41 citations · 134 across the 27 of their papers we have counts for
12 papers · 1 filter
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
Hongchang Liu, Jian Liu, Yujuan Ding +5
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view d…
BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding
Yijie Su, Yakun Zhu, Yi Bin +5
Language-guided 3D affordance grounding aims to localize functional regions on 3D objects according to interaction intents. However, existing methods exhibit poor generalization to…
GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning
Yakun Zhu, Yi Bin, Yujuan Ding +5
Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete tokens, limitin…
Reconstruction-Shift Discrimination via Mask-Guided Latent Diffusion for Medical Anomaly Detection
Yibo Wan, Jinyu Cai, Yunhe Zhang +2
Unsupervised medical anomaly detection learns normal anatomical patterns from healthy training images and identifies deviations at test time. Reconstruction-based and diffusion-bas…
VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding
Haiyue Zhang, Yi Bin, Xun Jiang +5
Large vision-language models (LVLMs) have achieved significant progress in video understanding, yet understanding long videos remains challenging due to the large number of visual…
OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
Haoxi Zeng, Qiankun Liu, Yi Bin +5
Open-Vocabulary Segmentation (OVS) aims to segment image regions beyond predefined category sets by leveraging semantic descriptions. While CLIP based approaches excel in semantic…
HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
Haoxi Zeng, Haoxuan Li, Yi Bin +4
Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due…
GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation
Weijia Dou, Xu Zhang, Yi Bin +5
Recent attempts to transfer features from 2D Vision-Language Models (VLMs) to 3D semantic segmentation expose a persistent trade-off. Directly projecting 2D features into 3D yields…
Exploring Deeper! Segment Anything Model with Depth Perception for Camouflaged Object Detection
Zhenni Yu, Xiaoqin Zhang, Li Zhao +2
This paper introduces a new Segment Anything Model with Depth Perception (DSAM) for Camouflaged Object Detection (COD). DSAM exploits the zero-shot capability of SAM to realize pre…
MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning
Thong Nguyen, Yi Bin, Xiaobao Wu +6
Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perf…
Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination
Haoxuan Li, Yi Bin, Junrong Liao +2
Most existing image-text matching methods adopt triplet loss as the optimization objective, and choosing a proper negative sample for the triplet of <anchor, positive, negative> is…
Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval
Yi Bin, Haoxuan Li, Yahui Xu +3
Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for text…