- –
Publication data from OpenAlex; 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.