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.
Works31 from public data
- Rethinking Few-shot 3D Point Cloud Semantic Segmentation50
This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant is-sues in the state-of-the-art: foreground leakage and sparse point distribution, and proposes a novel FS-PCS model based on correlation optimization, referred to as Correlation Optimization Segmentation (COSeg).
- Object Segmentation by Mining Cross-Modal Semantics47
A novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features, with the aim of controlling the modal contribution based on relative entropy.
- 44
- TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models35
TUNA is presented, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with a representation encoder that avoids representation format mismatches introduced by separate encoders, outperforming decoupled alternatives in both understanding and generation.
- Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model32
This work introduces a GFS-PCS framework that synergizes dense but noisy pseudo-labels from 3D VLMs with precise yet sparse few-shot samples to maximize the strengths of both, named GFS-VL.
- kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies29
This work introduces a novel training-free strategy, kNN-CLIP, which augments the model with a database of instance embeddings for semantic and panoptic segmentation that achieves zero forgetting and achieves state-of-the-art performance across large-vocabulary semantic and panoptic segmentation datasets.
- What You Have is What You Track: Adaptive and Robust Multimodal Tracking22
This paper proposes a flexible framework for robust multimodal tracking through a novel Heterogeneous Mixture-of-Experts fusion mechanism with adaptive complexity, coupled with a video-level masking strategy that ensures both temporal consistency and spatial completeness - critical for effective video tracking.
- RGB-D Indiscernible Object Counting in Underwater Scenes21
IOCFormer is proposed, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes and IOCFormer-D is proposed to enable the effective usage of depth modality to help count objects hidden in their environments.
- ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis16
ChatMotion is introduced, a multimodal multi-agent framework for human motion analysis that dynamically interprets user intent, decomposes complex tasks into meta-tasks, and activates specialized function modules for motion comprehension.
- Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentation10
A novel solution THE-Mask for VSS is presented, which introduces temporal-aware hierarchical object queries for the first time and achieves state-of-the-art performance on the latest challenging VSS benchmark VSPW without bells and whistles.
- Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning9
It is suggested that video generation is not merely a media tool, but a scalable, generalizable paradigm for visual reasoning, positing that generated frames can act as intermediate reasoning steps between initial states and solutions.
- DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer8
DreamBeast significantly enhances the quality of generated 3D creatures with user-specified part compositions while reducing computational overhead, as demonstrated by extensive quantitative and qualitative evaluations.
- Video Understanding: From Geometry and Semantics to Unified Models6
A structured overview of video understanding is presented by organizing the literature into three complementary perspectives: low-level video geometry understanding, high-level semantic understanding, and unified video understanding models, highlighting a broader shift from isolated, task-specific pipelines toward unified modeling paradigms that can be adapted to diverse downstream objectives.
- Stitched Value Model for Diffusion Alignment2
This work proposes StitchVM, a model stitching framework that efficiently transfers reward models pretrained for clean images to the noisy latent regime, and shows that this approach yields improvements across a broad range of downstream steering and post-training methods.
- Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks1
The proposed Track2View is a dual-view track conditioner that transfers visual context from source to target view through parameter-free geometric operations and learned temporal aggregation, ensuring generalization to arbitrary camera trajectories without memorizing specific motions.
- 1
- –
- –
- Revisiting the Perception-Distortion Trade-off with Spatial-Semantic Guided Super-Resolution–
This work proposes SpaSemSR, a spatial-semantic guided diffusion framework with two complementary guidances that achieves a superior perception-distortion balance, producing both realistic and faithful restorations.
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.