17 citations · 45 across the 13 of their papers we have counts for
13 papers
FlowComposer: Composable Flows for Compositional Zero-Shot Learning
Zhenqi He, Lin Li, Long Chen
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on visio…
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…
Zero-shot Compositional Action Recognition with Neural Logic Constraints
Gefan Ye, Lin Li, Kexin Li +2
Zero-shot compositional action recognition (ZS-CAR) aims to identify unseen verb-object compositions in the videos by exploiting the learned knowledge of verb and object primitives…
A Survey on Multimodal Benchmarks: In the Era of Large AI Models
Lin Li, Guikun Chen, Hanrong Shi +2
The rapid evolution of Multimodal Large Language Models (MLLMs) has brought substantial advancements in artificial intelligence, significantly enhancing the capability to understan…
From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation
Hanrong Shi, Lin Li, Jun Xiao +2
Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-structure representation based on panoptic segmentation masks. Despite remarkable progress in PSG, almo…
Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainer
Jiaming Lei, Lin Li, Chunping Wang +2
Benefiting from strong generalization ability, pre-trained vision language models (VLMs), e.g., CLIP, have been widely utilized in zero-shot scene understanding. Unlike simple reco…
Compositional Zero-shot Learning via Progressive Language-based Observations
Lin Li, Guikun Chen, Zhen Wang +2
Compositional zero-shot learning aims to recognize unseen state-object compositions by leveraging known primitives (state and object) during training. However, effectively modeling…
Compositional Feature Augmentation for Unbiased Scene Graph Generation
Lin Li, Guikun Chen, Jun Xiao +3
Scene Graph Generation (SGG) aims to detect all the visual relation triplets \texttt{sub}, \texttt{pred}, \texttt{obj} in a given image. With the emergence of various advance…
Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models
Lin Li, Jun Xiao, Guikun Chen +3
Pretrained vision-language models, such as CLIP, have demonstrated strong generalization capabilities, making them promising tools in the realm of zero-shot visual recognition. Vis…
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
Lin Li, Long Chen, Hanrong Shi +4
The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over th…
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
Lin Li, Jun Xiao, Hanrong Shi +4
Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth annotation qualities of mainstream SGG datasets, i.e., they assume: 1) all the manually ann…
The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation
Lin Li, Long Chen, Yifeng Huang +3
Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG da…
Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation
Jiahui Li, Kun Kuang, Lin Li +4
Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans. However, thei…