Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks51 from public data
- Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework436
This paper proposes a purely point-based framework for joint crowd counting and individual localization, called Point to Point Network (P2PNet), and proposes a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation.
- Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering426
A novel method of dynamically fuse multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities is proposed, which can robustly capture the high-level interactions between language and vision domains.
- Personalize Segment Anything Model with One Shot400
A training-free Personalization approach for SAM, termed as PerSAM, which effectively adapt SAM for private use without any training, and can enhance DreamBooth to personalize Stable Diffusion for text-to-image generation, which discards the background disturbance for better target appearance learning.
- Rethinking Mobile Block for Efficient Attention-based Models312
This work rethinks lightweight infrastructure from efficient IRB and effective components of Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMB) for lightweight model design.
- 297
- 179
- Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model177
This paper presents Instruct2Act, a framework that utilizes Large Language Models to map multi-modal instructions to sequential actions for robotic manipulation tasks, employing the LLM model to generate Python programs that constitute a comprehensive perception, planning, and action loop for robotic tasks.
- SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking164
This work proposes a novel symmetric multimodal tracking framework called SDSTrack, which introduces lightweight adaptation for efficient fine-tuning, which directly transfers the feature extraction ability from RGB to other domains with a small number of trainable parameters and integrates multimodal features in a balanced, symmetric manner.
- Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers147
This technical report introduces the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions.
- 130
- DIRL: Domain-Invariant Representation Learning for Generalizable Semantic Segmentation99
The domain-invariant representation is constructed which suppresses the effect of the domain-specific style on the quality and correlation of the features and can enhance the robustness of various backbone networks with little computational cost.
- You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction79
This work proposes a lightweight fast Illumination Adaptive Transformer (IAT) which comprises two transformer-style branches: local estimation branch and global ISP branch which could also conduct both object detection and semantic segmentation under various light conditions.
- Learning Where to Focus for Efficient Video Object Detection70
A novel module called Learnable Spatio-Temporal Sampling (LSTS) has been proposed to learn semantic-level correspondences among adjacent frame features accurately and achieves state-of-the-art performance on the ImageNet VID dataset with less computational complexity and real-time speed.
- ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models57
ManipVQA is proposed, a novel framework that infuses MLLMs with manipulation-centric knowledge through a Visual Question-Answering (VQA) format and preserves the original vision-reasoning abilities while incorporating the newly acquired robotic insights.
- Video Object Detection with Locally-Weighted Deformable Neighbors56
This paper proposes LWDN (Locally-Weighted Deformable Neighbors) for video object detection without utilizing time-consuming optical flow extraction networks and adopts brain-inspired memory mechanism to propagate and update the memory feature from keyframes to keyframes, called Memory-Guided Propagation.
- SiamRCR: Reciprocal Classification and Regression for Visual Object Tracking42
A novel siamese tracking algorithm called SiamRCR is proposed, addressing this problem with a simple, light and effective solution, and builds reciprocal links between classification and regression branches, which can dynamically re-weight their losses for each positive sample.
- Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement39
RAG is a Regional-Aware text-to-image Generation method conditioned on regional descriptions for precise layout composition that achieves superior performance over attribute binding and object relationship than previous tuning-free methods.
- OSV: One Step is Enough for High-Quality Image to Video Generation37
This work introduces a two-stage training framework that effectively combines consistency distillation with adversarial training to address video diffusion challenges, and proposes a novel video discriminator design, which eliminates the need for decoding the video latents and improves the final performance.
- VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation34
This work proposes VividPose, an innovative end-to-end pipeline based on Stable Video Diffusion (SVD) that ensures superior temporal stability and enhances the retention of human identity, and introduces a geometry-aware pose controller that utilizes both dense rendering maps from SMPL-X and sparse skeleton maps.
- 23
- MambaGesture: Enhancing Co-Speech Gesture Generation with Mamba and Disentangled Multi-Modality Fusion19
This work presents MambaGesture, a novel framework integrating a Mamba-based attention block, MambaAttn, with a multi-modality feature fusion module, SEAD, achieving state-of-the-art performance in co-speech gesture generation.
- STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation19
This work presents a simple and efficient single-stage VIS framework based on the instance segmentation method CondInst by adding an extra tracking head and proposes a novel bi-directional spatio-temporal contrastive learning strategy for tracking embedding across frames.
- 17
- Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis16
This work presents Unify-Agent, a unified multimodal agent for world-grounded image synthesis, which reframes image generation as an agentic pipeline consisting of prompt understanding, multimodal evidence searching, grounded recaptioning, and final synthesis.
- 15
- UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models15
This work proposes a comprehensive paradigm, termed UniAff, that integrates 3D object-centric manipulation and task understanding in a unified formulation and constructed a dataset labeled with manipulation-related key attributes, comprising 900 articulated objects and 600 tools from 12 categories.
- MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation14
This work introduces a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G, which directly implements the denoising process on gesture sequences and proposes an efficient inference strategy that diminishes the denoising computation by leveraging previously calculated results, thereby achieving a speedup with negligible performance degradation.
- PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models12
PointSeg is presented, a novel training-free paradigm that leverages off-the-shelf vision foundation models to address 3D scene perception tasks and demonstrates impressive segmentation performance across various datasets, all without training.
- RealVVT: Towards Photorealistic Video Virtual Try-on via Spatio-Temporal Consistency11
This work leverages pre-existing video foundation models to introduce RealVVT, a photoRealistic Video Virtual Try-on framework tailored to bolster stability and realism within dynamic video contexts, offering a viable solution for practical applications within the realms of fashion e-commerce and virtual fitting environments.
- NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models11
NoiseBoost is proposed, a broadly applicable and simple method for alleviating hallucinations for MLLMs through the integration of noise feature perturbations and pioneerly enables semi-supervised learning for MLLMs, unleashing the power of unlabeled data.
- 10
- 7
- 6
- SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation5
Experimental results indicate that the VLM-based method significantly enhances keypoint detection accuracy and task success rates, providing a more flexible and general solution for robotic garment manipulation.
- 5
- 4
- Atlas-based linear volume-of-interest (ABL-VOI) image correction4
A method to recover the lost low-frequency information in volume-of-interest imaging by assuming that the correct scaling can be modeled by a linear transformation of the object densities and employing an atlas of correctly scaled volumes.
- 3
- 3
- Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge2
FreeCure, a framework that improves the prompt consistency of personalization models with their latent foundation models'knowledge, and introduces a novel foundation-aware self-attention module, coupled with an inversion-based process to bring well-aligned attribute information to the personalization process.
- Dual Path Transformer with Partition Attention2
This paper introduces a novel attention mechanism, called dual attention, which is both efficient and effective, and presents a hierarchical vision backbone called DualFormer, which achieves 81.5\% top-1 accuracy on ImageNet, outperforming the recent state-of-the-art MPViT-XS by 0.6%, and evaluates the effectiveness of the model on several computer vision tasks.
- 1
- 1
- 1
- 1
- Learning Motion Priors for Efficient Video Object Detection.1
This paper first initialize some motion priors for each location and then use them to propagate features across frames and achieves state-of-the-art performance on the ImageNet VID dataset with real-time speed.
- –
- –
- AdapNet: Adaptive Noise-Based Network for Low-Quality Image Retrieval–
A novel setting for low-quality image retrieval is introduced, and an innovative adaptive noise-based loss function is introduced, which dynamically adjusts its focus on the gradient in accordance with image quality, thereby augmenting the learning of unknown noisy samples during training and enhancing intra-class compactness.
- A Radiotherapy Positioning Method for Both Coarse Guidance and Precise Verification Based on Integration of AR and Optical Surface Imaging–
The combination of AR and optical surface has utility and feasibility for patient positioning, in terms of both safety and accuracy, and its feasibility in clinical workflow is evaluated.
- –
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 2026-10-14. 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.