9 citations · 14 across the 20 of their papers we have counts for
20 papers
CPath: Class-Conditional Pathway Decoupling for Vision-Language Incremental Object Detection
Lecheng Xu, Feifei Shao, Ouyangzi Ye +5
Incremental Object Detection (IOD) aims to enable detectors to continuously learn novel categories while preserving previously acquired knowledge. However, existing methods suffer…
SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation
Jinsheng Quan, Jianhua Li, Siyi Xie +7
Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approa…
PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning
Hangrui Zhang, Feifei Shao, Yawei Luo +6
In-context learning (ICL) has attracted increasing attention for enabling models to perform new tasks using only a few ``input--output'' prompt examples. However, existing approach…
RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control
Youcan Xu, Jiaxin Shi, Zhen Wang +5
Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcas…
GateMOT: Q-Gated Attention for Dense Object Tracking
Mingjin Lv, Zelin Liu, Feifei Shao +4
While large models demonstrate the strong representational power of vanilla attention, this core mechanism cannot be directly applied to Dense Object Tracking: its quadratic all-to…
IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation
Haoyu Zheng, Jiang Liu, Tianwei Lin +6
Industrial anomaly inspection requires complementary capabilities: explaining an observed defect, localizing its pixels, and synthesizing a controlled edit. We present IAD-Unify, a…
Rendering Multi-Human and Multi-Object with 3D Gaussian Splatting
Weiquan Wang, Jun Xiao, Feifei Shao +3
Reconstructing dynamic scenes with multiple interacting humans and objects from sparse-view inputs is a critical yet challenging task, essential for creating high-fidelity digital…
DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection
Hongyuan Qi, Feifei Shao, Ming Li +2
The rapid evolution of video generation technologies poses a significant challenge to media forensics, as conventional detection methods often fail to generalize beyond their train…
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging
Jie Cao, Zhenxuan Fan, Zhuonan Wang +8
Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT metho…
MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation
Zhuonan Wang, Zhenxuan Fan, Siwen Tan +8
As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dat…
Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering
Weiquan Wang, Feifei Shao, Lin Li +4
High-fidelity rendering of dynamic humans from monocular videos typically degrades catastrophically under occlusions. Existing solutions incorporate external priors-either hallucin…
Unified Personalized Understanding, Generating and Editing
Yu Zhong, Tianwei Lin, Ruike Zhu +9
Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-…
em: Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning
Lin Li, Jiahui Li, Jiaming Lei +3
Compositional zero-shot learning (CZSL) aims to recognize unseen state-object compositions by generalizing from a training set of their primitives (state and object). Current metho…
CoMo: Compositional Motion Customization for Text-to-Video Generation
Youcan Xu, Zhen Wang, Jiaxin Shi +6
While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods f…
MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing
Feifei Shao, Ping Liu, Zhao Wang +3
Point cloud processing (PCP) encompasses tasks like reconstruction, denoising, registration, and segmentation, each often requiring specialized models to address unique task charac…
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization
Feifei Shao, Yawei Luo, Lei Chen +4
Contemporary weakly-supervised object localization (WSOL) methods have primarily focused on addressing the challenge of localizing the most discriminative region while largely over…
Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
Feifei Shao, Yawei Luo, Fei Gao +2
Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when…
Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
Feifei Shao, Yawei Luo, Ping Liu +4
The expensive annotation cost is notoriously known as the main constraint for the development of the point cloud semantic segmentation technique. Active learning methods endeavor t…
Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey
Feifei Shao, Long Chen, Jian Shao +5
Weakly-Supervised Object Detection (WSOD) and Localization (WSOL), i.e., detecting multiple and single instances with bounding boxes in an image using image-level labels, are long-…
Improving Weakly-supervised Object Localization via Causal Intervention
Feifei Shao, Yawei Luo, Li Zhang +4
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perce…